%0 Journal Article %T Real-time multiple objects tracking on Raspberry-Pi-based smart embedded camera %+ Département d'Architectures, Conception et Logiciels Embarqués-LIST (DACLE-LIST) %+ Université Blaise Pascal - Clermont-Ferrand 2 (UBP) %A Dziri, A. %A Duranton, M. %A Chapuis, R. %< avec comité de lecture %@ 1017-9909 %J Journal of Electronic Imaging %I SPIE and IS&T %V 25 %N 4 %8 2016 %D 2016 %R 10.1117/1.JEI.25.4.041005 %K multiobject tracking %K occlusion handling %K smart cameras %K Raspberry-Pi %K background subtraction %K Gaussian mixture probability hypothesis density %Z Engineering Sciences [physics] %Z Engineering Sciences [physics]/Signal and Image processingJournal articles %X Multiple-object tracking constitutes a major step in several computer vision applications, such as surveillance, advanced driver assistance systems, and automatic traffic monitoring. Because of the number of cameras used to cover a large area, these applications are constrained by the cost of each node, the power consumption, the robustness of the tracking, the processing time, and the ease of deployment of the system. To meet these challenges, the use of low-power and low-cost embedded vision platforms to achieve reliable tracking becomes essential in networks of cameras. We propose a tracking pipeline that is designed for fixed smart cameras and which can handle occlusions between objects. We show that the proposed pipeline reaches real-time processing on a low-cost embedded smart camera composed of a Raspberry-Pi board and a RaspiCam camera. The tracking quality and the processing speed obtained with the proposed pipeline are evaluated on publicly available datasets and compared to the state-of-the-art methods. %G English %L cea-01846863 %U https://cea.hal.science/cea-01846863 %~ CEA %~ PRES_CLERMONT %~ UNIV-BPCLERMONT %~ DRT %~ UNIV-PARIS-SACLAY %~ LIST %~ GS-ENGINEERING %~ GS-COMPUTER-SCIENCE %~ DSCIN