remote sensing

Article
Assessment of Machine Learning Algorithms for
Automatic Benthic Cover Monitoring and Mapping
Using Towed Underwater Video Camera and
High-Resolution Satellite Images
Hassan Mohamed 1,* ID , Kazuo Nadaoka 2 and Takashi Nakamura 2
1 Department of Geomatics Engineering, Shoubra Faculty of Engineering, Benha
University, Cairo 11672, Egypt
2 Department of Transdisciplinary Science and Engineering, School of Environment and Society, Tokyo
Institute of Technology, O-okayama W8-13 2-12-1, Meguro-ku, Tokyo, 152-8552, Japan;
[email protected] (K.N.); [email protected] (T.N.)
* Correspondence: [email protected] or [email protected]
CHECK EOJ
Received: 28 March 2018; Accepted: 16 May 2018; Published: 17 May 2018 updates

Abstract: Benthic habitat monitoring is essential for many applications involving biodiversity,
marine resource management, and the estimation of variations over temporal and spatial scales.
Nevertheless, both automatic and semi-automatic analytical methods for deriving ecologically
significant information from towed camera images are still limited. This study proposes a
methodology that enables a high-resolution towed camera with a Global Navigation Satellite
System (GNSS) to adaptively monitor and map benthic habitats. First, the towed camera finishes
a pre-programmed initial survey to collect benthic habitat videos, which can then be converted to
geo-located benthic habitat images. Second, an expert labels a number of benthic habitat images to
class habitats manually. Third, attributes for categorizing these images are extracted automatically
using the Bag of Features (BOF) algorithm. Fourth, benthic cover categories are detected
automatically using Weighted Majority Voting (WMV) ensembles for Support Vector Machines
(SVM), K-Nearest Neighbor (K-NN), and Bagging (BAG) classifiers. Fifth, WMV-trained ensembles
can be used for categorizing more benthic cover images automatically. Finally, correctly
categorized geo-located images can provide ground truth samples for benthic cover mapping
using high-resolution satellite imagery. The proposed methodology was tested over Shiraho,
Ishigaki Island, Japan, a heterogeneous coastal area. The WMV ensemble exhibited 89% overall
accuracy for categorizing corals, sediments, seagrass, and algae species. Furthermore, the same
WMV ensemble produced a benthic cover map using a Quickbird satellite image with 92.7%
overall accuracy.

Keywords: machine learning algorithms; benthic cover monitoring; towed underwater video
camera; hybrid classifiers

1. Introduction
Monitoring and mapping of benthic habitats using remote sensing systems and machine
learning approaches can expand our understanding of living conditions in such environments, and
ensure, with appropriate supervision, the survival of occupying species over time. Recently,
developments in high-quality video cameras have meant that data from videos from towed cameras
can be accurately recorded and geo-located. As a result, the capability of recording geo-located
sampling points enables scientists to accurately and repeatedly survey the same locations to assess
the spatiotemporal variations and long-term changes in these areas. Furthermore, high-quality
towed video cameras can

Remote Sens. 2018, 10, 773; doi:10.3390/rs10050773 www.mdpi.com/journal/remotesensing

