DOI QR코드

DOI QR Code

A study on improving self-inference performance through iterative retraining of false positives of deep-learning object detection in tunnels

터널 내 딥러닝 객체인식 오탐지 데이터의 반복 재학습을 통한 자가 추론 성능 향상 방법에 관한 연구

  • Kyu Beom Lee (Dept. of Future & Smart Construction Research, Korea Institute of Civil Engineering and Building Technology / Smart City and Construction Convergence, University of Science & Technology (UST)) ;
  • Hyu-Soung Shin (Dept. of Future & Smart Construction Research, Korea Institute of Civil Engineering and Building Technology)
  • 이규범 (한국건설기술연구원 미래스마트건설연구본부 / 과학기술연합대학원대학교 (UST) 스마트도시건설융합) ;
  • 신휴성 (한국건설기술연구원 미래스마트건설연구본부)
  • Received : 2024.02.07
  • Accepted : 2024.03.11
  • Published : 2024.03.31

Abstract

In the application of deep learning object detection via CCTV in tunnels, a large number of false positive detections occur due to the poor environmental conditions of tunnels, such as low illumination and severe perspective effect. This problem directly impacts the reliability of the tunnel CCTV-based accident detection system reliant on object detection performance. Hence, it is necessary to reduce the number of false positive detections while also enhancing the number of true positive detections. Based on a deep learning object detection model, this paper proposes a false positive data training method that not only reduces false positives but also improves true positive detection performance through retraining of false positive data. This paper's false positive data training method is based on the following steps: initial training of a training dataset - inference of a validation dataset - correction of false positive data and dataset composition - addition to the training dataset and retraining. In this paper, experiments were conducted to verify the performance of this method. First, the optimal hyperparameters of the deep learning object detection model to be applied in this experiment were determined through previous experiments. Then, in this experiment, training image format was determined, and experiments were conducted sequentially to check the long-term performance improvement through retraining of repeated false detection datasets. As a result, in the first experiment, it was found that the inclusion of the background in the inferred image was more advantageous for object detection performance than the removal of the background excluding the object. In the second experiment, it was found that retraining by accumulating false positives from each level of retraining was more advantageous than retraining independently for each level of retraining in terms of continuous improvement of object detection performance. After retraining the false positive data with the method determined in the two experiments, the car object class showed excellent inference performance with an AP value of 0.95 or higher after the first retraining, and by the fifth retraining, the inference performance was improved by about 1.06 times compared to the initial inference. And the person object class continued to improve its inference performance as retraining progressed, and by the 18th retraining, it showed that it could self-improve its inference performance by more than 2.3 times compared to the initial inference.

터널 내 CCTV를 통한 딥러닝 객체인식 적용에 있어서 터널의 열악한 환경조건, 즉 낮은 조도 및 심한 원근현상으로 인해 오탐지가 대량 발생한다. 이 문제는 객체인식 성능에 기반한 영상유고시스템의 신뢰성 문제로 직결되므로 정탐지 향상과 더불어 오탐지의 저감 방안이 더욱 필요한 상황이다. 이에 본 논문은 딥러닝 객체인식 모델을 기반으로, 오탐지 데이터의 재학습을 통해 오탐지의 저감뿐만 아니라 정탐지 성능 향상도 함께 추구하는 오탐지 학습법을 제안한다. 본 논문의 오탐지 학습법은 객체인식 단계를 기반으로 진행되며, 학습용 데이터셋 초기학습 - 검증용 데이터셋 추론 - 오탐지 데이터 정정 및 데이터셋 구성 - 학습용 데이터셋에 추가 후 재학습으로 이어진다. 본 논문은 이에 대한 성능을 검증하기 위해 실험을 진행하였으며, 우선 선행 실험을 통해 본 실험에 적용할 딥러닝 객체인식 모델의 최적 하이퍼파라미터를 결정하였다. 그리고 본 실험에서는 학습영상 포맷을 결정하기 위한 실험, 반복적인 오탐지 데이터셋의 재학습을 통해 장기적인 성능향상을 확인하기 위한 실험을 순차적으로 진행하였다. 그 결과, 첫 번째 본 실험에서는 추론된 영상 내에서 객체를 제외한 배경을 제거시키는 경우보다 배경을 포함시키는 경우가 객체인식 성능에 유리한 것으로 나타났으며, 두 번째 본 실험에서는 재학습 차수별 독립적으로 오탐지 데이터를 재학습시키는 경우보다 차수마다 발생하는 오탐지 데이터를 누적시켜 재학습 시키는 경우가 지속적인 객체인식 성능 향상 측면에서 유리한 것으로 나타났다. 두 실험을 통해 결정된 방법으로 오탐지 데이터 재학습을 진행한 결과, 차량 객체 클래스는 1차 재학습 이후부터 AP값이 0.95 이상 우수한 추론 성능이 발현되었으며, 5차 재학습까지 초기 추론 대비 약 1.06배 추론성능이 향상되었다. 보행자 객체 클래스는 재학습이 진행됨에 따라 지속적으로 추론 성능이 향상되었으며, 18차 재학습까지 초기 추론대비 2.3배 이상 추론성능이 자가 향상될 수 있음을 보였다.

