基于Faster-RCNN的道路异常状态检测方法研究
Research on Road Abnormal State Detection Method Based on Faster-RCNN
摘要: 利用无人机等方式开展道路巡检时采集的图像存在图像背景复杂以及目标较小等问题，准确识别道路异常目标成为智能巡检研究热点。本文对两阶段目标检测算法Faster-RCNN进行改进，利用深度残差网络ResNet50作为网络的特征提取backbone，并利用不同层次的特征构造特征金字塔FPN网络，提高了道路异常状态检测模型的性能。
Abstract: The images collected when using drones and other means to carry out road inspections have problems such as complex image backgrounds and small targets. Accurately identifying abnormal road targets has become a research hotspot in intelligent inspection. This paper improves the two-stage target detection algorithm Faster-RCNN, uses the deep residual network ResNet50 as the feature extraction backbone of the network, and uses different levels of features to construct a feature pyramid FPN network, which improves the performance of the road abnormal state detection model.
文章引用：梁泓, 赵曙光. 基于Faster-RCNN的道路异常状态检测方法研究[J]. 计算机科学与应用, 2022, 12(3): 546-553. https://doi.org/10.12677/CSA.2022.123055

参考文献

[1] 郑晓光, 杨群, 吕伟民. 沥青路面水损害的病害特征与机理分析[J]. 公路工程, 2006, 31(2): 96-98.
[2] Girshick, R., Donahue, J., Darrell, T., et al. (2014) Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmen-tation. arXiv:1311.2524 [cs.CV] [Google Scholar] [CrossRef] 
[3] Girshick, R. (2015) Fast R-CNN. 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, 7-13 December 2015, 1440-1448. [Google Scholar] [CrossRef] 
[4] Ren, S., He, K., Girshick, R. and Sun, J. (2016) Faster R-CNN: To-wards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Ma-chine Intelligence, 39, 1137-1149. [Google Scholar] [CrossRef] 
[5] Redmon, J., Divvala, S., Girshick, R., et al. (2016) You Only Look Once: Unified，Real-Time Object Detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, 27-30 June 2016, 779-788. [Google Scholar] [CrossRef] 
[6] Liu, W., Anguelov, D., Erhan, D., et al. (2016) SSD: Single Shot Multibox Detector. arXiv:1512.02325 [cs.CV] [Google Scholar] [CrossRef] 
[7] Simonyan, K. and Zisserman, A. (2015) Very Deep Convolu-tional Networks for Large-Scale Image Recognition. arXiv:1409.1556 [cs.CV]
[8] Bengio, Y., Simard, P. and Frasconi, P. (1994) Learning Long-Term Dependencies with Gradient Descent Is Difficult. IEEE Transactions on Neural Networks, 5, 157-166. [Google Scholar] [CrossRef] [PubMed]