ABSTRACT
In the automatic railway anomaly inspection technology based on image processing and deep learning, an effective algorithm used for high-precision detection of the fastening system is very important, especially in turnout sections. It is challenging because the background of the turnout sections is complicated with various types of targets. This paper improved the Faster R-CNN model, used multi-scale feature map fusion for small targets. And modified predefined anchor to generate region proposals, added attention module to make the network focus on meaningful feature. Besides, this paper used cross-entropy function and SmoothL1 loss function for training and labeled 1200 image samples as dataset. Compared with the original Faster R-CNN model, the experimental results (AP) of the improved model in this paper increased from 96.3% to 98.9%, which effectively reduced the fault detection and missed detection and improved the accuracy of location.
- Sadeghi, J., Najar, M. M., Zakeri, J. A., & Kuttelwascher, C. (2019). Development of railway ballast geometry index using automated measurement system. Measurement, 138, 132-142.Google ScholarCross Ref
- Gibert, X., Patel, V. M., & Chellappa, R. (2016). Deep multitask learning for railway track inspection. IEEE transactions on intelligent transportation systems, 18(1), 153-164.Google Scholar
- Chen, J., Liu, Z., Wang, H., Nunez, A., & Han, Z. (2017). Automatic defect detection of fasteners on the catenary support device using deep convolutional neural network. IEEE Transactions on Instrumentation and Measurement, 67(2), 257-269.Google ScholarCross Ref
- Anzhong, Z., Xinyang, H., Minyu, J., & Xiukun, W. (2020, August). Multi-target defect detection of railway track based on image processing. In 2020 Chinese Control And Decision Conference (CCDC) (pp. 3377-3382). IEEE.Google ScholarCross Ref
- Wei, X., Yang, Z., Liu, Y., Wei, D., Jia, L., & Li, Y. (2019). Railway track fastener defect detection based on image processing and deep learning techniques: A comparative study. Engineering Applications of Artificial Intelligence, 80, 66-81.Google ScholarDigital Library
- Qi, H., Xu, T., Wang, G., Cheng, Y., & Chen, C. (2020). MYOLOv3-Tiny: A new convolutional neural network architecture for real-time detection of track fasteners. Computers in Industry, 123, 103303.Google ScholarCross Ref
- Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. arXiv preprint arXiv:1506.01497.Google Scholar
- He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).Google ScholarCross Ref
- Girshick, R. (2015). Fast r-cnn. In Proceedings of the IEEE international conference on computer vision (pp. 1440-1448).Google ScholarDigital Library
- Cao, C., Wang, B., Zhang, W., Zeng, X., Yan, X., Feng, Z., ... & Wu, Z. (2019). An improved faster R-CNN for small object detection. IEEE Access, 7, 106838-106846.Google ScholarCross Ref
- Lin, T. Y., Dollár, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2117-2125).Google ScholarCross Ref
- Xu, H., Yao, L., Zhang, W., Liang, X., & Li, Z. (2019). Auto-fpn: Automatic network architecture adaptation for object detection beyond classification. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 6649-6658).Google ScholarCross Ref
- Ghiasi, G., Lin, T. Y., & Le, Q. V. (2019). Nas-fpn: Learning scalable feature pyramid architecture for object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 7036-7045).Google ScholarCross Ref
- Woo, S., Park, J., Lee, J. Y., & Kweon, I. S. (2018). Cbam: Convolutional block attention module. In Proceedings of the European conference on computer vision (ECCV) (pp. 3-19).Google ScholarDigital Library
- Fu, H., Song, G., & Wang, Y. (2021). Improved YOLOv4 Marine Target Detection Combined with CBAM. Symmetry, 13(4), 623.Google ScholarCross Ref
- Eggert, C., Brehm, S., Winschel, A., Zecha, D., & Lienhart, R. (2017, July). A closer look: Small object detection in faster R-CNN. In 2017 IEEE international conference on multimedia and expo (ICME) (pp. 421-426). IEEE.Google ScholarCross Ref
Recommendations
Fruit target detection method based on faster R-CNN
With the rapid development of agricultural modernisation, fruit picking is becoming more and more automatic. The detection of fruit target by machine vision technology is the key to realise fruit automatic picking. In recent years, with the development of ...
Improved localization accuracy by LocNet for Faster R-CNN based text detection in natural scene images
Highlights- We are motivated to address the text localization accuracy problem and propose replacing the bounding box regression module with a novel LocNet based ...
AbstractAlthough Faster R-CNN based text detection approaches have achieved promising results, their localization accuracy is not satisfactory in certain cases due to their sub-optimal bounding box regression based localization modules. In ...
Local keypoint-based Faster R-CNN
AbstractRegion-based Convolutional Neural Network (R-CNN) detectors have achieved state-of-the-art results on various challenging benchmarks. Although R-CNN has achieved high detection performance, the research of local information in producing candidates ...
Comments