Remote Sens. 2018, 10, 773 2 of 17

record clear images of seafloor benthic habitats, and cover large regions quickly without affecting
the environment [1], consequently providing a potential system for monitoring benthic habitats
within coastal ecosystems. The towed video cameras are also much cheaper than acoustic
backscatter systems [2].
However, the analysis of recorded towed videos in marine applications is usually performed
manually [3], and automatic feature extraction is not often applied [4,5]. Therefore, the automatic
classification of benthic habitats from towed underwater photos is a comparatively novel and
innovative method [6]. The implementation of appropriate algorithms is fairly difficult, and many
complexities are still associated with the video data of a towed system, including unstable
illumination due to limited energy and variable velocities, angles, and elevations of the camera
above the seafloor. In addition, the algorithms have to analyze a wide spectrum of overlapping
features spread over the seafloor.
Examples of attempts used for benthic cover detection with underwater video systems can be
found in the literature [7]. However, most researchers process photos captured from towed cameras
mounted on remotely operated vehicles (ROVs) or autonomous underwater vehicles (AUVs) [3].
Adam et al. [2] investigated a random forest, neural network, and classification trees machine
learning algorithms to classify two seabed categories, sand and maerl, using (RGB or LAB) pixels
manually extracted from images captured by an ROV. This research assumed that the ROV had a
constant speed and altitude above the seafloor surface. The resulting classification accuracies from
all machine learning algorithms were high, slightly outperforming the classification trees method.
Ludtke et al. [3] automatically detected Pogonophora seafloor coverage successfully with Support
Vector Machines (SVM), K-Nearest Neighbor (K-NN), classification trees, and Naïve Bayes
supervised machine learning algorithms. A data set of 4108 geo-referenced video mosaics captured
using an ROV with a 3 m elevation above the seabed surface were used for Pogonophora
recognition. These mosaic data regions were portioned into regular grid cells. The detection was
performed using 49 numerical image attributes extracted from each cell. SVM results outperformed
other approaches, with a classification accuracy of up to 98.86%. Jan et al. [8] used 26 color, shape,
and texture attributes extracted from stereo images captured using an AUV to automatically
characterize nine benthic habitats. The extracted attributes were adjusted using hue-saturation
values, local binary patterns, and simple patch-gap summaries. The Random Forest (RF) classifier
achieved an overall accuracy of 84% when compared to nine habitat classes assigned manually by a
human expert. In addition, Paul et al. [9] proposed the Bag of Features (BOF) approach for attribute
extraction with a Gaussian classifier to detect three classes, sand, seagrass, and algae, from AUV
captured images. The proposed approach classified habitats correctly with 643 corrected images
from a total of 730, an accuracy rate of 88%.
Teixido et al. [5] developed Seascape, a software program for obtaining semi-automatically
segmented images of benthic habitats from underwater images. Bewley et al. [6] applied the
same program with a hierarchical classification scheme to collect Australian benthic data sets
(BENTHOZ-2015) using AUV field survey images from around Australia. This program analyzed
images individually, and the input sampling points needed to be assigned manually to each image.
The final outputs were segmented images with benthic habitat classes.
Nonetheless, previous studies performed to automatically extract benthic habitats from an
underwater towed camera directly attached to a vessel are still limited. For instance, Paul et al. [10]
used the BOF approach with a Gaussian classifier to extract eight classes from images captured
using a towed camera. These classes included algae, corals, sponges, rhodoliths, uncolonized, and
mixed classes. Approximately 55 images were divided according to 75% training and 25% testing
sets, and were used for the calibration and validation processes of the proposed model. This
process is very challenging because of the large number of classes, and non-uniform and poor
lighting. The classes also share the same region, resulting in significant similarities between them.
As a result, the proposed approach exhibited some significant confusion between the classes, or
completely failed to differentiate between some classes; thus, improvement is required.
 From a literature review, benthic cover classification using remote sensing techniques can be
applied using various approaches, for example, the use of hyperspectral images with spectral
libraries or look-up tables (LUTs) [11–14]. Alternatively, the integration of satellite images, or
underwater videos with a multibeam echosounder (MBES), can also be used [15–18]. Finally, there
is also the use of high-resolution images with in-situ video samples [19–22].
However, the abovementioned approaches have a number of drawbacks. The satellite
hyperspectral images mostly have coarse spatial resolutions. Alternatively, the airborne
hyperspectral images have limited coverage for large areas, are more expensive than multispectral
satellite images, are computationally hard to process, and the produced datasets from these images
are voluminous even when covering comparatively small areas [23]. On the other hand, MBES is
relatively expensive. The production of benthic maps from multispectral satellite images has
remained challenging [24]. Both multispectral images and MBES require field video samples that are
usually analyzed manually. This is a time consuming and labor intensive process which is ill-suited
for mapping large tracts of coastlines [25].
The contribution of this study is the proposal of a semi-automated system for benthic
cover monitoring and mapping. Field survey video samples were analyzed automatically,
and high-resolution satellite imagery was classified using these samples. A number of attributes
were collected using the BOF approach from video images. These images were captured using an
underwater towed high-resolution camera and geo-located by a Global Navigation Satellite System
(GNSS). Three machine learning algorithms K-NN, SVM, and Bagging (BAG) outcomes were
assembled using the Weighted Majority Voting (WMV) approach for benthic cover detection. The
trained WMV ensemble was used for categorizing more geo-located images which can provide
ground truth samples for benthic mapping. Formerly, a Quickbird image was classified using the
correctly categorized geo-located images collected over the same field survey path. The
abovementioned classification process was performed using the same K-NN, SVM, and BAG
algorithms, and assembled using the WMV method. Finally, the achieved results for both benthic
cover detection and mapping were then evaluated and compared using the overall accuracy and the
Kappa statistical criteria.

2. Materials and Methods

2.1. Study Area

The study area was the Shiraho subtropical territory, which is positioned in the south-eastern
part of Ishigaki Island, Japan (see Figure 1). It is an irregular heterogeneous shallow, low turbidity
water area with a 3.5 m maximum depth. The Shiraho area has rich marine biodiversity that
includes various species, such as seagrass and corals, fishes, and has the largest colony in the
northern hemisphere of a blue ridge coral (Heliopora coerulea). It also has a reefscape with a well-
developed fringing reef (reef slope, reef crest, channels, and moat) that includes complex patches of
branching (Acropora spp., Montipora spp., Porites cylindrica, etc.) and massive corals (Porites spp.,
Heliopora coerulea, etc.) and seagrass. Furthermore, there is also a wide range of sediments including
mud, sand, cobble, and boulders.

2.2. Imagery Data

A Quickbird satellite image was used for benthic cover mapping of the study area with a 0.6 m
spatial resolution. The image was acquired during calm weather conditions on 20 July 2007.
However, field data for the Shiraho area were collected on 21 August 2016. Although there was a
time difference between imagery collection and the field data observations, the Shiraho area did not
experience tsunamis or big currents until 2014 [21]. Nevertheless a big typhoon occurred in 2015
around this area, but the benthic habitats experienced no significant changes. The required values
for radiometric calibrations are presented in metadata files of the images.
 Figure 1. The study area of Shiraho, Ishigaki Island, Japan.

2.3. Benthic Cover Field Data

Benthic cover field data were collected from field surveys performed on 21st August, 2016.
The Shiraho area experienced socio-ecological spatial stability during these observation years until
2014 [21]. Moreover the single big typhoon that occurred in 2015 did not cause significant changes
in this area. The collection of marine images was undertaken using local knowledge of the area
and a Quickbird image inspection. Underwater images were acquired using a low-cost compact
high-resolution video camcorder (GoPro Hero 3, 12 mega pixel effective photo resolution, 12 mega
pixel camcorder sensor resolution, and 30 frames per second with a wide field of view), placed just
below the water surface, so that the shallow seabed could be monitored. An array of 3 h of video
recordings from the survey trip was collected and geo-located using a Lawrence GNSS system.
These videos enabled the extraction and further analysis of many high-quality images. A free video
to JPG converter program was used for image extraction from the video files with a 2 s image
interval synchronized with the GNSS surveys. A sample of 2000 images with known locations using
a GNSS system was extracted and labeled manually for the four classes (see Figure 2). These sample
images were used for validating and calibrating all algorithms in the benthic cover detection
process. Formerly, about 1000 more images were categorized with the trained ensemble algorithms,
and checked individually. Finally, 3000 points were collected from the field survey path over
Shiraho study area, constituting the field data for benthic mapping from the Quickbird image (see
Figure 3).
Figure 2. Various examples of seafloor still images obtained with GoPro Hero 3 towed video camera
for each habitat class over Shiraho study area: (a) algae, (b) corals, (c) seagrass, and (d) sediments
samples.

