People detection
Document Actions
This work is part of the project CAPTHOM in the framework of the competitiveness cluster "Science and Power Systems Electric" (S2E2) of the Région Centre. Industrial partners of this project are STMicroelectronics, Legrand, Thermor, Agilicom, Sorec and Wirecom Technologies. The Prisme Institut, the Pôle Capteurs and the CRESITT Industrie also participate in the project. The project aims to develop a sensor to detect the human presence in a room. In this project, my work focused on developing algorithms to detect human presence using vision.
Comparative Study of background subtraction algorithm
Locating moving objects in a video sequence is the first step of many computer vision applications. Among the various motion-detection techniques, background subtraction methods are commonly implemented, especially for applications relying on a fixed camera. Since the basic inter-frame difference with global threshold is often a too simplistic method, more elaborate (and often probabilistic) methods have been proposed. These methods often aim at making the detection process more robust to noise, background motion and camera jitter. In this project, we evaluate background subtraction algorithm. In order to gauge performances of each method, tests are performed on a wide range of real, synthetic and semi-synthetic video sequences representing different challenges.
- Y. Benezeth, P.M. Jodoin, B. Emile, H. Laurent, C. Rosenberger, "Review and evaluation of commonly-implemented background subtraction algorithms", International Conference on Pattern Recognition (ICPR), 2008.
- Y. Benezeth, P.-M. Jodoin, B. Emile, H. Laurent, C. Rosenberger, "Comparative Study of Background Subtraction Algorithm", Journal of Electronic Imaging, vol. 19(3), 2010.
Human detection in images sequences
We propose a vision-based system for human detection and tracking in indoor environment using a static camera. The proposed method is based on object recognition in still images combined with methods using temporal information from the video. Doing that, we improve the performance of the overall system and reduce the task complexity. We first use background subtraction to limit the search space of the classifier. The segmentation is realized by modeling each background pixel by a single gaussian model. As each connected component detected by the background subtraction potentially corresponds to one person, each blob is independently tracked. The tracking process is based on the analysis of connected components position and interest points tracking. In order to know the nature of various objects that could be present in the scene, we use multiple cascades of boosted classiffers based on Haar-like filters.
|
|
 |
 |
- Y. Benezeth, B. Emile, H. Laurent, C. Rosenberger, "Vision-based system for human detection and tracking in indoor environment", International Journal of Social Robotics, special issue on people detection and tracking 2009
- Y. Benezeth, B. Emile, H. Laurent, C. Rosenberger, "A real time human detection system based on far infrared vision", International Conference on Image and Signal Processing (ICISP), 2008.
Human detection with a multi-sensors stereovision system
We propose a human detection process using Far-Infrared (FIR) and daylight cameras mounted on a stereovisions setup. Although daylight or FIR cameras have long been used to detect pedestrians, they nonetheless suffer from known limitations. In this project, both collaborate inside a stereovision setup to reduce the false positive rate inherent to their individual use. Our detection method is based on two distinctive steps. First, human positions are detected in both FIR and daylight images using a cascade of boosted classifiers. Then, both results are fused based on the geometric information of the sterovision system.
- Y. Benezeth, P.M. Jodoin, B. Emile, H. Laurent and C. Rosenberger, “Human detection with a multi-sensors stereovision system”, International Conference on Image and Signal Processing (ICISP), 2010.