Multirésolution adaptative pour un système de vision ultra faible consommation avec détection de mouvement et suivi intégrés

Cet article decrit un systeme de video surveillance ultra faible consommation. Base sur un principe d'acquisition multi resolution, ce Capteur d'Image CMOS (CIC) realise une detection de mouvement avec suivi integre en appliquant une haute resolution sur les cibles, tout en maintenant le fond de la scene en sous resolution. Dans un contexte de camera fixe embarquee, cette adaptation de l'acuite de capteur suivant l'activite de la scene permet a l'imageur de se reveiller sur des regions d'interet et de reduire ainsi la quantite de donnees a memoriser et traiter. Une reduction drastique de la consommation est ainsi obtenue. Les differentes etapes de traitement sont exposees, de meme que les resultats de simulations obtenus a partir d'une description haut niveau integrant les parametres technologiques du capteur d'image.

[1]  Lionel Lacassagne,et al.  Low power image processing: analog versus digital comparison , 2005, Seventh International Workshop on Computer Architecture for Machine Perception (CAMP'05).

[2]  Graham A. Jullien,et al.  A wide dynamic range CMOS active pixel sensor with frame difference , 2005, 2005 IEEE International Symposium on Circuits and Systems.

[3]  Jinn-Shyan Wang,et al.  A new current-mode sense amplifier for low-voltage low-power SRAM , 1998, Proceedings Eleventh Annual IEEE International ASIC Conference (Cat. No.98TH8372).

[4]  Suki Kim,et al.  A CMOS image sensor (CIS) architecture with low power motion detection for portable security camera applications , 2003, IEEE Trans. Consumer Electron..

[5]  Jaehyuk Choi,et al.  A Spatial-Temporal Multi-Resolution CMOS Image Sensor with Adaptive Frame Rates for Moving Objects in the Region-of-Interest , 2007, 2007 IEEE International Solid-State Circuits Conference. Digest of Technical Papers.

[6]  A. Dupret,et al.  SystemC validation of a low power analog CMOS image sensor architecture , 2007, 2007 IEEE Northeast Workshop on Circuits and Systems.

[7]  Derek Abbott,et al.  An insect vision-based motion detection chip , 1997, IEEE J. Solid State Circuits.

[8]  Ralph Etienne-Cummings,et al.  Vision chip for navigating and controlling Micro Unmanned Aerial Vehicles , 2003, Proceedings of the 2003 International Symposium on Circuits and Systems, 2003. ISCAS '03..

[9]  James E. Black,et al.  A novel method for video tracking performance evaluation , 2003 .

[10]  Guang Yang,et al.  Dynamically reconfigurable vision with high performance CMOS active pixel sensors (APS) , 2002, Proceedings of IEEE Sensors.

[11]  Orly Yadid-Pecht,et al.  Adaptive multiple resolution CMOS active pixel sensor , 2004 .

[12]  Antoine Manzanera,et al.  A Robust and Computationally Efficient Motion Detection Algorithm Based on Sigma-Delta Background Estimation , 2004, ICVGIP.

[13]  Mohamad Sawan,et al.  Variable resolution CMOS current mode active pixel sensor , 2000, 2000 IEEE International Symposium on Circuits and Systems. Emerging Technologies for the 21st Century. Proceedings (IEEE Cat No.00CH36353).

[14]  Tieniu Tan,et al.  A survey on visual surveillance of object motion and behaviors , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[15]  Paul L. McCarley,et al.  Large-format variable spatial acuity superpixel imaging: visible and infrared systems applications , 2004, SPIE Defense + Commercial Sensing.

[16]  Lionel Lacassagne,et al.  Implementing motion Markov detection on general purpose processor and associative mesh , 2005, Seventh International Workshop on Computer Architecture for Machine Perception (CAMP'05).

[17]  Ralph Etienne-Cummings,et al.  Normal Optical Flow measurement on a CMOS APS imager , 2004, 2004 IEEE International Symposium on Circuits and Systems (IEEE Cat. No.04CH37512).

[18]  Patrick Garda,et al.  Motion detection, labeling, data association and tracking, in real-time on RISC computer , 1999, Proceedings 10th International Conference on Image Analysis and Processing.

[19]  Lionel Lacassagne,et al.  Multirésolution adaptative pour imageurs CMOS très basse consommation , 2007 .

[20]  Hervé Mathias,et al.  Architecture for a low power image sensor with motion detection based ROI , 2007, 2007 14th IEEE International Conference on Electronics, Circuits and Systems.

[21]  Jacques-Olivier Klein,et al.  An improved analog computation cell for Paris II, a programmable vision chip , 2004, 2004 IEEE International Symposium on Circuits and Systems (IEEE Cat. No.04CH37512).

[22]  Mark Moelich.  Autonomous Motion Segmentation of Multiple Objects in Low Resolution Video Using Variational Level Sets , 2003 .

[23]  Larry H. Matthies,et al.  Multiresolution image sensor , 1997, IEEE Trans. Circuits Syst. Video Technol..

[24]  A. Dupret,et al.  Low Power Motion Detection with Low Spatial and Temporal Resolution for CMOS Image Sensor , 2007, 2006 International Workshop on Computer Architecture for Machine Perception and Sensing.