Figure 3. The field survey path over Shiraho study area, Ishigaki Island, Japan.
2.4. Methodology
The proposed framework for benthic cover detection and mapping over the Shiraho coral reef
area was performed using the following steps:

1- An array of video recordings was converted to geo-located images using a free video to image
converter program with 2 s intervals synchronized with the GNSS recorded locations.
2- Approximately 2000 converted images were labeled with four benthic cover categories algae,
sediments, seagrass, and corals.
3- The labeled geo-located images were used as inputs to the BOF approach to create the
attributes for automatic detection.
4- Three machine learning classifiers BAG, SVM, and K-NN were ensemble with WMV
algorithm to detect the benthic cover category using the attributes produced from BOF as
inputs and image labels as outputs.
5- Evaluation of the performance of classifiers was performed using independent 75% training
and 25% testing samples.
6- Once the algorithms were validated and calibrated, they were used for categorizing more
images, and the resultant images were checked individually.
7- About 1000 additional images were categorized automatically as correct, and checked
individually for further analysis.
8- Approximately 3000 images correctly categorized with known locations over the field survey
track were used for benthic cover mapping.
9- A Quickbird image was classified using the same ensemble classifiers with WMV approach,
using about 3000 geo-located images with correctly categorized benthic habitats.

The performance of algorithms depended on the overall accuracy (OA) and Kappa statistical
values (Kappa). The OA is the ratio of the number of validation samples that are classified correctly
to the total number of validation samples of the class. Also, the Kappa value is the proportion of
correctly classified validation samples after random agreement is neglected.
All the benthic cover detection and mapping algorithms were implemented in the MATLAB
environment with the subsequent explained parameters for each method.
For image categorization, the BOF approach was performed using the following parameters:
the vocabulary size was 250, the grid point selection method was used for selecting the feature point
locations, the grid step was 16, the block width was 32, and the retained percentage of the strongest
feature from each category was 80%.
Furthermore, the classification approaches were applied for detecting and mapping benthic
cover, using the following parameters:
The Bag approach had 25 trees and 20 splits for each tree. On the other hand, the SVM model
used a polynomial kernel function with a 3rd order polynomial. Finally, K-NN had a K value of five
neighbors, with the city block method for the distance calculation; the applied distance weighting
function method was the squared inverse distance weight. All of these parameters for each
algorithm were selected based on the highest OA and Kappa values.
Finally, the results from each classifier were assembled using a WMV model. In the WMV
ensemble, if all or two classifier outputs agree on a class, the result will be that class. Conversely,
if there are three different values, the resulting class will be produced from the classifier with the
highest accuracy. The proposed method consists of several key procedures, as shown in Figure 4.
 Figure 4. Workflow processing steps of presented methodology for benthic cover detection and
mapping by different approaches.

2.5. Proposed Algorithms for Benthic Cover Recognition and Mapping

2.5.1. Bag of Features

BOF was used for classifying images into categories, as a histogram of visual word occurrences
that represent an image can be generated. These were used to create histograms, known as a bag of
visual words, which can be used for training an image category classifier. The key steps of the BOF
model are as follows [26]. Local features: detection and description of local features by dividing each
image to small sub-images called patches. Codebook collection: the idea is to assemble the patch
descriptors of all patches into clusters; the elements of the resulting clusters are then used as visual
words for each codebook [27]. Feature quantization: after finishing the codebook, each local feature
is assigned to one “visual word” using an unsupervised clustering method, e.g., K-means clustering.
Finally, categorizing the images using the bag of visual words as the inputs for a classifier. Recently,
the BOF model achieved considerable success in the application of image analysis and classification,
because of its simplicity and efficiency [28].
2.5.2. Bagging
Bag is a machine learning algorithm proposed by Breiman [29]. It is an ensemble of decision
trees used to improve the classification accuracy and prediction performance by reducing variance
and avoiding overfitting. The basic idea of bagging is to generate some independent samples with
replacements from the available training data set, and then to fit a model to each of these samples
before finally aggregating these models using majority voting [30]. For a standard training set L of
size n, bagging generates m new training sets Li, i = 1 to m, each of size n, by sampling from the
training set uniformly and with replacements. As a result of sampling with replacements, some
observations may be repeated, whereas others may not be selected at all. This process is known as
bootstrap sampling. The m bootstrap samples are used for fitting the m models, and they return the
class that receives the maximum number of votes [31]. DeFries and Chan [32] found that Bag is more
stable and vigorous against calibration data noise than classification trees.

2.5.3. Support Vector Machines

SVM is a supervised, non-parametric classifier developed by Vapnik [33]. It is a well-adapted
machine learning algorithm for solving linear, non-linear, and high dimensional space classification
problems. In addition, it is the recommended method for the classification of multispectral and
hyperspectral images that have small separated spectral values [34]. In this approach, separation
between classes is performed with an optimal hyper-plane through an n-dimensional spectral space
that maximizes the margin between these classes [35]. The nearest training samples in the training
datasets known as support vectors are used to maximize the margin from the tested point to the
optimal hyper-plane. The classification accuracy increases as the margins size are maximized [36].
In non-linear SVM problems, complex hyper-planes are represented by kernels. The Gaussian radial
basis function is considered to be the optimal kernel type for many classification problems, due to
its high efficiency; it requires the definition of a small number of parameters and performs better
than other kernels with robust capabilities in the handling of remote sensing data [37].

2.5.4. K-Nearest Neighbor (K-NN)

K-NN is considered one of the simplest classification approaches, and has been used widely in
numerous types of classification tasks [38,39]. Each object is assigned to a class using majority
voting of the closest K training samples in the feature space. K is a predefined user value; the search
continues until reaching this value. In addition, the K-NN method requires a small number of
training samples, which makes it easy to implement, powerful, and capable of outperforming other
classification algorithms [40]. The accuracy of the K-NN classifier depends on K, the distance
between an unknown point and the nearest known samples, and the sample size [41]. Numerous
recent studies have used K-NN for benthic cover mapping [14,42,43].

3. Results
Figures 5 and 6 present examples of correct and misclassified benthic cover categories
computed by applying the proposed WMV algorithm for the Shiraho area; Tables 1 and 2
summarize the corresponding OA and Kappa values. The number of the correct species detected
from each classifier are displayed in Figure 7.
Figures 8 and 9 show samples of the correctly categorized and geo-located images along the
field survey path, as well as the benthic cover map produced by the WMV ensemble using the
Quickbird image for the Shiraho area. Tables 3 and 4 summarize the corresponding OA and Kappa
values. Additionally, the number of correct features classified by each classifier are presented in
Figure 10.
Figure 5. Various examples of categorized images, and a sample of their visual words occurrences
over the Shiraho area.

Figure 6. Samples of resulted processed benthic cover images (a) correctly categorized images (b)
wrong categorized images over the Shiraho area.
 Table 1. The OA and Kappa results of all methods for benthic habitats detection for Shiraho area.

Methodology BAG K-NN SVM WMV

OA % 80.4 81.4 85.6 89.4
Kappa 0.73 0.74 0.80 0.85

Table 2. The confusion matrix for benthic habitats detection using WMV method.

Reference Data
Classification Data Row. Total UA
Algae Corals Sediments Seagrass
Algae 59 11 3 4 77 77%
Corals 2 121 3 5 131 92%
Sediments 17 6 177 1 201 88%
Seagrass 0 1 0 90 91 99%
Col. Total 78 139 183 100 OA = 89.4%
PA 76% 87% 97% 90% Kappa val. = 0.85

Figure 7. The amount of correct features detected from each classifier for benthic habitats detection.

Figure 8. A sample of the correctly categorized and geo-located images along the field survey path
used for benthic cover mapping over the Shiraho study area.
Figure 9. The benthic cover map of the Shiraho study area resulted from the Quickbird image using
the WMV algorithm.

Table 3. The OA and Kappa results of all methods for benthic habitats mapping for the Shiraho area.

Methodology BAG K-NN SVM WMV

OA % 88.0 86.8 86.9 92.7
Kappa 0.83 0.81 0.81 0.89

Table 4. The confusion matrix for benthic habitats mapping using WMV method.

Reference Data
Classification Data Row. Total UA
Algae Corals Sediments Seagrass
Algae 160 9 4 5 178 90%
Corals 9 153 0 6 168 91%
Sediments 3 7 296 3 309 96%
Seagrass 3 6 0 86 95 91%
Col. Total 175 175 300 100 OA = 92.7%
PA 91% 87% 98% 86% Kappa val. = 0.89

