Fuzzy boundary guidance and oriented Gaussian function-based anchor-free network for rail positioning in turnout sections

Abstract

Rail positioning is a critical step for detecting rail defects downstream. However, existing orientation-based detectors struggle to effectively manage rails with arbitrary inclinations and high aspect ratios, particularly in turnout sections. To address these challenges, a fuzzy boundary guidance and oriented Gaussian function-based anchor-free network termed the rail positioning network (RP-Net) is proposed for rail positioning in turnout sections. First, an oriented Gaussian function-based label generation strategy is introduced. This strategy produces smoother and more accurate label values by accounting for the specific aspect ratios and orientations of the rails. Second, a fuzzy boundary learning module is developed to enhance the network’s ability to model the rail boundary regions effectively. Furthermore, a boundary guidance module is developed to direct the network in fusing the features obtained from the downsampled network output with the boundary region features, which have been enhanced to contain more refined positional and structural information. A local channel attention mechanism is integrated into this module to identify critical channels. Finally, experiments conducted on the tracking dataset show that the proposed RP-Net achieves high positioning accuracy and demonstrates strong adaptability in complex scenarios.

Keywords

rail positioning / label generation / boundary guidance / oriented object detection

References

[1] LANG N, WANG D C, CHENG P, et al. Rail surface defect inspection via a self-reference template and similarity evaluation[J]. Measurement Science and Technology, 2022, 33(1): 015401.

[2] LI Y X, MIN Y Z, YUE B. ISRM: Introspective self-supervised reconstruction model for rail surface defect detection and segmentation[J]. Measurement Science and Technology, 2024, 35(5): 055208.

[3] WANG S, ZHANG L J, YIN G J. Defect identification method for steel surfaces based on improved YOLOv5[J]. Journal of Southeast University (English Edition), 2024, 40(1): 49-57.

[4] YE J Q, STEWART E, CHEN Q Y, et al. A vision-based method for line-side switch rail condition monitoring and inspection[J]. Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 2022, 236(8): 986-996.

[5] JAGANNATHAN J, SHERAJDHEEN A, VIJAY DEEPAK R M, et al. License plate character segmentation using horizontal and vertical projection with dynamic thresholding[C]// 2013 IEEE International Conference on Emerging Trends in Computing, Communication and Nanotechnology (ICECCN). Tirunelveli, India, 2013: 700-705.

[6] VON GIOI R G, JAKUBOWICZ J, MOREL J M, et al. LSD: A fast line segment detector with a false detection control[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(4): 722-732.

[7] SOBEL I, FELDMAN G. A 3 × 3 isotropic gradient operator for image processing[R]. Stanford, CA, USA: Stanford Artificial Intelligence Laboratory, 1968.

[8] ROBERTS L. Machine perception of three-dimensional solids[C]// Optical and Electro-Optical Information Processing. Cambridge, MA, USA: MIT Press, 1963: 159-197.

[9] CANNY J. A computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8(6): 679-698.

[10] RONNEBERGER O, FISCHER P, BROX T. U-Net: Convolutional networks for biomedical image segmentation[C]// International Conference on Medical Image Computing and Computer-Assisted Intervention. Munich, Germany, 2015: 234-241.

[11] QIN X B, ZHANG Z C, HUANG C Y, et al. U2-Net: Going deeper with nested U-structure for salient object detection[J]. Pattern Recognition, 2020, 106: 107404.

[12] ZHOU Z W, SIDDIQUEE M M R, TAJBAKHSH N, et al. UNet++: A nested U-Net architecture for medical image segmentation[C]// 4th Deep Learning in Medical Image Analysis (DLMIA) Workshop. Granada, Spain, 2018, 11045: 3-11.

[13] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL]. (2014-09-04)[2023-06-15]. https://arxiv.org/abs/1409.1556v6.

[14] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: Towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.

[15] SHANG L D, YANG Q S, WANG J N, et al. Detection of rail surface defects based on CNN image recognition and classification[C]// 2018 20th International Conference on Advanced Communication Technology (ICACT). Chuncheon, Republic of Korea, 2018: 45-51.

[16] ZHOU J, ZHOU Z L, LUO Y, et al. Object detection in remote sensing images based on region mask contrastive distillation[J]. Journal of Southeast University (Natural Science Edition), 2024, 54(3): 761-771. (in Chinese)

[17] XIA G S, BAI X, DING J, et al. DOTA: A large-scale dataset for object detection in aerial images[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA, 2018: 3974-3983.

[18] LIU Z K, YUAN L, WENG L B, et al. A high resolution optical satellite image dataset for ship recognition and some new baselines[C]// Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods. Porto, Portugal, 2017: 324-331.

[19] ZHAO P B, QU Z S, BU Y J, et al. PolarDet: A fast, more precise detector for rotated target in aerial images[J]. International Journal of Remote Sensing, 2021, 42(15): 5831-5861.

[20] HOU L P, LU K, XUE J, et al. Shape-adaptive selection and measurement for oriented object detection[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2022, 36(1): 923-932.

[21] YI J R, WU P X, LIU B, et al. Oriented object detection in aerial images with box boundary-aware vectors[C]// 2021 IEEE Winter Conference on Applications of Computer Vision (WACV). Waikoloa, HI, USA, 2021: 2149-2158.

[22] CHEN Z M, CHEN K A, LIN W Y, et al. PIoU loss: Towards accurate oriented object detection in complex environments[C]// European Conference on Computer Vision—ECCV 2020. Glasgow, UK, 2020: 195-211.

[23] YANG X, YAN J C, FENG Z M, et al. R3Det: Refined single-stage detector with feature refinement for rotating object[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(4): 3163-3171.

[24] HAN J M, DING J, XUE N, et al. ReDet: A rotation-equivariant detector for aerial object detection[C]// 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville, TN, USA, 2021: 2785-2794.

[25] LI J X, TIAN Y, XU Y P, et al. Oriented object detection in remote sensing images with anchor-free oriented region proposal network[J]. Remote Sensing, 2022, 14(5): 1246.

[26] LIAO R X, WU T, ZHANG Y M, et al. Vision-based vessel detection for vessel-bridge collision warnings under complex scenes[J]. Journal of Southeast University (Natural Science Edition), 2024, 40(1): 33-40. (in Chinese)

[27] CHENG G, WANG J B, LI K, et al. Anchor-free oriented proposal generator for object detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5625411.

[28] HAN J M, DING J, LI J, et al. Align deep features for oriented object detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 60: 5602511.

[29] MING Q, MIAO L J, ZHOU Z Q, et al. Sparse label assignment for oriented object detection in aerial images[J]. Remote Sensing, 2021, 13(14): 2664.

[30] MING Q, ZHOU Z Q, MIAO L J, et al. Dynamic anchor learning for arbitrary-oriented object detection[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(3): 2355-2363.

[31] DUAN K W, BAI S, XIE L X, et al. CenterNet: Keypoint triplets for object detection[C]// 2019 IEEE/CVF International Conference on Computer Vision (ICCV). Seoul, Republic of Korea, 2019: 6568-6577.

[32] YANG M K, YU K, ZHANG C, et al. DenseASPP for semantic segmentation in street scenes[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT, USA, 2018: 3684-3692.

[33] MA J Q, SHAO W Y, YE H, et al. Arbitrary-oriented scene text detection via rotation proposals[J]. IEEE Transactions on Multimedia, 2018, 20(11): 3111-3122.

[34] DING J, XUE N, LONG Y, et al. Learning RoI transformer for oriented object detection in aerial images[C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, CA, USA, 2019: 2844-2853.

[35] XIE X X, CHENG G, WANG J B, et al. Oriented R-CNN for object detection[C]// 2021 IEEE/CVF International Conference on Computer Vision (ICCV). Montreal, QC, Canada, 2021: 3500-3509.

Funding

Major Scientific Research Projects of China Railway Group(K2019G046)

National Key Research and Development Program of China(2020YFB1600700)