Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
144 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

Object-Size-Driven Design of Convolutional Neural Networks: Virtual Axle Detection based on Raw Data (2309.01574v4)

Published 4 Sep 2023 in cs.CV

Abstract: As infrastructure ages, the need for efficient monitoring methods becomes increasingly critical. Bridge Weigh-In-Motion (BWIM) systems are crucial for cost-effective determination of loads and, consequently, the residual service life of road and railway infrastructure. However, conventional BWIM systems require additional sensors for axle detection, which must be installed in potentially inaccessible locations or places that interfere with bridge operation. This study presents a novel approach for real-time detection of train axles using sensors arbitrarily placed on bridges, providing an alternative to dedicated axle detectors. The developed Virtual Axle Detector with Enhanced Receptive Field (VADER) has been validated on a single-track railway bridge using only acceleration measurements, detecting 99.9% of axles with a spatial error of 3.69cm. Using raw data as input outperformed the state-of-the-art spectrogram-based method in both speed and memory usage by 99%, thereby making real-time application feasible for the first time. Additionally, we introduce the Maximum Receptive Field (MRF) rule, a novel approach to optimise hyperparameters of Convolutional Neural Networks (CNNs) based on the size of objects. In this context, the object size relates to the fundamental frequency of a bridge. The MRF rule effectively narrows the hyperparameter search space, overcoming the need for extensive hyperparameter tuning. Since the MRF rule can theoretically be applied to all unstructured data, it could have implications for a wide range of deep learning problems, from earthquake prediction to object recognition.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (44)
  1. Moving force identification studies, i: Theory, Journal of Sound and Vibration 247 (2001) 59–76. URL: https://www.sciencedirect.com/science/article/pii/S0022460X01936302. doi:https://doi.org/10.1006/jsvi.2001.3630.
  2. A. Kazemi Amiri, C. Bucher, A procedure for in situ wind load reconstruction from structural response only based on field testing data, Journal of Wind Engineering and Industrial Aerodynamics 167 (2017) 75–86. URL: https://www.sciencedirect.com/science/article/pii/S0167610516303452. doi:https://doi.org/10.1016/j.jweia.2017.04.009.
  3. Estimation of modal loads using structural response, Journal of Sound and Vibration 326 (2009) 522–539. URL: https://www.sciencedirect.com/science/article/pii/S0022460X09004271. doi:https://doi.org/10.1016/j.jsv.2009.05.003.
  4. Joint input-response estimation for structural systems based on reduced-order models and vibration data from a limited number of sensors, Mechanical Systems and Signal Processing 29 (2012) 310–327. URL: https://www.sciencedirect.com/science/article/pii/S088832701200012X. doi:https://doi.org/10.1016/j.ymssp.2012.01.011.
  5. A time domain method for reconstruction of pedestrian induced loads on vibrating structures, Mechanical Systems and Signal Processing 171 (2022) 108887. URL: https://www.sciencedirect.com/science/article/pii/S0888327022000772. doi:https://doi.org/10.1016/j.ymssp.2022.108887.
  6. Improved axle detection for bridge weigh-in-motion systems using fiber optic sensors, Journal of Civil Structural Health Monitoring 7 (2017) 325–332. URL: https://link.springer.com/article/10.1007/s13349-017-0229-4. doi:10.1007/s13349-017-0229-4.
  7. Identification of moving train loads on railway bridge based on strain monitoring, Smart Structures and Systems 23 (2019) 263–278. URL: https://koreascience.or.kr/article/JAKO201913457807828.page. doi:10.12989/sss.2019.23.3.263.
  8. State-of-the-art review on bridge weigh-in-motion technology, Advances in Structural Engineering 19 (2016) 1514–1530. URL: http://journals.sagepub.com/doi/10.1177/1369433216655922. doi:10.1177/1369433216655922.
  9. Virtual axle method for bridge weigh-in-motion systems requiring no axle detector, Journal of Bridge Engineering 24 (2019) 04019086. URL: {https://ascelibrary.org/doi/abs/10.1061/%28ASCE%29BE.1943-5592.0001474}. doi:10.1061/(ASCE)BE.1943-5592.0001474.
  10. Strategies for Axle Detection in Bridge Weigh-in-Motion Systems, in: Proceedings of the International Conference on Weigh-In-Motion, June, 2012, pp. 79–88. URL: https://www.researchgate.net/publication/281031765_STRATEGIES_FOR_AXLE_DETECTION_IN_BRIDGE_WEIGH-IN-MOTION_SYSTEMS.
  11. Wavelet-based optimum identification of vehicle axles using bridge measurements, Applied Sciences 10 (2020). URL: https://www.mdpi.com/2076-3417/10/21/7485. doi:10.3390/app10217485.
  12. Estimation of bridge static response and vehicle weights by frequency response analysis, Canadian Journal of Civil Engineering 25 (1998) 631–639. URL: https://cdnsciencepub.com/doi/10.1139/l97-128. doi:10.1139/l97-128.
  13. Train classification using a weigh-in-motion system and associated algorithms to determine fatigue loads, Sensors 22 (2022). URL: https://www.mdpi.com/1424-8220/22/5/1772. doi:10.3390/s22051772.
  14. A survey and comparison of low-cost sensing technologies for road traffic monitoring, Sensors 18 (2018). URL: https://www.mdpi.com/1424-8220/18/10/3243. doi:10.3390/s18103243.
  15. Review of trackside monitoring solutions: From strain gages to optical fibre sensors, Sensors 15 (2015) 20115–20139. URL: https://www.mdpi.com/1424-8220/15/8/20115. doi:10.3390/s150820115.
  16. Recent developments in bridge weigh in motion (b-wim), Journal of Civil Structural Health Monitoring 6 (2016) 69–81. URL: https://link.springer.com/article/10.1007/s13349-015-0119-6. doi:10.1007/s13349-015-0119-6.
  17. An extended bridge weigh-in-motion system without vehicular axles and speed detectors using nonnegative lasso regularization, Journal of Bridge Engineering 28 (2023) 04023022. URL: https://ascelibrary.org/doi/abs/10.1061/JBENF2.BEENG-5864. doi:10.1061/JBENF2.BEENG-5864. arXiv:https://ascelibrary.org/doi/pdf/10.1061/JBENF2.BEENG-5864.
  18. Sound event detection: A tutorial, IEEE Signal Processing Magazine 38 (2021) 67–83. doi:10.1109/MSP.2021.3090678.
  19. Sound event detection in the dcase 2017 challenge, IEEE/ACM Transactions on Audio, Speech, and Language Processing 27 (2019) 992–1006. doi:10.1109/TASLP.2019.2907016.
  20. T. K. Chan, C. S. Chin, A comprehensive review of polyphonic sound event detection, IEEE Access 8 (2020) 103339–103373. doi:10.1109/ACCESS.2020.2999388.
  21. Few-shot sound event detection, in: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, pp. 81–85. doi:10.1109/ICASSP40776.2020.9054708.
  22. Deep learning for audio signal processing, IEEE Journal of Selected Topics in Signal Processing 13 (2019) 206–219. doi:10.1109/JSTSP.2019.2908700.
  23. Robust speech recognition via large-scale weak supervision, in: A. Krause, E. Brunskill, K. Cho, B. Engelhardt, S. Sabato, J. Scarlett (Eds.), Proceedings of the 40th International Conference on Machine Learning, volume 202 of Proceedings of Machine Learning Research, PMLR, 2023, pp. 28492–28518. URL: https://proceedings.mlr.press/v202/radford23a.html.
  24. 1d convolutional neural networks and applications: A survey, Mechanical Systems and Signal Processing 151 (2021) 107398. URL: https://www.sciencedirect.com/science/article/pii/S0888327020307846. doi:https://doi.org/10.1016/j.ymssp.2020.107398.
  25. Multi-channel spectrograms for speech processing applications using deep learning methods, Pattern Analysis and Applications 24 (2021) 423–431. URL: https://doi.org/10.1007/s10044-020-00921-5. doi:10.1007/s10044-020-00921-5.
  26. A study of time-frequency features for cnn-based automatic heart sound classification for pathology detection, Computers in Biology and Medicine 100 (2018) 132–143. URL: https://www.sciencedirect.com/science/article/pii/S0010482518301744. doi:https://doi.org/10.1016/j.compbiomed.2018.06.026.
  27. Acoustic scene classification in dcase 2019 challenge: Closed and open set classification and data mismatch setups, in: Workshop on Detection and Classification of Acoustic Scenes and Events, 2019. doi:10.33682/m5kp-fa97.
  28. Acoustic modelling from the signal domain using cnns, in: Interspeech 2016, 2016, pp. 3434–3438. URL: http://dx.doi.org/10.21437/Interspeech.2016-1495. doi:10.21437/Interspeech.2016-1495.
  29. H. B. Sailor, H. A. Patil, Novel unsupervised auditory filterbank learning using convolutional rbm for speech recognition, IEEE/ACM Transactions on Audio, Speech, and Language Processing 24 (2016) 2341–2353. doi:10.1109/TASLP.2016.2607341.
  30. Wavelet domain analysis for identification of vehicle axles from bridge measurements, Computers & Structures 84 (2006) 1792–1801. URL: https://www.sciencedirect.com/science/article/pii/S0045794906001933. doi:https://doi.org/10.1016/j.compstruc.2006.04.013.
  31. Non-intrusive schemes for speed and axle identification in bridge-weigh-in-motion systems, Measurement Science and Technology 28 (2017) 025102. URL: https://doi.org/10.1088/1361-6501/aa52ec. doi:10.1088/1361-6501/aa52ec.
  32. Vehicle axle identification using wavelet analysis of bridge global responses, Journal of Vibration and Control 23 (2017) 2830–2840. URL: https://journals.sagepub.com/doi/10.1177/1077546315623147. doi:10.1177/1077546315623147.
  33. Acceleration-based deep learning method for vehicle monitoring, IEEE Sensors Journal 21 (2021) 17154–17161. URL: https://ieeexplore.ieee.org/document/9437183. doi:10.1109/JSEN.2021.3082145.
  34. Virtual axle detector based on analysis of bridge acceleration measurements by fully convolutional network, Sensors 22 (2022). URL: https://www.mdpi.com/1424-8220/22/22/8963. doi:10.3390/s22228963.
  35. M. Reiterer, A. Firus, Dynamische analyse der zugüberfahrt bei eisenbahnbrücken unter berücksichtigung von nichtlinearen effekten, Beton-und Stahlbetonbau 117 (2022) 90–98.
  36. Pywavelets: A python package for wavelet analysis, Journal of Open Source Software 4 (2019) 1237. URL: https://doi.org/10.21105/joss.01237. doi:10.21105/joss.01237.
  37. Fully convolutional networks for semantic segmentation, in: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 3431–3440. URL: https://ieeexplore.ieee.org/document/7298965. doi:10.1109/CVPR.2015.7298965.
  38. U-net: Convolutional networks for biomedical image segmentation, in: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, Springer International Publishing, Cham, 2015, pp. 234–241. URL: https://link.springer.com/chapter/10.1007/978-3-319-24574-4_28. doi:10.1007/978-3-319-24574-4_28.
  39. Review the state-of-the-art technologies of semantic segmentation based on deep learning, Neurocomputing 493 (2022) 626–646. URL: https://www.sciencedirect.com/science/article/pii/S0925231222000054. doi:https://doi.org/10.1016/j.neucom.2022.01.005.
  40. Techniques and challenges of image segmentation: A review, Electronics 12 (2023). URL: https://www.mdpi.com/2079-9292/12/5/1199. doi:10.3390/electronics12051199.
  41. U-net and its variants for medical image segmentation: A review of theory and applications, IEEE Access 9 (2021) 82031–82057. doi:10.1109/ACCESS.2021.3086020.
  42. Deep residual learning for image recognition, in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778. URL: https://ieeexplore.ieee.org/document/7780459. doi:https://doi.org/10.1109/CVPR.2016.90.
  43. Y. Wu, K. He, Group normalization, International Journal of Computer Vision 128 (2020) 742–755. URL: https://doi.org/10.1007/s11263-019-01198-w. doi:10.1007/s11263-019-01198-w.
  44. Focal loss for dense object detection, in: 2017 IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2999–3007. doi:10.1109/ICCV.2017.324.

Summary

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

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