Papers by Marta Marron-Romera
Communications in computer and information science, 2023
Sensors
This paper presents GAVT, a highly accurate audiovisual 3D tracking system based on particle filt... more This paper presents GAVT, a highly accurate audiovisual 3D tracking system based on particle filters and a probabilistic framework, employing a single camera and a microphone array. Our first contribution is a complex visual appearance model that accurately locates the speaker’s mouth. It transforms a Viola & Jones face detector classifier kernel into a likelihood estimator, leveraging knowledge from multiple classifiers trained for different face poses. Additionally, we propose a mechanism to handle occlusions based on the new likelihood’s dispersion. The audio localization proposal utilizes a probabilistic steered response power, representing cross-correlation functions as Gaussian mixture models. Moreover, to prevent tracker interference, we introduce a novel mechanism for associating Gaussians with speakers. The evaluation is carried out using the AV16.3 and CAV3D databases for Single- and Multiple-Object Tracking tasks (SOT and MOT, respectively). GAVT significantly improves th...
Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 2020
In this work, we propose a people detection system that uses only depth information, provided by ... more In this work, we propose a people detection system that uses only depth information, provided by an RGB-D camera in frontal position. The proposed solution is based on a Convolutional Neural Network (CNN) with an encoder-decoder architecture, formed by ResNet residual layers, that have been widely used in detection and classification tasks. The system takes a depth map as input, generated by a time-of-flight or a structuredlight based sensor. Its output is a probability map (with the same size of the input) where each detection is represented as a Gaussian function, whose mean is the position of the person's head. Once this probability map is generated, some refinement techniques are applied in order to improve the detection precision. During the system training process, there have only been used synthetic images generated by the software Blender, thus avoiding the need to acquire and label large image datasets. The described system has been evaluated using both, synthetic and real images acquired using a Microsoft Kinect II camera. In addition, we have compared the obtained results with those from other works of the state-of-the-art, proving that the results are similar in spite of not having used real data during the training procedure.
International Journal of Environmental Research and Public Health
Under the umbrella of assistive technologies research, a lot of different platforms have appeared... more Under the umbrella of assistive technologies research, a lot of different platforms have appeared since the 1980s, trying to improve the independence of people with severe mobility problems. Those works followed the same path coming from the field of robotics trying to reach users’ needs. Nevertheless, those approaches rarely arrived on the market, due to their specificity and price. This paper presents a new prototype of an intelligent wheelchair (IW) that tries to fill the gap between research labs and market. In order to achieve such a goal, the proposed solution balances the criteria of performance and cost by using low-cost hardware and open software standards in mobile robots combined together within a modular architecture, which can be easily adapted to different profiles of a wide range of potential users. The basic building block consists of a mechanical chassis with two electric motors and a low-level electronic control system; driven by a joystick, this platform behaves s...
Toxics
Pharmaceuticals and personal care products (PPCPs) are partially degraded in wastewater treatment... more Pharmaceuticals and personal care products (PPCPs) are partially degraded in wastewater treatment plants (WWTPs), thereby leading to the formation of more toxic metabolites. Bacterial populations in bioreactors operated in WWTPs are sensitive to different toxics such as heavy metals and aromatic compounds, but there is still little information on the effect that pharmaceuticals exert on their metabolism, especially under anaerobic conditions. This work evaluated the effect of selected pharmaceuticals that remain in solution and attached to biosolids on the metabolism of anaerobic biomass. Batch reactors operated in parallel under the pressure of four individual and mixed PPCPs (carbamazepine, ibuprofen, triclosan and sulfametoxazole) allowed us to obtain relevant information on anaerobic digestion performance, toxicological effects and alterations to key enzymes involved in the biodegradation process. Cell viability was quantitatively evaluated using an automatic analysis of confoca...
Multimedia Tools and Applications
This work describes an end-to-end approach for real-time human action recognition from raw depth ... more This work describes an end-to-end approach for real-time human action recognition from raw depth image-sequences. The proposal is based on a 3D fully convolutional neural network, named 3DFCNN, which automatically encodes spatio-temporal patterns from raw depth sequences. The described 3D-CNN allows actions classification from the spatial and temporal encoded information of depth sequences. The use of depth data ensures that action recognition is carried out protecting people’s privacy, since their identities can not be recognized from these data. The proposed 3DFCNN has been optimized to reach a good performance in terms of accuracy while working in real-time. Then, it has been evaluated and compared with other state-of-the-art systems in three widely used public datasets with different characteristics, demonstrating that 3DFCNN outperforms all the non-DNN-based state-of-the-art methods with a maximum accuracy of 83.6% and obtains results that are comparable to the DNN-based approa...
Sensors, 2021
New processing methods based on artificial intelligence (AI) and deep learning are replacing trad... more New processing methods based on artificial intelligence (AI) and deep learning are replacing traditional computer vision algorithms. The more advanced systems can process huge amounts of data in large computing facilities. In contrast, this paper presents a smart video surveillance system executing AI algorithms in low power consumption embedded devices. The computer vision algorithm, typical for surveillance applications, aims to detect, count and track people’s movements in the area. This application requires a distributed smart camera system. The proposed AI application allows detecting people in the surveillance area using a MobileNet-SSD architecture. In addition, using a robust Kalman filter bank, the algorithm can keep track of people in the video also providing people counting information. The detection results are excellent considering the constraints imposed on the process. The selected architecture for the edge node is based on a UpSquared2 device that includes a vision p...