Figure 10. The number of the correct species classified by each classifier for benthic cover mapping.
4. Discussion
Benthic detection and mapping of coral reefs area using remote sensing techniques can provide
valuable information significant to coral reef health. In addition, it is possible to increase the
accuracy of benthic cover classification by adding field reference samples, especially in shallow
areas where errors of misclassification, due to confusion and overlap between various species,
occur. This study proposes a strategy for monitoring benthic habitats using field samples collected
semi-automatically from a towed video camera for classifying a high-resolution Quickbird satellite
image.
Numerous studies have attempted to produce benthic cover maps using high-resolution
satellite images, e.g., IKONOS, Quickbird, and Worldview-2 [20,21,44]. Roelfsema et al. [25] used a
transecting lines method for training and validation of five benthic habitats classifications, of 1–25%
seagrass, 25–50% seagrass, 50–75% seagrass, 75–100% seagrass, and algae. The produced results
proved that transecting lines method can increase the spatial availability of the observed data.
Roelfsema et al. [45] integrated snorkeler and AUV surveys with satellite images for five seagrass
species mapping. The mapped seagrass species were Z. mueller, C. serrulata, H. ovalis, H. spinulosa,
S. isoetifolium. Kutser et al. [46] mapped fifteen classes of seagrass biomass and substrate type, using
the photo library method. A photo-library was established for biomass classification, where each
field quadrat photo is supplemented with seagrass dry weight of the sample and a photo of the
sorted sample, taken in laboratory.
Other studies attempted to use unsupervised classification of an image, subsequently naming
the classes based on in situ measurements. Baumstark et al. [47] presented a combination of water
column correction, unsupervised pixel classification, and image segmentation techniques, to
provide a seagrass density map. Three classes of seagrass were mapped: dense seagrass, patchy
seagrass, and sparse medium, with 77% overall accuracy. However, the accuracy assessment process
was performed with only 30 ground truth points. On the other hand, Baumstark et al. [48] proposed
an object-based image analysis OBIA method followed by unsupervised classification process for
mapping five habitats using an IKONOS image. The classified habitats were hard bottom, sand
mixed seagrass, seagrass dense, seagrass medium, and seagrass sparse. To ensure all benthic classes
were assessed, sixty-five random points were stratified across benthic types. The overall accuracy
using the OBIA method was 78%. Although these results were lower than typical accuracy
standards, the authors believe that accuracy could be improved with additional ground truth
samples. Alternatively, Vassallo et al. [49] proposed predictive spatial modelling as an alternative
method for producing benthic habitat maps. This method was performed with complete acoustic
coverage of the seafloor together, and a comparatively low number of sea truths. A Fuzzy clustering
unsupervised method, applied to a set of observations made by scuba diving and used as sea truth,
recognized five coralligenous habitats. The classified five coral species were Cystoseira zosteroides,
Axinella polypoides, Eunicella cavolini, Eunicella singularis, and Paramuricea clava. In total, 57 stations
were surveyed to within tens of meters positional accuracy; this was considered adequate at the
scale 1:25,000 of the final map. The overall accuracy of the classification reached 89%. Still, this
method has some weaknesses, and consequently, threats. For example, it significantly depended
on data reliability, accuracy, and resolution. In addition, sea truthing samples remain
indispensable for making prediction and verifying accuracy. Finally, incorrect analyses of outputs
and results can lead to management errors.
However, the abovementioned studies have various demerits: the benthic habitat detection
process was performed manually, producing small sampling size for calibration and validation,
extensive laboratory work, and requiring a long time for processing. Moreover, the unsupervised
method of the satellite image which can be used as an alternative to ensemble supervised classifiers
still needs adequate ground truth samples. Finally, all the aforementioned studies suffer from a
limited number of ground samples used for the calibration and validation of classification methods.
Furthermore, the development of a ground sampling procedure can also improve benthic cover
classification [20]. As a result, the proposed approach attempts to increase the number of ground
truth samples and overcome these drawbacks, using a high-resolution camera that can be towed
beneath a small vessel and can collect high-resolution images. These images can be categorized
semi-automatically, providing adequate field survey samples for benthic cover classification.
The majority of previous studies that attempted to detect benthic cover species used towed
video cameras fixed on AUV or ROV systems as a feasible alternative to a towed camera directly
attached to a vessel or a diver. These systems have more stability and are supported by illumination
systems. Accordingly, they provide high-quality images with limited noise. This enables the
classification algorithms to discriminate between benthic species much more easily. On the other
hand, the detection of benthic species from a towed camera directly attached to a vessel is more
challenging. Paul et al. [9] tried to detect three species (sand, seagrass, and algae) from a towed
camera mounted on AUV system using BOF with SVM approach. However, his approach confused
the detected species and requires a number of improvements. In our study, the benthic cover
features discrimination attributes were extracted using the BOF approach. We then assembled the
results from SVM, BAG, and K-NN supervised classifiers using the WMV approach. The achieved
results from the WMV ensemble showed improvements in species discrimination accuracy
compared to a single SVM approach. As most of sea bottom cover was sediment, they overlapped
with other species in numerous images. This overlap results in confusion for classifiers, especially
for the algae and corals features. As a result, the classification accuracy of these two species was still
relatively low. Conversely, sediment and seagrass species were detected with high accuracy.
For benthic cover mapping, the Principal Components Analysis approach was tested in our
study as a means of removing irrelevant features from the twelve inputs, but the OA decreased to
70%. Furthermore, two machine learning algorithms, self-organized maps (SOM) NN and Naïve
Bayes, were evaluated for classification, but they produced lower OA values. The SOM and Naïve
Bayes algorithms produced OA values of 83% and 66% respectively. These results agree with similar
previous studies [50,51], and as a result, were ignored from our study. Previous researchers argued
the precedence of ensemble techniques to single classifiers in benthic cover mapping. As an
example, Diesing and Stephens [18] tested six single classifiers and three to five classifiers, for
mapping four textural classes: muddy sand, sand, gravelly sand, and sandy gravel. The five
classifiers ensemble increased the classification OA by 5%. Furthermore, Aidy et al. [43] tested three
ensemble techniques: majority voting, simple averaging, and mode combination, with five base
classifiers. These classifiers were tested to map four types of benthic habitat: dense coral, sparse
coral, dead coral, and sand. The majority voting ensemble achieved the highest OA (83%),
compared with the other ensembles. Recently, Zhang et al. [14] tested three classifiers, SVM, K-NN,
and RF, using WMV for benthic cover mapping with a fusion of various data sources. Three benthic
cover classes (hard bottom cover, patchy seagrass, and continuous seagrass) were distingsuished,
with an OA of 89%.
The proposed WMV ensemble simply combines the outcomes from three different classifiers
which are trained independently. These classifiers are BAG, SVM, and K-NN; each produced
different per-class accuracy, which is mainly caused by discrepancies in the concepts of the three
models. Three classifiers showed a diversity in per-class accuracy, which is primarily caused by the
discrepancies in concepts of three methods. BAG examines optimal decision trees to assemble data.
However, SVMs try to find the optimal hyper-plane to classify data, whereas k-NN looks for the
ideal match to represent inputs. For benthic cover detection, SVM achieved significantly better
results than K-NN for algae and corals classification. However, K-NN slightly outperformed SVM
for sediment and seagrass classification. Both classifiers produced significantly better results than
the BAG classifier. The most challenging part of this process was distinguishing between algae and
sediment or corals and sediment; both algae and corals species were surrounded by sediment in the
majority of benthic cover images. WMV ensemble increased the benthic cover detection OA and
Kappa values from the three base classifiers, with about 4% and 0.05 respectively, to reach 89.4%
and 0.85 respectively. For benthic cover mapping, K-NN and SVM resulted in the same classification
accuracy, whereas the BAG slightly surpassed both classifiers. The three classifiers had a difficulty
differentiating between algae and corals. However, the WMV ensemble improved the classification
OA and Kappa values for
benthic mapping from the three base classifiers, with about 5% and 0.08 respectively, to reach 92.7%
and 0.89 respectively. Certainly, the WMV ensemble approach resulted in higher classification
accuracy than BAG, SVM, and the K-NN classifiers used in benthic cover detection and mapping.
Monitoring the global spatio-temporal changes in benthic community structure can be
performed using the aforementioned semi-automated framework. More information about
ecological monitoring studies has been discussed at length in literature [23]. For example, Manuel
[52] used the coral point count method [53] for the quantification of the relative abundance of coral
reef functional groups, over time and space. Phinn [19] and Roelfsema [54] proposed a combination
of object-based image analysis and ecological modelling for the mapping of geomorphic and
ecological zones in coral reefs. Both studies used the geo-referenced photo-transect method [55],
and categorized the images based on the same coral point count method [53]. However, our
proposed methodology for detecting benthic cover images is faster than the semi-automated
method proposed by Manuel [52]. As soon as the algorithms were sufficiently trained with
adequate images, they could be used for distinguishing between geo-located images. Only a towed
camera which can be mounted on a small vessel, or a snorkeler can provide these images. This field
survey can be repeated every specific time over the same study area to monitor the benthic cover
features. Furthermore, the proposed fast processing of ground-truth images would help to increase
the sampling size which can be integrated with ecological modelling for monitoring purposes.
In summary, the proposed monitoring system has numerous merits. For instance, it is low cost,
because the required tools are not expensive, e.g., a GoPro camera, a GNSS, and a small boat or a
snorkeler. In addition, this monitoring system is not harmful to the surrounding ecosystem and can
be used annually to follow the health of benthic habitats. It also provides sufficient field categorized
images which can be used for benthic cover mapping. Finally, it requires a relatively short time for
processing images using simple programs. However, some demerits still require improvement, e.g.,
the limited shallow areas which can be processed and the limitations in mixed areas or small
patches. The results encourage more future studies in this field. These studies may include
performing the same approach with ROV systems at known locations for monitoring deep seafloor
areas. Additionally, the same approach can be developed to process video files for benthic cover
detection in the field. This development can be used in monitoring coral reef bleaching or their
spatial or temporal changes. Furthermore, the same ensemble or fuzzy majority voting techniques
can be tested with soft classifiers for the same targets. On the other hand, testing the performance of
deep learning algorithms using a
high-quality benthic cover images would build a well-established benthic cover monitoring system.

5. Conclusions
Benthic habitat monitoring and mapping are essential for the management and conservation
of coral reef environments. The construction of an accurate and informative monitoring system is
important in effectively planning a network of threatened zones, and to monitor habitat
fragmentation degree. This study assessed the performance of integrating three machine learning
algorithms for benthic cover habitat monitoring, using towed underwater videos and a GNSS
system. In addition, we also mapped seafloor habitats using Quickbird satellite images. In this
article, we introduced an approach for the semi-automatic detection and mapping of the Shiraho
heterogeneous coastal area, including corals, algae, seagrass, and sediment. The WMV algorithm
was applied to collate the outputs from three machine learning algorithms. These algorithms were
SVM, K-NN, and BAG. The automatic detection of benthic habitats was based on the BOF
technique. A number of attributes were extracted from labeled examples using raw towed video
image data. Furthermore, the correctly detected benthic habitat images were synchronized with the
GNSS system, and were used to classify Quickbird satellite imagery. We achieved an OA of
automatic detection for the four habitats of 89.4% using the WMV algorithm. Finally, accurate
habitat maps for the Shiraho area were produced with a 92.7% OA with the same WMV ensemble.
These results demonstrate improvements in automatic benthic habitats monitoring, and in mapping
accuracies.
Author Contributions: H.M. and T.N designed and performed the field work of collecting the benthic habitats
samples from the study site. K.N. supervised this research work. H.M. and K.N. developed the benthic habitats
detection and mapping algorithms. H.M. analyzed the results and wrote the manuscript. K.N. and T.N. have
provided substantial edits and reviews on the many early drafts of this manuscript.
Acknowledgments: The first author would like to thank the Egyptian Ministry of Higher Education and
Nadaoka Laboratory in Tokyo Institute of Technology for their support and for offering the tools needed for
this research. This research was financially supported partly by JSPS Grant-in-Aids for Scientific Research (No.
15H02268), and Science and Technology Research Partnership for Sustainable Development (SATREPS)
program, Japan Science and Technology Agency (JST)/Japan International Cooperation Agency (JICA).
Conflicts of Interest: The authors declare no conflict of interest.

References
1. Tran, M. Mapping and Predicting Benthic Habitats in Estuaries Using Towed Underwater Video.
Master’s Thesis, University of Technology, Sydney, Australia, 2013.
2. Gauci, A.; Deidun, A.; Abela, J.; Zarb, K. Machine Learning for benthic sand and maerl classification and
coverage estimation in coastal areas around the Maltese Islands. J. Appl. Res. Technol. 2016, 14, 338–344.
[CrossRef]
3. Lüdtke, A.; Jerosch, K.; Herzog, O.; Schlüter, M. Development of a machine learning technique for
automatic analysis of seafloor image data: Case example, Pogonophora coverage at mud volcanoes.
Comput. Geosci. 2012, 39, 120–128. [CrossRef]
4. Guinan, J.; Brown, C.; Dolan, M.; Grehan, A. Ecological Informatics Ecological niche modelling of the
distribution of cold-water coral habitat using underwater remote sensing data. Ecol. Inform. 2009, 4, 83–92.
[CrossRef]
5. Teixido, N.; Albajes-Eizagirre, A.; Bolbo, D.; Le Hir, E.; Demestre, M.; Garrabou, J.; Guigues, L.; Gili, J.M.;
Piera, J.; Prelot, T.; Soria-Frisch, A. Hierarchical segmentation-based software for cover classification
analyses of seabed images (Seascape). Mar. Ecol. Prog. Ser. 2011, 431, 45–53. [CrossRef]
6. Bewley, M.; Friedman, A.; Ferrari, R.; Hill, N.; Hovey, R.; Barrett, N.; Pizarro, O.; Figueira, W.; Meyer, L.;
Babcock, R.; et al. Australian sea-floor survey data, with images and expert annotations. Sci. Data 2015, 2,
150057. [CrossRef] [PubMed]
7. Mallet, D.; Pelletier, D. Archimer Underwater video techniques for observing coastal marine biodiversity:
A review of sixty years of publications (1952–2012). Fish. Res. 2014, 154, 44–62. [CrossRef]
8. Seiler, J.; Friedman, A.; Steinberg, D.; Barrett, N.; Williams, A.; Holbrook, N. Image-based continental
shelf habitat mapping using novel automated data extraction techniques. Cont. Shelf Res. 2012, 45, 87–97.
[CrossRef]
9. Rigby, P.; Pizarro, O.; Williams, S. Toward Adaptive Benthic Habitat Mapping Using Gaussian Process
Classification. J. Field Robot. 2010, 27, 741–758. [CrossRef]
10. Pizarro, O.; Rigby, P.; Johnson-Roberson, M.; Williams, S.B.; Colquhoun, J. Towards image-based marine
habitat classification. In Proceedings of the MTS/ IEEE Oceans Conference, Quebec City, QC, Canada, 15–
18 September 2008; pp. 1–7.
11. Kutser, T.; Miller, I.; Jupp, D. Mapping coral reef benthic habitat with a hyperspectral spaceborne sensor.
In Proceedings of the Ocean Optics XVI Conference, Santa Fe, NM, USA, 18–22 November 2002.
12. Mobley, C.; Sundman, L.; Davis, C.; Bowles, J.; Downes, T.; Leathers, R.; Montes, M.; Bissett, W.; Kohler,
D.; Reid, R.; et al. Interpretation of hyperspectral remote-sensing imagery by spectrum matching and
look-up tables. Appl. Opt. 2005, 44, 3576–3592. [CrossRef] [PubMed]
13. Giardino, C.; Candiani, G.; Bresciani, M.; Lee, Z.; Gagliano, S.; Pepe, M. BOMBER: A tool for estimating
water quality and bottom properties from remote sensing images. Comput. Geosci. 2012, 45, 313–318.
[CrossRef]
14. Zhang, C. Applying data fusion techniques for benthic habitat mapping and monitoring in a coral reef
ecosystem. ISPRS J. Photogramm. Remote Sens. 2015, 104, 213–223. [CrossRef]
15. Hasan, R.; Ierodiaconou, D.; Laurenson, L. Combining angular response classification and backscatter
imagery segmentation for benthic biological habitat mapping. Estuar. Coast. Shelf Sci. 2012, 97, 1–9.
[CrossRef]
16. Hasan, R.; Ierodiaconou, D.; Laurenson, L.; Schimel, A. Integrating multibeam backscatter angular
response, mosaic and bathymetry data for benthic habitat mapping. PLoS ONE 2014, 9, e97339.
17. Reshitnyk, L.; Costa, M.; Robinson, C.; Dearden, P. Evaluation of WorldView-2 and acoustic remote
sensing for mapping benthic habitats in temperate coastal Pacific waters. Remote Sens. Environ. 2014, 153,
7–23. [CrossRef]
18. Diesing, M.; Stephens, D. A multi-model ensemble approach to seabed mapping. J. Sea Res. 2015, 100, 62–
69. [CrossRef]
19. Phinn, S.; Roelfsema, C.; Mumby, P. Multi-scale, object-based image analysis for mapping geomorphic
and ecological zones on coral reefs. Int. J. Remote Sens. 2012, 33, 3768–3797. [CrossRef]
20. Zapata-Ramírez, P.; Blanchon, P.; Olioso, A.; Hernandez-Nuñez, H.; Sobrino, J. Accuracy of IKONOS for
mapping benthic coral-reef habitats: A case study from the Puerto Morelos Reef National Park, Mexico.
Int. J. Remote Sens. 2013, 34, 3671–3687. [CrossRef]
21. Collin, A.; Nadaoka, K.; Nakamura, T. Mapping VHR Water Depth, Seabed and Land Cover Using
Google Earth Data. ISPRS Int. J. Geo-Inf. 2014, 3, 1157–1179. [CrossRef]
22. Eugenio, F.; Marcello, J.; Martin, J. High-Resolution Maps of Bathymetry and Benthic Habitats in Shallow-
Water Environments Using Multispectral Remote Sensing Imagery. IEEE Trans. Geosci. Remote Sens. 2015,
53, 3539–3549. [CrossRef]
23. Hedley, J.; Roelfsema, C.; Chollett, I.; Harborne, A.; Heron, S.; Weeks, S.; Skirving, W.; Strong, A.; Eakin,
C.M.; Christensen, T.; et al. Remote sensing of coral reefs for monitoring and management: A review.
Remote Sens. 2016, 8, 1–40. [CrossRef]
24. Estomata, M.; Blanco, A.; Nadaoka, K.; Tomoling, E. Extraction of Benthic Cover Information from Video
Tows and Photographs Using Object-Based Image Analysis. In Proceedings of the International Archives
of the Photogrammetry, Remote Sensing and Spatial Information Science, XXXIX-B8, XXII ISPRS
Congress, Melbourne, QC, Australia, 25 August–1 September 2012; pp. 539–544.
25. Roelfsema, C.; Phinn, S.; Udy, N.; Maxwell, P. An integrated field and remote sensing approach for
mapping Seagrass Cover, Moreton Bay, Australia. J. Spat. Sci. 2009, 54, 45–62. [CrossRef]
26. Liu, Z.G.; Zhang, X.Y.; Yang, Y.; Wu, C.C. A Flame Detection Algorithm Based on Bag-of—Features In The
YUV Color Space. In Proceedings of the International Conference on Intelligent Computing and Internet
of Things (IC1T), Harbin, China, 10–12 December 2015; pp. 64–67.
27. Yu, J.; Qin, Z.; Wan, T.; Zhang, X. Feature integration analysis of bag-of-features model for image retrieval.
