Papers by Paolo Remagnino
Proceedings of the 9th International Conference on Computer Vision Theory and Applications, 2014
The main contribution of this paper is a compact representation of the 'short tracks' or tracklet... more The main contribution of this paper is a compact representation of the 'short tracks' or tracklets present in a time window of a given video input, which allows to analyse and detect different crowd events. To proceed, first, tracklets are extracted from a time window using a particle filter multi-target tracker. After noise removal, the tracklets are plotted into a square image by normalising their lengths to the size of the image. Different histograms are then applied to this compact representation. Thus, different events in a crowd are detected via a Bag-of-words modelling. Novel video sequences, can then be analysed to detect whether an abnormal or chaotic situation is present. The whole algorithm is tested with our own dataset, also introduced in the paper.
Proceedings of the Fourth International Conference on Computer Vision Theory and Applications, 2009
Video surveillance is one of the most studied application in Computer Vision. We propose a novel ... more Video surveillance is one of the most studied application in Computer Vision. We propose a novel method to identify and track people in a complex environment with stereo cameras. It uses two stereo cameras to deal with occlusions, two different background models that handle shadows and illumination changes and a new segmentation algorithm that is effective in crowded environments. The algorithm is able to work in real time and results demonstrating the effectiveness of the approach are shown.
Multi-view action recognition has gained a great interest in video surveillance, human computer i... more Multi-view action recognition has gained a great interest in video surveillance, human computer interaction, and multimedia retrieval, where multiple cameras of different types are deployed to provide a complementary field of views. Fusion of multiple camera views evidently leads to more robust decisions on both tracking multiple targets and analysing complex human activities, especially where there are occlusions. In this paper, we incorporate the marginalised stacked denoising autoencoders (mSDA) algorithm to further improve the bag of words (BoWs) representation in terms of robustness and usefulness for multi-view action recognition. The resulting representations are fed into three simple fusion strategies as well as a multiple kernel learning algorithm at the classification stage. Based on the internal evaluation, the codebook size of BoWs and the number of layers of mSDA may not significantly affect recognition performance. According to results on three multi-view benchmark datasets, the proposed framework improves recognition performance across all three datasets and outputs record recognition performance, beating the state-of-art algorithms in the literature. It is also capable of performing real-time action recognition at a frame rate ranging from 33 to 45, which could be further improved by using more powerful machines in future applications.
Multi-view action recognition has gained a great interest in video surveillance, human computer i... more Multi-view action recognition has gained a great interest in video surveillance, human computer interaction, and multimedia retrieval, where multiple cameras of different types are deployed to provide a complementary field of views. Fusion of multiple camera views evidently leads to more robust decisions on both tracking multiple targets and analysing complex human activities, especially where there are occlusions. In this paper, we incorporate the marginalised stacked denoising autoencoders (mSDA) algorithm to further improve the bag of words (BoWs) representation in terms of robustness and usefulness for multi-view action recognition. The resulting representations are fed into three simple fusion strategies as well as a multiple kernel learning algorithm at the classification stage. Based on the internal evaluation, the codebook size of BoWs and the number of layers of mSDA may not significantly affect recognition performance. According to results on three multi-view benchmark datasets, the proposed framework improves recognition performance across all three datasets and outputs record recognition performance, beating the state-of-art algorithms in the literature. It is also capable of performing real-time action recognition at a frame rate ranging from 33 to 45, which could be further improved by using more powerful machines in future applications.
IEEE Access, 2020
Physical rehabilitation aims at improving the functional ability and quality of life of patients ... more Physical rehabilitation aims at improving the functional ability and quality of life of patients affected by physical impairments or disabilities. Neurological diseases represent the largest cause of disability worldwide. For many, there is no cure and physiotherapy allows symptoms to be managed. Physiotherapy is based on the daily execution of exercises, traditionally under the supervision of a therapist. However, performing these exercises requires that both the patient and the physiotherapist are together so that the physiotherapist can assist the patient while exercising. For patients with a neurological condition, rehabilitation is a long term process, lasting months or even years. Not withstanding the personal costs, the cost of care/physiotherapy is high and represents e27,711 per year in Spain. This is compounded by a shortage of qualified therapists, often cited as one reason why stroke survivors do not received the recommended amount of therapy. The challenge is even greater in low to mid-income countries where there is a lack of trained personnel as well as under-served and remote regions. Technology can be employed to alleviate these problems by remotely monitoring a rehabilitation session taking place at home or anywhere in the community. This paper presents a computer vision-based system for home-use that automatically assesses how well the patient performs the exercises and transmits the information back to the clinic. The patient and physiotherapist do not need to be co-located. Gamification methods and techniques are used to engage patients when carrying out the rehabilitation routines. To this end, we propose a distributed gamified system that automatically evaluates the performance of exercises by analyzing and comparing motion curves using the DTW (Dynamic Time Warping) algorithm. INDEX TERMS Assistive technologies, remote physical rehabilitation, gamification, dynamic time warping (DTW).
IEEE Access, 2020
Physical rehabilitation aims at improving the functional ability and quality of life of patients ... more Physical rehabilitation aims at improving the functional ability and quality of life of patients affected by physical impairments or disabilities. Neurological diseases represent the largest cause of disability worldwide. For many, there is no cure and physiotherapy allows symptoms to be managed. Physiotherapy is based on the daily execution of exercises, traditionally under the supervision of a therapist. However, performing these exercises requires that both the patient and the physiotherapist are together so that the physiotherapist can assist the patient while exercising. For patients with a neurological condition, rehabilitation is a long term process, lasting months or even years. Not withstanding the personal costs, the cost of care/physiotherapy is high and represents e27,711 per year in Spain. This is compounded by a shortage of qualified therapists, often cited as one reason why stroke survivors do not received the recommended amount of therapy. The challenge is even greater in low to mid-income countries where there is a lack of trained personnel as well as under-served and remote regions. Technology can be employed to alleviate these problems by remotely monitoring a rehabilitation session taking place at home or anywhere in the community. This paper presents a computer vision-based system for home-use that automatically assesses how well the patient performs the exercises and transmits the information back to the clinic. The patient and physiotherapist do not need to be co-located. Gamification methods and techniques are used to engage patients when carrying out the rehabilitation routines. To this end, we propose a distributed gamified system that automatically evaluates the performance of exercises by analyzing and comparing motion curves using the DTW (Dynamic Time Warping) algorithm. INDEX TERMS Assistive technologies, remote physical rehabilitation, gamification, dynamic time warping (DTW).
IEEE Intelligent Systems, 2015
IEEE Intelligent Systems, 2015
Sensors (Basel, Switzerland), Jan 16, 2015
Multi-view action recognition has gained a great interest in video surveillance, human computer i... more Multi-view action recognition has gained a great interest in video surveillance, human computer interaction, and multimedia retrieval, where multiple cameras of different types are deployed to provide a complementary field of views. Fusion of multiple camera views evidently leads to more robust decisions on both tracking multiple targets and analysing complex human activities, especially where there are occlusions. In this paper, we incorporate the marginalised stacked denoising autoencoders (mSDA) algorithm to further improve the bag of words (BoWs) representation in terms of robustness and usefulness for multi-view action recognition. The resulting representations are fed into three simple fusion strategies as well as a multiple kernel learning algorithm at the classification stage. Based on the internal evaluation, the codebook size of BoWs and the number of layers of mSDA may not significantly affect recognition performance. According to results on three multi-view benchmark dat...
Sensors (Basel, Switzerland), Jan 16, 2015
Multi-view action recognition has gained a great interest in video surveillance, human computer i... more Multi-view action recognition has gained a great interest in video surveillance, human computer interaction, and multimedia retrieval, where multiple cameras of different types are deployed to provide a complementary field of views. Fusion of multiple camera views evidently leads to more robust decisions on both tracking multiple targets and analysing complex human activities, especially where there are occlusions. In this paper, we incorporate the marginalised stacked denoising autoencoders (mSDA) algorithm to further improve the bag of words (BoWs) representation in terms of robustness and usefulness for multi-view action recognition. The resulting representations are fed into three simple fusion strategies as well as a multiple kernel learning algorithm at the classification stage. Based on the internal evaluation, the codebook size of BoWs and the number of layers of mSDA may not significantly affect recognition performance. According to results on three multi-view benchmark dat...
Sixth International Conference of Information Fusion, 2003. Proceedings of the, 2003
Multi-camera firsion is rapidly becoming an emerging research area, especially for visual surveil... more Multi-camera firsion is rapidly becoming an emerging research area, especially for visual surveillance applications. Data fusion can be obtained with calibrated cameras, either calibrating prior use - following standard techniques (I) - or through learning mechanism in 30 Cartesian frame (2), typically the scene ground plane. In this paper we describe a method to merge video data acquired by two
Sixth International Conference of Information Fusion, 2003. Proceedings of the, 2003
Multi-camera firsion is rapidly becoming an emerging research area, especially for visual surveil... more Multi-camera firsion is rapidly becoming an emerging research area, especially for visual surveillance applications. Data fusion can be obtained with calibrated cameras, either calibrating prior use - following standard techniques (I) - or through learning mechanism in 30 Cartesian frame (2), typically the scene ground plane. In this paper we describe a method to merge video data acquired by two
2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance, 2009
We propose an adaptive tracking system for assisted living that integrates user information about... more We propose an adaptive tracking system for assisted living that integrates user information about emergency events. Information fusion between user data and visual data is performed in order to estimate and assess the situation at hand. The system is able to dynamically switch between different segmentation and tracking algorithms improving its performance, as shown by the proposed examples.
2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance, 2009
We propose an adaptive tracking system for assisted living that integrates user information about... more We propose an adaptive tracking system for assisted living that integrates user information about emergency events. Information fusion between user data and visual data is performed in order to estimate and assess the situation at hand. The system is able to dynamically switch between different segmentation and tracking algorithms improving its performance, as shown by the proposed examples.
Lecture Notes in Computer Science, 2006
... 1 Introduction Understanding crowd behavior is a relatively new research topic in computer vi... more ... 1 Introduction Understanding crowd behavior is a relatively new research topic in computer vision. It can be applied to a variety of domain problems, including space opti-mization, ambient intelligence and visual surveillance. ...
Lecture Notes in Computer Science, 2006
... 1 Introduction Understanding crowd behavior is a relatively new research topic in computer vi... more ... 1 Introduction Understanding crowd behavior is a relatively new research topic in computer vision. It can be applied to a variety of domain problems, including space opti-mization, ambient intelligence and visual surveillance. ...
Ant Colony Optimization and Swarm Intelligence
... In this paper we have presented a new algorithm for edge detection in image processing using ... more ... In this paper we have presented a new algorithm for edge detection in image processing using an ant algorithm approach. ... of noise susceptibility addressed in this paper is not specific to our approach, and is in fact a typical problem amongst edge detection algorithms. ...
Ant Colony Optimization and Swarm Intelligence
... In this paper we have presented a new algorithm for edge detection in image processing using ... more ... In this paper we have presented a new algorithm for edge detection in image processing using an ant algorithm approach. ... of noise susceptibility addressed in this paper is not specific to our approach, and is in fact a typical problem amongst edge detection algorithms. ...
Uploads
Papers by Paolo Remagnino