Challenges and Potential Solutions for Designing A Practical Pedestrian Detection Framework for Supporting Autonomous Driving

ABSTRACT

In recent years, in the face of the increasingly complicated traffic environment caused by the significant increase in the number of motor vehicles, in order to improve road traffic safety, autonomous driving technology has become the focus of research, and various related approaches have been proposed. Among them, the design of practical traffic-related target detection method has received a lot of attention as an indispensable prerequisite for vehicles to independently formulate pedestrian and obstacle collision avoidance strategies. In this article, we will first briefly introduce the development of related detection technologies. Then we will systematically introduce the current development trend of traffic target detection technology, and focus on the technical problems and related technical challenges that have not been solved by the existing methods in practical use. At the end of the article, we will provide some potential solutions to these challenges.

References

1. T. Begin, A. Busson, I. Guérin Lassous, and A. Boukerche. Video on demand in ieee 802.11p-based vehicular networks: Analysis and dimensioning. In Proc. ACM MSWiM, pages 303--310, 2018.
2. BMW. Intelligent driving. [Online]. Available: https://www.bmw.ca/en/topics/experience/connected-drive/bmw-connecteddrive-driver-assistance.html, 2019. Accessed on: May, 2019.
3. M. Braun, S. Krebs, F. Flohr, and D. M. Gavrila. Eurocity persons: A novel benchmark for person detection in traffic scenes. IEEE Trans. Pattern Anal. Mach. Intell., 41(8):1844--1861, 2019.
4. G. Brazil and X. Liu. Pedestrian detection with autoregressive network phases. In Proc. IEEE/CVF CVPR, pages 7224--7233, 2019.
5. G. Brazil, X. Yin, and X. Liu. Illuminating pedestrians via simultaneous detection and segmentation. In Proc. IEEE ICCV, pages 4960--4969, 2017.
6. N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. In Proc. IEEE/CVF CVPR, volume 1, pages 886--893, 2005.
7. M. Di Felice, L. Bedogni, and L. Bononi. Dysco: A dynamic spectrum and contention control framework for enhanced broadcast communication in vehicular networks. In Proc. ACM MobiWac, pages 97--106, 2012.
8. P. Dollar, S. Belongie, and P. Perona. The fastest pedestrian detector in the west. In Proc. BMVC, pages 68:1--68:11, 2010.
9. P. Dollar, Z. Tu, P. Perona, and S. Belongie. Integral channel features. In Proc. BMVC, pages 91:1--91:11, 2009.
10. P. Dollar, C. Wojek, B. Schiele, and P. Perona. Pedestrian detection: An evaluation of the state of the art. IEEE Trans. Pattern Anal. Mach. Intell., 34(4):743--761, 2012.
11. P. Dollár, R. Appel, S. Belongie, and P. Perona. Fast feature pyramids for object detection. IEEE Trans. Pattern Anal. Mach. Intell., 36(8):1532--1545, 2014.
12. X. Du, M. El-Khamy, J. Lee, and L. Davis. Fused dnn: A deep neural network fusion approach to fast and robust pedestrian detection. In Proc. IEEE WACV, pages 953--961, 2017.
13. X. Du, M. El-Khamy, V. I. Morariu, J. Lee, and L. Davis. Fused deep neural networks for efficient pedestrian detection, 2018.
14. P. Felzenszwalb, D. McAllester, and D. Ramanan. A discriminatively trained, multiscale, deformable part model. In Proc. IEEE/CVF CVPR, pages 1--8, 2008.
15. H. Ge, Y. Song, C. Wu, J. Ren, and G. Tan. Cooperative deep q-learning with q-value transfer for multi-intersection signal control. IEEE Access, 7:40797--40809, 2019.