Keywords

Acknowledgement

본 연구는 과학기술정보통신부 한국건설기술연구원 주요사업사업의 일환으로 수행되었다(과제번호 20230081-001, 극한건설 환경 구현 인프라 및 TRL6 이상급 극한건설 핵심기술 개발).

References

  1. Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M. (2020), "Yolov4: Optimal speed and accuracy of object detection", arXiv preprint arXiv:2004.10934.
  2. Brownlee, J. (2022), Difference between a batch and an epoch in a neural network, https://machinelearningmastery.com/difference-between-a-batch-and-an-epoch (December 27, 2023).
  3. Dalal, N., Triggs, B. (2005), "Histograms of oriented gradients for human detection", Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), San Diego, Vol. 1, pp. 886-893.
  4. Fawcett, T. (2006), "An introduction to ROC analysis", Pattern Recognition Letters, Vol. 27, No. 8, pp. 861-874.
  5. Felzenszwalb, P., McAllester, D., Ramanan, D. (2008), "A discriminatively trained, multiscale, deformable part model", Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, pp. 1-8.
  6. Frias-Velazquez, A., Nino-Castaneda, J.O., Jelaca, V., Pizurica, A., Philips, W. (2011), "A mathematical morphology-based approach for vehicle detection in road tunnels", Applications of Digital Image Processing XXXIV, Vol. 8135, pp. 560-567.
  7. Girshick, R., Donahue, J., Darrell, T., Malik, J. (2014), "Rich feature hierarchies for accurate object detection and semantic segmentation", Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, pp. 580-587.
  8. LeCun, Y., Bengio, Y., Hinton, G. (2015), "Deep learning", Nature, Vol. 521, No. 7553, pp. 436-444.
  9. Lee, K.B., Shin, H.S. (2019), "Effect on self-enhancement of deep-learning inference by repeated training of false detection cases in tunnel accident image detection", Journal of Korean Tunnelling and Underground Space Association, Vol. 21, No. 3, pp. 419-432.
  10. Lee, K.B., Shin, H.S. (2022), "A study for improvement of far-distance performance of a tunnel accident detection system by using an inverse perspective transformation", Journal of Korean Tunnelling and Underground Space Association, Vol. 24, No. 3, pp. 247-262.
  11. Lewis, D.D. (1990), "Representation quality in text classification: An introduction and experiment", Speech and Natural Language: Proceedings of a Workshop Held at Hidden Valley, Pennsylvania, pp. 288-295.
  12. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., Berg, A.C. (2016), "SSD: Single shot multibox detector", Proceedings of the 14th European Conference on Computer Vision (ECCV 2016), Amsterdam, pp. 21-37.
  13. Lu, D., Weng, Q. (2007), "A survey of image classification methods and techniques for improving classification performance", International journal of Remote sensing, Vol. 28, No. 5, pp. 823-870.
  14. MOLIT (2015), Study on revision of installation and operation guideline for hazard mitigation facilities of road tunnels, Ministry of Land, Infrastructure and Transport, pp. 223-236.
  15. MOLIT (2021), Guideline of installation and management of disaster prevention facilities on road tunnels (established rule of MOLIT No. 336), Ministry of Land, Infrastructure and Transport, Korea.
  16. Neubeck, A., Van Gool, L. (2006), "Efficient non-maximum suppression", Proceedings of the 18th International Conference on Pattern Recognition (ICPR'06), Vol. 3, pp. 850-855.
  17. Redmon, J., Divvala, S., Girshick, R., Farhadi, A. (2016), "You only look once: unified, real-time object detection", Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CV PR), Las Vegas, pp. 779-788.
  18. Ren, S., He, K., Girshick, R., Sun, J. (2015), "Faster R-CNN: Towards real-time object detection with region proposal networks", Proceedings of the Advances in Neural Information Processing Systems, Montreal, pp. 91-99.
  19. Sergey, T., Venu, G. (2013), Handbook of Statistics, Vol. 31, Elsevier, Amsterdam, pp. 151-175.
  20. Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M. (2023), "YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors", Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, pp. 7464-7475.
  21. Zhu, M. (2004), "Recall, precision and average precision", Working Paper, Department of Statistics and Actuarial Science, University of Waterloo, Vol. 2, No. 30, pp. 1-11.
  22. Zou, Z., Chen, K., Shi, Z., Guo, Y., Ye, J. (2023), "Object detection in 20 years: A survey", Proceedings of the IEEE, Vol. 111, No. 3, pp. 257-276.