Near infrared nighttime road pedestrians recognition based on convolutional neural network
| Autor: | Jianqiao Meng, Xiaobiao Dai, Shicai Liu, Caiqi Hu, Dapeng Chen, Chunlei Luo, Yuxia Duan, Junping Hu, Yunze He |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Computer science
business.industry Pedestrian recognition Pedestrian detection Near-infrared spectroscopy 02 engineering and technology Pedestrian Protection system 021001 nanoscience & nanotechnology Condensed Matter Physics 01 natural sciences Convolutional neural network Atomic and Molecular Physics and Optics Electronic Optical and Magnetic Materials 010309 optics Imaging quality 0103 physical sciences Softmax function Computer vision Artificial intelligence 0210 nano-technology business |
| Zdroj: | Infrared Physics & Technology. 97:25-32 |
| ISSN: | 1350-4495 |
| DOI: | 10.1016/j.infrared.2018.11.028 |
| Popis: | Pedestrian recognition is the core technology of pedestrian detection in pedestrian protection systems. This paper compares and analyzes, visible and infrared images obtained via visible-spectrum, near-infrared, short-wave infrared, and long-wave infrared cameras. The results show that near-infrared camera was the best for nighttime pedestrian detection when device cost and pedestrian imaging quality were considered. This paper reports on the first time use of a self-learning softmax with a 9-layer Convolutional Neural Network (CNN) model to identify near-infrared nighttime pedestrians. 267,000 samples obtained from the near-infrared images were employed to optimize the CNN recognition model. Collected near-infrared nighttime samples had 3 categories (background, pedestrian, and cyclist or motorcyclist) and will be made publicly available for researchers use. Testing results indicated that the optimized CNN model using self-learning softmax had a competitive accuracy and potential in real-time pedestrian recognition. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect