Citation: | CHEN Yong, WANG Zhen, ZHANG Jiaojiao. Lightweight Detection of Railway Object Intrusion Based on Spectral Pooling and Shuffled-Convolutional Block Attention Module Enhancement[J]. Journal of Southwest Jiaotong University, 2024, 59(6): 1294-1304. doi: 10.3969/j.issn.0258-2724.20220074 |
In infrared low-light scenes, railway object intrusion detection faces low detection accuracy, and it is difficult to achieve lightweight real-time detection. Therefore, a lightweight detection method of railway object intrusion based on convolutional block attention module (CBAM) enhancement was proposed. Firstly, the Darknet53 feature extraction network was improved by deep separable convolution to achieve lightweight extraction of railway object intrusion characteristics in infrared low-light scenes. Secondly, semantic-guided infrared spectral pooling was used for feature enhancement to improve the feature quality of infrared image downsampling. Then, a shuffled-CBAM was proposed to achieve feature extraction and fusion of key infrared targets and improve the accuracy of infrared target detection. Finally, the lightweight anchor-free network was used to predict the output result of railway object intrusion, overcoming the deficiency of poor real-time performance due to non-maximum value suppression operation with anchor frame detection, and it reduced calculation load and speeded up the detection efficiency. The experimental results show that the lightweight model has higher detection accuracy, and the size of the model is reduced by 179.01 MB after the improvement. The detection rate is increased to 39 frames/s, which is 3.9 times that of the YOLOv4 method. Compared with other detection methods, the proposed method can detect infrared railway object intrusion quickly and accurately.
[1] |
TIAN R L, SHI H M, GUO B Q, et al. Multi-scale object detection for high-speed railway clearance intrusion[J]. Applied Intelligence, 2022, 52(4): 3511-3526. doi: 10.1007/s10489-021-02534-9
|
[2] |
CHEN J B, TALLEY J, KELLY K F. Infrared object classification with a hybrid optical convolution neural network[J]. Applied Optics, 2021, 60(25): G224-G231. doi: 10.1364/AO.427973
|
[3] |
刘可佳,马荣生,唐子木,等. 采用优化卷积神经网络的红外目标识别系统[J]. 光学精密工程,2021,29(4): 822-831. doi: 10.37188/OPE.20212904.0822
LIU Kejia, MA Rongsheng, TANG Zimu, et al. Design of infrared target recognition system with optimized convolutional neural network[J]. Optics and Precision Engineering, 2021, 29(4): 822-831. doi: 10.37188/OPE.20212904.0822
|
[4] |
LI Y S, LI Z Z, ZHANG C, et al. Infrared maritime dim small target detection based on spatiotemporal cues and directional morphological filtering[J]. Infrared Physics and Technology, 2021, 115: 103657.1-103657.19. doi: 10.1016/j.infrared.2021.103657
|
[5] |
LI Q, NIE J Y, QU S C. A small target detection algorithm in infrared image by combining multi-response fusion and local contrast enhancement[J]. Optik, 2021, 241: 166919.1-166919.12. doi: 10.1016/j.ijleo.2021.166919
|
[6] |
HAN J H, LIU C Y, LIU Y C, et al. Infrared small target detection utilizing the enhanced closest-mean background estimation[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14: 645-662. doi: 10.1109/JSTARS.2020.3038442
|
[7] |
FAN M M, TIAN S Q, LIU K, et al. Infrared small target detection based on region proposal and CNN classifier[J]. Signal, Image and Video Processing, 2021, 15(8): 1927-1936. doi: 10.1007/s11760-021-01936-z
|
[8] |
李淼,林再平,樊建鹏,等. 基于深度时空卷积神经网络的点目标检测(英文)[J]. 红外与毫米波学报,2021,40(1): 122-132. doi: 10.11972/j.issn.1001-9014.2021.01.017
LI Miao, LIN Zaiping, FAN Jianpeng, et al. Point target detection based on deep spatial-temporal convolution neural network[J]. Journal of Infrared and Millimeter Waves, 2021, 40(1): 122-132. doi: 10.11972/j.issn.1001-9014.2021.01.017
|
[9] |
DU J M, LU H Z, HU M F, et al. CNN-based infrared dim small target detection algorithm using target-oriented shallow-deep features and effective small anchor[J]. IET Image Processing, 2021, 15(1): 1-15. doi: 10.1049/ipr2.12001
|
[10] |
LI Y D, LIU Y, DONG H, et al. Intrusion detection of railway clearance from infrared images using generative adversarial networks[J]. Journal of Intelligent & Fuzzy Systems, 2021, 40(3): 3931-3943.
|
[11] |
GUO F, QIAN Y, SHI Y F. Real-time railroad track components inspection based on the improved YOLOv4 framework[J]. Automation in Construction, 2021, 125: 1-15. doi: 10.1016/j.autcon.2021.103596
|
[12] |
ZOU W, YIN G D, LIU H J, et al. Low-observable Target detection method for autonomous vehicles based on multi-modal feature fusion[J]. China Mechanical Engineering, 2021, 32(9): 1114-1125.
|
[13] |
MENG L, SUN X Y, ZHAO B, et al. An identification method of high-speed railway sign based on convolutional neural network[J]. Acta Automatica Sinica, 2020, 46(3): 518-530.
|
[14] |
吴双忱,左峥嵘. 基于深度卷积神经网络的红外小目标检测[J]. 红外与毫米波学报,2019,38(3): 371-380. doi: 10.11972/j.issn.1001-9014.2019.03.019
WU Shuangchen, ZUO Zhengrong. Small target detection in infrared images using deep convolutional neural networks[J]. Journal of Infrared and Millimeter Waves, 2019, 38(3): 371-380. doi: 10.11972/j.issn.1001-9014.2019.03.019
|
[15] |
LI Y D, DONG H, LI H G, et al. Multi-block SSD based on small object detection for UAV railway scene surveillance[J]. Chinese Journal of Aeronautics, 2020, 33(6): 1747-1755. doi: 10.1016/j.cja.2020.02.024
|
[16] |
HSIEH C C, LIN Y W, TSAI L H, et al. Offline deep-learning-based defective track fastener detection and inspection system[J]. Sensors and Materials, 2020, 32(10): 3429.1-3429.14. doi: 10.18494/SAM.2020.2921
|
[17] |
LIU S W, YU L, ZHANG D K. An efficient method for high-speed railway dropper fault detection based on depthwise separable convolution[J]. IEEE Access, 2019, 7: 135678-135688. doi: 10.1109/ACCESS.2019.2942079
|
[18] |
ZHOU A R, XIE W X, PEI J H. Background modeling in the Fourier domain for maritime infrared target detection[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2020, 30(8): 2634-2649. doi: 10.1109/TCSVT.2019.2922036
|
[19] |
李恒超,刘香莲,刘鹏,等. 基于多尺度感知的密集人群计数网络[J]. 西南交通大学学报,2024,59(5): 1176-1183,1214. doi: 10.3969/j.issn.0258-2724.20220823
LI Hengchao , LIU Xianglian , LIU Peng , et al. Dense crowd counting network based on multi-scale perception[J]. Journal of Southwest Jiaotong University, 2024, 59(5): 1176-1183,1214. doi: 10.3969/j.issn.0258-2724.20220823
|
[20] |
YANG K, CHANG S L, TIAN Z X, et al. Automatic polyp detection and segmentation using shuffle efficient channel attention network[J]. Alexandria Engineering Journal, 2022, 61(1): 917-926. doi: 10.1016/j.aej.2021.04.072
|
[21] |
CHEN Y W, SONG B, ZENG Y, et al. A deep learning-based approach for fault diagnosis of current-carrying ring in catenary system[J]. Neural Computing and Applications, 2023, 35(33): 23725-23737. doi: 10.1007/s00521-021-06280-4
|
[22] |
ZHOU X, WANG D, KRAHENBUHL P. Objects as points[J]. Applied Physics Reviews, 2019, 1904: 07850.1-07850.12.
|
[1] | FAN Hong, HOU Yun, LI Bailin, XIONG Ying. Adaptive Detection Algorithm for High-Speed Railway Fasteners by Vision[J]. Journal of Southwest Jiaotong University, 2020, 55(4): 896-902. doi: 10.3969/j.issn.0258-2724.20180496 |
[2] | ZHANG Shuangyang, ZHAO Renda, JIA Yi, WANG Yongbao, XIE Haiqing. Model Test Study on Long-Span Railway Concrete Arch Bridge with Rigid Skeleton[J]. Journal of Southwest Jiaotong University, 2017, 30(6): 1088-1096. doi: 10.3969/j.issn.0258-2724.2017.06.008 |
[3] | LIAO Hongjian, ZHU Qingnü, ZAN Yuewen, XIE Yongyong, SUN Junyu. Detection of Ballastless Track Diseases in High-Speed Railway Based on Ground Penetrating Radar[J]. Journal of Southwest Jiaotong University, 2016, 29(1): 8-13. doi: 10.3969/j.issn.0258-2724.2016.01.002 |
[4] | PENG Qiyuan, YANG Kui, WEN Chao, TAO Siyu. Organization Methods of Overnight Operation for Chinese High-Speed Railways[J]. Journal of Southwest Jiaotong University, 2015, 28(4): 569-576. doi: 10.3969/j.issn.0258-2724.2015.04.001 |
[5] | PENG Qiyuan, BAO Jingjing, WEN Chao, FENG Liping. Evaluation Theory and Method of High-Speed Train Diagrams[J]. Journal of Southwest Jiaotong University, 2013, 26(6): 969-974. doi: 10.3969/j.issn.0258-2724.2013.06.001 |
[6] | LI Renxian, GUAN Yongjiu, ZHAO Jing, ZHAO Jiwei. Aerodynamic Analysis on Entrance Hood of High Speed railway Tunnels[J]. Journal of Southwest Jiaotong University, 2012, 25(2): 175-180. doi: 10.3969/j.issn.0258-2724.2012.02.001 |
[7] | WANG Jing, WANG Dian-Hai, CHEN Song. Macro Planning of Highway Hubs Adapting to Changchun-Jilin High-Speed Railway Project[J]. Journal of Southwest Jiaotong University, 2011, 24(5): 853-860. doi: 10.3969/j.issn.0258-2724.2011.05.024 |
[8] | QIU Yanjun, FANG Mingjing, ZHANG Xiaojing, WEI Yongxing. Dynamic Analysis of Structural Adaptivity of Ballastless Track Substructure of High-Speed Railway[J]. Journal of Southwest Jiaotong University, 2011, 24(2): 183-187. doi: 10.3969/j.issn.0258-2724.2011.02.001 |
[9] | ZHAN Yongxiang, JIANG Guanlu, NIU Guohui, WEI Yongxing. Model Test Investigation of Pile-Plank Embankment of Ballastless Truck for High-Speed Railway[J]. Journal of Southwest Jiaotong University, 2007, 20(4): 400-403,408. |
[10] | CAI Cheng-biao. Calculation of Additional Longitudinal Forces in Continuously Welded Rails on Supper-Large Bridges of High-Speed Railways[J]. Journal of Southwest Jiaotong University, 2003, 16(5): 609-614. |
[11] | LENGJun-feng, LUFeng-shan, WANGMei-yun. Study on Forecast of the PassengerTraffic Volume ofHigh-Speed Railways[J]. Journal of Southwest Jiaotong University, 2001, 14(1): 88-91. |
[12] | LIUhua. Study on Rational Distance between Stations of High-Speed Railways[J]. Journal of Southwest Jiaotong University, 2001, 14(3): 245-249. |
[13] | LIUWan-ming. The Prerequisite to Investment in High-Speed Railway in the View of Market Demand[J]. Journal of Southwest Jiaotong University, 2000, 13(4): 379-382. |