0466336 20240103213042.120161205235959.9 2016 motion detection background subtraction obejct detection python1300 camera Zynq FPGA Trenz cav_un_auth*0101179 Zpracování signálů Department of Signal Processing ZS ZS Department of Signal Processing 100 Pohl Zdeněk UTIA-B Ústav teorie informace a automatizace AV ČR, v. v. i. http://sp.utia.cz/index.php?ids=results&id=imgproc cav_un_auth*0306850 7H14004 GA MŠk Three demo applications implemented for ALMARVI Python Camera Platform. Each demo shows one example of hardware accelerated video processing algorithm. As the first algorithm was chosen simple motion detection algorithm which uses Sobel filter on two consecutive frames of video and compares detected edges. The second algorithm is a background subtraction based on Gaussian Mixture-based background/Fore-ground Segmentation Algorithm. Its source is available in OpenCV library. It was simplified and modified to be synthesizable by Vivado HLS. The last one is the algorithm for object detection. We have used Cascade Classifier algorithm which is available in sources in OpenCV 2.4 library. The sources were also modified to be synthesizable by Vivado HLS. Only the detection process was hardware accelerated in FPGA. IN 2017 1 http://hdl.handle.net/11104/0265784 1 S 2016 2016