Abstract | ||
---|---|---|
A surveillance system requires to achieve high accuracy of object detection at all times and to meet real-time processing requirements (30 frames per second) with high energy-efficiency. Since thermal cameras allow to see even in darkness unlike a RGB camera, object detection with a thermal camera obtains higher accuracy in the night, and thereby it has attracted much attention. However, since it is challenging to extract informative features from a thermal image, implementation challenges of an object detection with high accuracy remain. To meet the requirements, we present a sparse YOLOv2-based pedestrian detector with a thermal camera on an FPGA. For high accuracy, we propose a preprocessing that concatenates a thermal image with the background subtracted one for a detector to extract more informative features. Also, we develop a zero weight skipping architecture dedicated to our detector that contains a vectorizing unit that packs successive valid values into the same memory address to realize high parallel degree calculation. It leads to meet the real-time processing requirement with high energy-efficiency. Compared with a conventional one, F-score was 29 points higher, and speed was 3.3 times faster. Therefore, our system is more suitable for surveillance systems. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/ReConFig48160.2019.8994773 | 2019 International Conference on ReConFigurable Computing and FPGAs (ReConFig) |
Keywords | Field | DocType |
FPGA,Thermal Camera,YOLOv2,Pedestrian Detection | Object detection,Computer science,Field-programmable gate array,Real-time computing,Preprocessor,RGB color model,Frame rate,Memory address,Detector,Pedestrian detection | Conference |
ISSN | ISBN | Citations |
2325-6532 | 978-1-7281-1958-8 | 0 |
PageRank | References | Authors |
0.34 | 6 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ryosuke Kuramochi | 1 | 0 | 2.70 |
Masayuki Shimoda | 2 | 8 | 6.45 |
Youki Sada | 3 | 1 | 1.71 |
Shimpei Sato | 4 | 43 | 13.03 |
Hiroki Nakahara | 5 | 155 | 37.34 |