AspectNet: Aspect-Aware Anchor-Free Detector for Autonomous Driving
Source abstract
Abstract
The anchor-free-based object detection method is a crucial part in an autonomous driving system because of its low computing cost. However, the under-fitting of positive samples and over-fitting of negative samples affect the detection performance. An aspect-aware anchor-free detector is proposed in this paper to address this problem. Specifically, it adds an aspect prediction head at the end of the detector, which can learn different distributions of aspect ratios between other objects. The sample definition method is improved to alleviate the problem of positive and negative sample imbalance. A loss function is designed to strengthen the learning weight of the center point of the network. The validation results show that the AP50 and AP75 of the proposed method are 97.3% and 93.4% on BCTSDB, and the average accuracies of the car, pedestrian, and cyclist are 92.7%, 77.4%, and 78.2% on KITTI, respectively. The comparison results demonstrate that the proposed algorithm is better than existing anchor-free methods.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Video Surveillance and Tracking Methods · Visual Attention and Saliency Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing 100101, China
College of Robotics, Beijing Union University, Beijing 100101, China
Funding
National Natural Science Foundation of China · Beijing Municipal Education Commission Science and Technology Program · Beijing Union University Research and Innovation Projects for Postgraduates · Premium Funding Project for Academic Human Resources Development in Beijing Union University
References (37)
Show source-provided references
1. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks10.1109/TPAMI.2016.2577031 ↗
2. Focal Loss for Dense Object Detection10.1109/TPAMI.2018.2858826 ↗
3. CornerNet: Detecting Objects as Paired Keypoints10.1007/s11263-019-01204-1 ↗
4. Zhou, X., Wang, D., and Krähenbühl, P. (2019). Objects as Points. arXiv.
5. FCOS: A Simple and Strong Anchor-Free Object Detector
6. Zhang, S., Chi, C., Yao, Y., Lei, Z., and Li, S.Z. (2020, January 13–19). Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection. Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR42600.2020.00978 ↗
7. Redmon, J., and Farhadi, A. (2018). YOLOv3: An Incremental Improvement. arXiv.
8. Histograms of Oriented Gradients for Human Detection10.1109/CVPR.2005.177 ↗
9. Object Detection with Discriminatively Trained Part-Based Models10.1109/TPAMI.2009.167 ↗
10. Support-Vector Networks10.1007/BF00994018 ↗
11. Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014, January 23–28). Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA.10.1109/CVPR.2014.81 ↗
12. Girshick, R. (2015, January 7–13). Fast R-CNN. Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.10.1109/ICCV.2015.169 ↗
13. Cai, Z., and Vasconcelos, N. (2014, January 18–23). Cascade R-CNN: Delving Into High Quality Object Detection. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00644 ↗
14. SSD: Single Shot MultiBox Detector10.1007/978-3-319-46448-0_2 ↗
15. Zhou, X., Zhuo, J., and Krahenbuhl, P. (2019, January 15–20). Bottom-Up Object Detection by Grouping Extreme and Center Points. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.10.1109/CVPR.2019.00094 ↗
16. Yang, Z., Liu, S., Hu, H., Wang, L., and Lin, S. (November, January 27). RepPoints: Point Set Representation for Object Detection. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea.10.1109/ICCV.2019.00975 ↗
17. FoveaBox: Beyound Anchor-Based Object Detection10.1109/TIP.2020.3002345 ↗
18. ALODAD: An Anchor-Free Lightweight Object Detector for Autonomous Driving10.1109/ACCESS.2022.3166923 ↗
19. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27–30). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.91 ↗
20. Redmon, J., and Farhadi, A. (2017, January 21–26). YOLO9000: Better, Faster, Stronger. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.690 ↗
21. Long, J., Shelhamer, E., and Darrell, T. (2015, January 7–12). Fully Convolutional Networks for Semantic Segmentation. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.10.1109/CVPR.2015.7298965 ↗
22. Deep Sparse Rectifier Neural Networks
23. Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression10.1609/aaai.v34i07.6999 ↗
24. Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., and Belongie, S. (2017, January 21–26). Feature Pyramid Networks for Object Detection. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.106 ↗
25. Li, H., Xiong, P., An, J., and Wang, L. (2018). Pyramid Attention Network for Semantic Segmentation. arXiv.
26. Liang, T., Bao, H., Pan, W., and Pan, F. (2022). Traffic Sign Detection via Improved Sparse R-CNN for Autonomous Vehicles. J. Adv. Transp., 2022.10.1155/2022/3825532 ↗
27. Vision Meets Robotics: The KITTI Dataset10.1177/0278364913491297 ↗
28. Chen, K., Wang, J., Pang, J., Cao, Y., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., and Xu, J. (2019). MMDetection: Open MMLab Detection Toolbox and Benchmark. arXiv.
29. ImageNet Classification with Deep Convolutional Neural Networks10.1145/3065386 ↗
30. Glorot, X., and Bengio, Y. (2010, January 13–15). Understanding the Difficulty of Training Deep Feedforward Neural Networks. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, Sardinia, Italy.
31. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
32. Regionlets for Generic Object Detection10.1109/TPAMI.2015.2389830 ↗
33. Yang, B., Yan, J., Lei, Z., and Li, S.Z. (2016, January 27–30). CRAFT Objects from Images. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.650 ↗
34. Chen, X., Kundu, K., Zhang, Z., Ma, H., Fidler, S., and Urtasun, R. (2016, January 27–30). Monocular 3D Object Detection for Autonomous Driving. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.236 ↗
35. A Unified Multi-Scale Deep Convolutional Neural Network for Fast Object Detection10.1007/978-3-319-46493-0_22 ↗
36. Yi, J., Wu, P., and Metaxas, D.N. (2019). ASSD: Attentive Single Shot Multibox Detector. Comput. Vis. Image Underst., 189.10.1016/j.cviu.2019.102827 ↗
37. Receptive Field Block Net for Accurate and Fast Object Detection10.1007/978-3-030-01252-6_24 ↗