Seminario Anual de Automática, Electrónica Industrial e Instrumentación 2016 (SAAEI 2016), 2016
Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 2017
This work presents a robust system for people detection in RGB images. The proposal increases the... more This work presents a robust system for people detection in RGB images. The proposal increases the robustness of previous approaches against partial occlusions, and it is based on a bank of individual detectors whose results are combined using a multimodal association algorithm. Each individual detector is trained for a different body part (full body, half top, half bottom, half left and half right body parts). It consists of two elements: a feature extractor that obtains a Histogram of Oriented Gradients (HOG) descriptor, and a Support Vector Machine (SVM) for classification. Several experimental tests have been carried out in order to validate the proposal, using INRIA and CAVIAR datasets, that have been widely used by the scientific community. The obtained results show that the association of all the body part detections presents a better accuracy that any of the parts individually. Regarding the body parts, the best results have been obtained for the full body and half top body.
IECON 2019 - 45th Annual Conference of the IEEE Industrial Electronics Society, 2019
This work proposes a new method for face and mouth tracking using video cameras. This method has ... more This work proposes a new method for face and mouth tracking using video cameras. This method has been proposed to be used in intelligent spaces as an initial stage to provide information to higher level applications. The method incorporates the classifiers of the Viola and Jones detection method, modified to provide a probabilistic output previously proposed by the authors, useful for tracking with particle filter. The method combines classifiers trained to detect specific poses (frontal and side face views), building an independent likelihood model of pose changes. We also propose to combine the model in several cameras to allow the mouth tracking in a three-dimensional space. The system has been evaluated on the AV16.3 database sequences showing good results in both precision and recall when using a single camera (in a bidimensional space), and an error below 3cm when using three cameras (in a three-dimensional space).
Sensors (Basel, Switzerland), 2021
Surveillance cameras are being installed in many primary daily living places to maintain public s... more Surveillance cameras are being installed in many primary daily living places to maintain public safety. In this video-surveillance context, anomalies occur only for a very short time, and very occasionally. Hence, manual monitoring of such anomalies may be exhaustive and monotonous, resulting in a decrease in reliability and speed in emergency situations due to monitor tiredness. Within this framework, the importance of automatic detection of anomalies is clear, and, therefore, an important amount of research works have been made lately in this topic. According to these earlier studies, supervised approaches perform better than unsupervised ones. However, supervised approaches demand manual annotation, making dependent the system reliability of the different situations used in the training (something difficult to set in anomaly context). In this work, it is proposed an approach for anomaly detection in video-surveillance scenes based on a weakly supervised learning algorithm. Spatio...
2007 IEEE International Symposium on Intelligent Signal Processing, 2007
... D. Pizarro, E. Santiso, M. Mazo, M. Marron University of Alcala,Alcala de Henares, Spain, Ema... more ... D. Pizarro, E. Santiso, M. Mazo, M. Marron University of Alcala,Alcala de Henares, Spain, Email: {pizarro,santiso,mazo,marta} @depeca.uah.es ... a vector Yk the equivalent observation function is easily described using (3) and is denoted as Yk = ha(Xia) The proposal made in this ...
IFAC Proceedings Volumes, 2004
The work presented is related to the research area of autonomous navigation for mobile robots in ... more The work presented is related to the research area of autonomous navigation for mobile robots in unstructured, heavy crowded and highly dynamic environments. One of the main involved tasks in this researching area is the obstacle tracking module that has been successfully developed with different kind of probabilistic algorithms. The reliability that these techniques have shown estimating position with noisy measurements make them the most adequate to the mentioned problem, but their high computational cost has made them only useful with few and structured objects. In this paper a computational simple solution based on a multimodal (or extended) particle filter is proposed to track multiple and dynamic obstacles in an unstructured environment and based on the noisy position measurements taken from sonar sensors.
European Journal of Forensic Sciences, 2014
ABSTRACT Nowadays, detection of drugs of abuse is a usual practice in the legal field due to its ... more ABSTRACT Nowadays, detection of drugs of abuse is a usual practice in the legal field due to its incidence in several proceedings. Saliva is a matrix of increasing utility as it is a non-invasive sample that has been tested in international projects such as ROSITA and DRUID. Objectives: the study focused on the study of prevalence of drugs of abuse in a sample population of drivers of motor vehicles.3468 oral fluid samples came from local police activities, during the years 2007 until June 2010 in Barcelona (Spain). Methods: drivers suspected of driving under the influence of drugs had to comply with an analytical road side drug testing. A commercial kit immunoassay based was used (Cozart® DDS 801). Kits with positive results to any drug, 24.59%, were submitted to the Catalonia Institute of Legal Medicine, with an additional saliva sample ( as indicated by Cozart® DDS 801 provider) for confirmation by gas- chromatography mass- spectrometry (GC/MS). Drugs detected by the test Cozart® included:9 tetrahydrocannabinol, cocaine, opiates, methamphetamines amphetamines Results: after confirmation results showed a cannabis prevalence in 2064 samples (59.5%), cocaine in 1952 samples (56.2%) opiates in 258 (7.4%) amphetamines in 69 samples (1.9%) and methamphetamines in 57 (1.6%). No quantitative analysis was achieved. Conclusions: Results show that cannabis is the most prevalent in the study, followed by cocaine. Data are valuable in order to initiate sanctionary proceedings in Spanish legislation and also as signs of recreational drugs consumption which provide information to both epidemiology and public health.
IEEE 2002 28th Annual Conference of the Industrial Electronics Society. IECON 02
Uploads
Papers by Marta Marron-Romera