期刊
IEEE ACCESS
卷 8, 期 -, 页码 211164-211172出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2020.3036620
关键词
Autonomous vehicle (AV); advanced driver assistance system (ADAS); object detection; deep learning; driving safety
资金
- National Natural Science Foundation of China [51805332]
- Natural Science Foundation of Guangdong Province [2018A030310532]
- Shenzhen Fundamental Research Fund [JCYJ20190808142613246]
- Young Elite Scientists Sponsorship Program - China Society of Automotive Engineers
Effectively detecting road objects in various environments would significantly improve driving safety for autonomous vehicles. However, small objects, low illumination, and blurred outline in images strongly limit the performance of current road object detection methods. To solve these problems, this paper proposed a novel deep learning anchor-free approach based on CenterNet. The atrous spatial pyramid pooling (ASPP) was used to extract features from multiple scales to improve the detection performance while not increasing the computational cost and the number of parameters. The space to depth algorithm was then adopted in our proposed approach to optimize the traditional downsampling process. A large-scale naturalistic driving dataset (BDD100K) was used to examined the effectiveness of our proposed approach. The experimental results show that our proposed approach can effectively improve the detection performance on small objects in various traffic situations.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据