Neurocomputing 2013, 120, 355–364. [CrossRef]
28. Yang, S.; Bebis, G.; Chu, Y.; Zhao, L. Effective face recognition using bag of features with additive kernels.
J. Electron. Imaging 2016, 25. [CrossRef]
29. Breiman, L. Bagging Predictors. Mach. Learn. 1996, 24, 123–140. [CrossRef]
30. Kulkarni, S.; Kelkar, V. Classification of Multispectral Satellite Images Using Ensemble Techniques of
Bagging, Boosting and Ada-Boost. In Proceedings of the International Conference on Circuits, Systems,
Communication and Information Technology Applications (CSCITA) Classification, Mumbai, India, 4–
5 April 2014; pp. 253–258.
31. Ghimire, B.; Rogan, J.; Rodriguez-Galiano, V.; Panday, P.; Neeti, N. An Evaluation of Bagging, Boosting,
and Random Forests for Land-Cover Classiication in Cape Cod, Massachusetts, USA. GISci. Remote Sens.
2012, 5, 623–643. [CrossRef]
32. DeFries, R.; Chan, J. Multiple Criteria for Evaluating Machine Learning Algorithms for Land Cover
Classification from Satellite Data. Remote Sens. Environ. 2000, 74, 503–515. [CrossRef]
33. Cortes, C.; Vapnik, V. Support-Vector Networks. Mach. Learn. 1995, 20, 273–297. [CrossRef]
34. Chu, H.; Ge, L. Combination of Genetic Algorithm and Dempster-Shafer Theory of Evidence for Land
Cover Classification Using Integration of Sar and Optical Satellite Imagery. In Proceedings of the
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume
XXXIX-B7, XXXIX Congres, Melbourne, QC, Australia, 25 August–1 September 2012; pp. 173–178.
35. Kavzoglu, T.; Colkesen, I. A kernel functions analysis for support vector machines for land cover
classification.
Int. J. Appl. Earth Obs. Geoinf. 2009, 11, 352–359. [CrossRef]
36. Lenz, B.; Barak, B. Data Mining and Support Vector Regression Machine Learning in Semiconductor
Manufacturing to improve virtual metrology. In Proceedings of the Annual Hawaii International
Conference on System Sciences, Wailea, HI, USA, 7–10 January 2013; pp. 3447–3456.
37. Tzeng, Y.; Fan, K.; Chen, K. An adaptive thresholding multiple classifiers system for remote sensing
image classification. Eng. Remote Sens. 2009, 75, 679–687. [CrossRef]
38. He, J.; Tan, A.; Tan, C. On Machine Learning Methods for Chinese Document Categorization. Appl. Intell.
2003, 18, 311–322. [CrossRef]
39. Wan, C.; Lee, L.; Rajkumar, R.; Isa, D. A hybrid text classification approach with low dependency on
parameter by integrating K-nearest neighbor and support vector machine. Expert Syst. Appl. 2012, 39,
11880–11888. [CrossRef]
40. Gutierrez-Osuna, R. Lecture Notes CS 790: Introduction to Pattern Recognition; Dayton, OH, USA. 2002.
Available online: http://research.cs.tamu.edu/prism/lectures/iss/iss_l1.pdf (accessed on 20 June 2017).
41. Liu, H.; Zhang, S. Noisy data elimination using mutual k-nearest neighbor for classification mining.
J. Syst. Softw. 2012, 85, 1067–1074. [CrossRef]
42. Shihavuddin, A.; Gracias, N.; Garcia, R.; Gleason, A.; Gintert, B. Image-based coral reef classification and
thematic mapping. Remote Sens. 2013, 5, 1809–1841. [CrossRef]
43. Muslim, A.; Komatsu, T.; Dianachia, D. Evaluation of classification techniques for benthic habitat mapping.
Proc. SPIE 2012, 8525, 85250W.
44. Pu, R.; Bell, S. Mapping seagrass coverage and spatial patterns with high spatial resolution IKONOS
imagery.
Int. J. Appl. Earth Obs. Geoinf. 2017, 54, 145–158. [CrossRef]
45. Roelfsema, C.; Lyons, M.; Dunbabin, M.; Kovacs, E.; Phinn, S. Integrating field survey data with satellite
image data to improve shallow water seagrass maps: The role of AUV and snorkeller surveys. Remote
Sens. Lett. 2015, 6, 135–144. [CrossRef]
46. Kutser, T.; Vahtmäe, E.; Roelfsema, C.; Metsamaa, L. Photo-library method for mapping seagrass biomass.
Estuar. Coast. Shelf Sci. 2007, 75, 559–563. [CrossRef]
47. Baumstark, R.; Dixon, B.; Carlson, P.; Palandro, D.; Kolasa, K. Alternative spatially enhanced integrative
techniques for mapping seagrass in Florida’s marine ecosystem. Int. J. Remote Sens. 2013, 34, 1248–1264.
[CrossRef]
48. Baumstark, R.; Duffey, R.; Pu, R. Mapping seagrass and colonized hard bottom in Springs Coast, Florida
using WorldView-2 satellite imagery. Estuar. Coast. Shelf Sci. 2016, 170, 45–60. [CrossRef]
49. Vassallo, P.; Bianchi, C.; Paoli, C.; Holon, F.; Augusto, N.; Bavestrello, G.; Vietti, R.; Morri, C. A predictive
approach to benthic marine habitat mapping: Efficacy and management implications. Mar. Pollut. Bull.
2018, 131, 218–232. [CrossRef]
50. Collin, A.; Archambault, P.; Long, B. Predicting species diversity of benthic communities within turbid
nearshore using full-waveform bathymetric LiDAR and machine learners. PLoS ONE 2011, 6, e21265.
[CrossRef] [PubMed]
51. Wahidin, N.; Siregar, V.; Nababan, B.; Jaya, I.; Wouthuyzen, S. Object-based Image Analysis for Coral Reef
Benthic Habitat Mapping with Several Classification Algorithms. Procedia Environ. Sci. 2015, 24, 222–227.
[CrossRef]
52. González-Rivero, M.; Beijbom, O.; Rodriguez-Ramirez, A.; Holtrop, T.; González-Marrero, Y.; Ganase, A.;
Roelfsema, C.; Phinn, S.; Hoegh-Guldberg, O. Scaling up ecological measurements of coral reefs using
semi-automated field image collection and analysis. Remote Sens. 2016, 8, 30. [CrossRef]
53. Pante, E.; Dustan, P. Getting to the point: Accuracy of point count in monitoring ecosystem change.
J. Mar. Biol. 2012. [CrossRef]
54. Roelfsema, C.; Kovacs, E.; Ortiz, J.; Wolff, N.; Callaghan, D.; Wettle, M.; Ronan, M.; Hamylton, S.; Mumby,
P.; Phinn, S. Coral reef habitat mapping: A combination of object-based image analysis and ecological
modelling. Remote Sens. Environ. 2018, 208, 27–41. [CrossRef]
55. Roelfsema, C.; Phinn, S. Integrating field data with high spatial resolution multispectral satellite imagery
for calibration and validation of coral reef benthic community maps. J. Appl. Remote Sens. 2010, 4.
[CrossRef]

© 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access
article distributed under the terms and conditions of the Creative Commons
Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).