Abstract
In this paper an embedded vision system for human silhouette detection in thermal images is presented. As the computing platform a reprogrammable device (FPGA – Field Programmable Gate Array) is used. The detection algorithm is based on a sliding window approach, which content is compared with a probabilistic template. Moreover, detection is four scales in supported. On the used test database, the proposed method obtained 97% accuracy, with average one false detection per frame. Due to the used parallelization and pipelining real-time processing for 720 × 480 @ 50 fps and 1280 × 720 @ 50 fps video streams was achieved. The system has been practically verified in a test setup with a thermal camera.
References
[1] Bailey, D.G. (2011). Design for embedded image processing on FPGAs. John Wiley & Sons.
[2] Benenson, R., Omran, M., Hosang, J., Schiele, B. (2014, September). Ten years of pedestrian detection, what have we learned?. In European Conference on Computer Vision (pp. 613-627). Springer International Publishing
[3] Bulat, B., Kryjak, T., Gorgon, M. (2014, September). Implementation of advanced foreground segmentation algorithms gmm, vibe and pbas in fpga and gpu-a comparison. In International Conference on Computer Vision and Graphics (pp. 124-131). Springer International Publishing
[4] Dalal, N., Triggs, B. (2005, June). Histograms of oriented gradients for human detection. In Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on (Vol. 1, pp. 886-893). IEEE
[5] Fukui, H., Yamashita, T., Yamauchi, Y., Fujiyoshi, H., Murase, H. (2015, June). Pedestrian detection based on deep convolutional neural network with ensemble inference network. In Intelligent Vehicles Symposium (IV), 2015 IEEE (pp. 223-228). IEEE
[6] Geronimo, D., Lopez, A.M., Sappa, A.D., Graf, T. (2010). Survey of pedestrian detection for advanced driver assistance systems. IEEE transactions on pattern analysis and machine intelligence, 32(7), 1239-1258
[7] Hurney, P., Waldron, P., Morgan, F., Jones, E., Glavin, M. (2015). Review of pedestrian detection techniques in automotive far-infrared video. IET intelligent transport systems, 9(8), 824-832
[8] Lakshmi, A., Faheema, A.G.J., Deodhare, D. (2016). Pedestrian detection in thermal images: An automated scale based region extraction with curvelet space validation. Infrared Physics & Technology, 76, 421-438
[9] Nanda, H., Davis, L. (2002, June). Probabilistic template based pedestrian detection in infrared videos. In Intelligent Vehicle Symposium, 2002. IEEE (Vol. 1, pp. 15-20). IEEE
[10] Negied, N.K., Hemayed, E.E., Fayek, M. B. (2015). Pedestrians’ detection in thermal bands-Critical survey. Journal of Electrical Systems and Information Technology, 2(2), 141-148
[11] Walczyk, R. (2013). Hardware architectures for infrared pedestrian detection systems
[12] Walczyk, R., Armitage, A., Binnie, T.D. (2009). An embedded real-time pedestrian detection system using an infrared camera
[13] Walczyk, R., Balazs, A., Armitage, A., Binnie, T.D. (2011). System architectures for infrared pedestrian tracking
[14] Xiao, H., Song, H., He, W., Yuan, K. (2015, August). Real-time shape and pedestrian detection with FPGA. In Mechatronics and Automation (ICMA), 2015 IEEE International Conference on (pp. 2381-2386). IEEE
