A Battery Powered Vision Sensor for Forensic Evidence Gathering

We describe a novel battery-powered vision sensor developed to support surveillance and crime prevention activities of the Law Enforcement Agencies (LEA) in isolated or peripheral areas not equipped with energy grid. The sensor consists of a low-power, always-on vision chip interfaced with a processor executing visual tasks on demand. The chip continuously inspects the imaged scene in search for events potentially related to criminal acts. When an event is detected, the chip wakes-up the processor, normally in idle state, and starts delivering images to it together with information on the region containing the event. The processor re-works the received data in order to confirm, to recognize the detected action and in case to send the alert to the LEA. The sensor has been developed within a H2020 EU project and has been successfully tested in real-life scenarios.

[1]  David Blaauw,et al.  A 467nW CMOS visual motion sensor with temporal averaging and pixel aggregation , 2013, 2013 IEEE International Solid-State Circuits Conference Digest of Technical Papers.

[2]  Jaehyuk Choi,et al.  A 3.4µW CMOS image sensor with embedded feature-extraction algorithm for motion-triggered object-of-interest imaging , 2013, 2013 IEEE International Solid-State Circuits Conference Digest of Technical Papers.

[3]  Hossein Ragheb,et al.  MuHAVi: A Multicamera Human Action Video Dataset for the Evaluation of Action Recognition Methods , 2010, 2010 7th IEEE International Conference on Advanced Video and Signal Based Surveillance.

[4]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Massimo Gottardi,et al.  A $64\times64$ Pixel Vision Sensor for Local Binary Pattern Computation , 2019, IEEE Transactions on Circuits and Systems I: Regular Papers.

[6]  Barbara Caputo,et al.  Recognizing human actions: a local SVM approach , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[7]  Kenji Suzuki,et al.  Linear-time connected-component labeling based on sequential local operations , 2003, Comput. Vis. Image Underst..

[8]  M. Gottardi,et al.  A 100 $\mu$ W 128 $\times$ 64 Pixels Contrast-Based Asynchronous Binary Vision Sensor for Sensor Networks Applications , 2009, IEEE Journal of Solid-State Circuits.

[9]  Barbara Caputo,et al.  Recognizing human actions: a local SVM approach , 2004, ICPR 2004.