Abstract
In the paper, we proposed a deep learning-based industrial equipment detection algorithm ROMS R-CNN (Rotation Occlusion Multi-Scale Region-CNN). It can solve the problem of inaccurate detection of industrial equipment under complex working conditions such as multi-scale ratio, rotation tilt, occlusion and overlap. The method proposed in this paper first is to construct the MobileNetV2 as the feature pyramid network, and then to combine high semantic information with high resolution information solved industrial equipment detection of different scales. Secondly, a specific rotation anchor scheme is proposed, and the data set is clustered through the k-means algorithm to obtain a specific aspect ratio. Combined with the rotation angle, a rotation anchor of any direction and size is generated to solve the problem of easy tilting of industrial equipment. Finally, a Non-Maximum Suppression algorithm with penalty factors is introduced to solve the overlapping in industrial equipment detection. The experimental results in common industrial equipment detection show that this method is better than other algorithms, significantly improves the missed detection and false detection, and the mAP reaches 0.939.
Funder
Jilin Scientific and Technological Development Program
Department of Science and Technology of Jilin Province
Publisher
Public Library of Science (PLoS)
Reference35 articles.
1. Spatial pyramid pooling in deep convolutional networks for visual recognition;K. He;IEEE Trans,2015
2. R. Girshick. Fast R-CNN. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Boston, MA, USA, 2015. URL: https://doi.org/10.1109/ICCV.2015.169
3. Faster R-CNN: Towards realtime object detection with region proposal networks;S. Ren;IEEE Trans,2017
4. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi. You only look once:Unified, real-time object detection. Las Vegas, NV, USA, 2016, URL: https://doi.org/10.1109/CVPR.2016.91
5. Redmon, Joseph, and A. Farhadi. YOLO9000: Better, Faster, Stronger. Honolulu, HI, USA, 2017. https://doi.org/10.1109/CVPR.2017.690
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献