16. A. Geiger, P. Lenz, and R. Urtasun. Are we ready for autonomous driving? the kitti vision benchmark suite. In Proc. IEEE/CVF CVPR, pages 3354--3361, 2012.
17. R. Girshick. Fast r-cnn. In Proc. IEEE ICCV, pages 1440--1448, 2015.
18. R. Girshick, J. Donahue, T. Darrell, and J. Malik. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proc. IEEE/CVF CVPR, pages 580--587, 2014.
19. K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In Proc. IEEE/CVF CVPR, pages 770--778, 2016.
20. D. P. Huttenlocher, G. A. Klanderman, and W. J. Rucklidge. Comparing images using the hausdorff distance. IEEE Trans. Pattern Anal. Mach. Intell., 15(9):850--863, 1993.
21. A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In Proc. NIPS, pages 1097--1105, 2012.
22. D. Li, B. Fu, Y. Wang, G. Lu, Y. Berezin, H. E. Stanley, and S. Havlin. Percolation transition in dynamical traffic network with evolving critical bottlenecks. Proceedings of the National Academy of Sciences, 112(3):669--672, 2015.
23. X. Liang, X. Du, G. Wang, and Z. Han. A deep reinforcement learning network for traffic light cycle control. IEEE Trans. Veh. Technol., 68(2):1243--1253, 2019.
24. C. Lin, J. Lu, G. Wang, and J. Zhou. Graininess-aware deep feature learning for pedestrian detection. In Proc. ECCV, pages 732--747. Springer, 2018.
25. A. Mammeri, D. Zhou, and A. Boukerche. Animal-vehicle collision mitigation system for automated vehicles. IEEE Trans. Syst., Man, Cybern. Syst., 46(9):1287--1299, 2016.
26. J. Mao, T. Xiao, Y. Jiang, and Z. Cao. What can help pedestrian detection? In Proc. IEEE/CVF CVPR, pages 6034--6043, 2017.
27. Mercedes Benz. Mercedes safety. [Online]. Available: https://www.mbusa.com/mercedes/benz/safety, 2019. Accessed on: May, 2019.
28. B. S. P. Dollar, C. Wojek and P. Perona. Caltech pedestrian detection benchmark. [Online]. Available: http://www.vision.caltech.edu/Image_Datasets/CaltechPedestrians/, July 2019. Accessed on: April., 2020.
29. P. Sun and A. Boukerche. Tvdr: A novel traffic volume aware data routing protocol for vehicular networks. In Proc. WCNC, 2019.
30. S. Ren, K. He, R. Girshick, and J. Sun. Faster r-cnn: Towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell., 39(6):1137--1149, 2017.
31. C. Rezende, R. W. Pazzi, and A. Boukerche. A reactive solution with a redundancy-based error correction mechanism for video dissemination over vehicular ad hoc networks. In Proc. ACM MSWiM, pages 343--352, 2012.
32. W. R. Schwartz, A. Kembhavi, D. Harwood, and L. S. Davis. Human detection using partial least squares analysis. In Proc. ICCV, pages 24--31, 2009.
33. K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. In Proc. ICLR, 2015.
34. T. Song, L. Sun, D. Xie, H. Sun, and S. Pu. Small-scale pedestrian detection based on topological line localization and temporal feature aggregation. In Proc. ECCV, pages 554--569, 2018.
35. T. Song, L. Sun, D. Xie, H. Sun, and S. Pu. Small-scale pedestrian detection based on topological line localization and temporal feature aggregation. In Proc. ECCV, pages 554--569. Springer, 2018.
36. P. Sun, N. Aljeri, and A. Boukerche. A fast vehicular traffic flow prediction scheme based on fourier and wavelet analysis. In Proc. Globecom, pages 1--6, 2018.
37. P. Sun, N. AlJeri, and A. Boukerche. Dacon: A novel traffic prediction and data-highway-assisted content delivery protocol for intelligent vehicular networks. IEEE Trans. Sustain. Comput., pages 1--1, 2020. Early access, DOI: 10.1109/TSUSC.2020.2971628.
38. P. Sun and A. Boukerche. A novel passive road side unit detection scheme in vehicular networks. In Proc. Globecom, pages 1--5, 2017.
39. P. Sun and A. Boukerche. