Multi-task faster R-CNN for nighttime pedestrian detection and distance estimation
| Autor: | Chunlei Luo, Yuxia Duan, Ahmad Osman, Stefano Sfarra, Abubakar Shitu, Xiaobiao Dai, Hongmei Zhang, Junping Hu |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Faster R-CNN
Computer science Pedestrian detection Nighttime Pedestrian detection (PD) ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Word error rate Multi-task 02 engineering and technology Pedestrian 01 natural sciences 010309 optics 0103 physical sciences Computer vision Ground truth business.industry Detector Distance estimation (DE) 021001 nanoscience & nanotechnology Condensed Matter Physics Atomic and Molecular Physics and Optics Electronic Optical and Magnetic Materials Task (computing) Near-infrared (NIR) Lidar Artificial intelligence 0210 nano-technology Intelligent control business |
| Zdroj: | Infrared Physics & Technology. 115:103694 |
| ISSN: | 1350-4495 |
| DOI: | 10.1016/j.infrared.2021.103694 |
| Popis: | Distance estimation and pedestrian detection are critical for safe driving operation decision-making and autonomous vehicle intelligent control strategies. This paper proposes a novel multi-task Faster R-CNN detector which simultaneously realizes distance estimation and pedestrian detection using an improved ResNet-50 architecture. Images were acquired using a near-infrared camera with two near-infrared fill-lights devices during real road nighttime scenarios. Ground truth pedestrian distances used for training were obtained using LIDAR. The data used to optimize the multi-task Faster R-CNN detector were approximately 20 k high-quality near-infrared images with marked pedestrians and tagged distance values. The proposed algorithm including the distance estimation runs at a speed exceeding 7 fps. Pedestrian detection accuracy reached nearly 80% with a total average absolute distance estimation error rate of less than 5%. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect