Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
162 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Ultra-Fast Adaptive Track Detection Network (2405.13538v1)

Published 22 May 2024 in cs.CV

Abstract: Railway detection is critical for the automation of railway systems. Existing models often prioritize either speed or accuracy, but achieving both remains a challenge. To address the limitations of presetting anchor groups that struggle with varying track proportions from different camera angles, an ultra-fast adaptive track detection network is proposed in this paper. This network comprises a backbone network and two specialized branches (Horizontal Coordinate Locator and Perspective Identifier). The Perspective Identifier selects the suitable anchor group from preset anchor groups, thereby determining the row coordinates of the railway track. Subsequently, the Horizontal Coordinate Locator provides row classification results based on multiple preset anchor groups. Then, utilizing the results from the Perspective Identifier, it generates the column coordinates of the railway track. This network is evaluated on multiple datasets, with the lightweight version achieving an F1 score of 98.68% on the SRail dataset and a detection rate of up to 473 FPS. Compared to the SOTA, the proposed model is competitive in both speed and accuracy. The dataset and code are available at https://github.com/idnihai/UFATD

Definition Search Book Streamline Icon: https://streamlinehq.com
References (32)
  1. An optical fiber intrusion detection system for railway security. Sensors and Actuators A: Physical, 253:91–100, 2017.
  2. Improving lane detection with adaptive homography prediction. The Visual Computer, 39(2):581–595, 2023.
  3. Rethinking efficient lane detection via curve modeling. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 17062–17070, 2022.
  4. Material classification and semantic segmentation of railway track images with deep convolutional neural networks. In 2015 IEEE International Conference on Image Processing (ICIP), pages 621–625. IEEE, 2015.
  5. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
  6. Squeezenet: Alexnet-level accuracy with 50x fewer parameters and< 0.5 mb model size. arXiv preprint arXiv:1602.07360, 2016.
  7. Reading text in the wild with convolutional neural networks. International journal of computer vision, 116:1–20, 2016.
  8. Dnn based camera attitude estimation using aggregated information from camera and depth images. In 2023 IEEE/SICE International Symposium on System Integration (SII), pages 1–6. IEEE, 2023.
  9. Camera attitude estimation by neural network using classification network method instead of numerical regression. In 2022 IEEE/SICE International Symposium on System Integration (SII), pages 401–407. IEEE, 2022.
  10. Thomas Laurent. Train ego-path detection on railway tracks using end-to-end deep learning. arXiv preprint arXiv:2403.13094, 2024.
  11. Rail detection: An efficient row-based network and a new benchmark. In Proceedings of the 30th ACM International Conference on Multimedia, pages 6455–6463, 2022.
  12. Condlanenet: a top-to-down lane detection framework based on conditional convolution. In Proceedings of the IEEE/CVF international conference on computer vision, pages 3773–3782, 2021.
  13. Towards end-to-end lane detection: an instance segmentation approach. In 2018 IEEE intelligent vehicles symposium (IV), pages 286–291. IEEE, 2018.
  14. Judith MS Prewitt et al. Object enhancement and extraction. Picture processing and Psychopictorics, 10(1):15–19, 1970.
  15. Ultra fast structure-aware deep lane detection. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXIV 16, pages 276–291. Springer, 2020.
  16. Fcanet: Frequency channel attention networks. In Proceedings of the IEEE/CVF international conference on computer vision, pages 783–792, 2021.
  17. Ultra fast deep lane detection with hybrid anchor driven ordinal classification. IEEE transactions on pattern analysis and machine intelligence, 2022.
  18. Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4510–4520, 2018.
  19. A 3x3 isotropic gradient operator for image processing. a talk at the Stanford Artificial Project in, pages 271–272, 1968.
  20. A novel lane line detection algorithm for driverless geographic information perception using mixed-attention mechanism resnet and row anchor classification. ISPRS International Journal of Geo-Information, 12(3):132, 2023.
  21. Anchor-adaptive railway track detection from unmanned aerial vehicle images. Computer-Aided Civil and Infrastructure Engineering, 2023a.
  22. Trirnet: Real-time rail recognition network for uav-based railway inspection. IEEE Transactions on Intelligent Transportation Systems, 2023b.
  23. UIC. Uic safety report 2023, 2023. URL https://safetydb.uic.org/IMG/pdf/uic_safety_report_2023.pdf. Date of visit: 2024-01-08.
  24. A rail detection algorithm for accurate recognition of train fuzzy video. Cyber-Physical Systems, 8(1):67–84, 2022a.
  25. Lre-net: A vision-based real-time rail extraction method under metro tunnel low-light scene. Measurement, 221:113567, 2023.
  26. A keypoint-based global association network for lane detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1392–1401, 2022b.
  27. An adaptive track segmentation algorithm for a railway intrusion detection system. Sensors, 19(11), 2019a. ISSN 1424-8220. doi: 10.3390/s19112594. URL https://www.mdpi.com/1424-8220/19/11/2594.
  28. Railnet: A segmentation network for railroad detection. IEEE Access, 7:143772–143779, 2019b.
  29. Dalnet: A rail detection network based on dynamic anchor line. IEEE Transactions on Instrumentation and Measurement, 2024.
  30. Clrnet: Cross layer refinement network for lane detection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 898–907, 2022.
  31. Rail detection based on lsd and the least square curve fitting. International Journal of Automation and Computing, 18(1):85–95, 2021.
  32. Geometry constraints-based method for visual rail track extraction. Journal of Transportation Systems Engineering and Information Technology, 17(6):56, 2017.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets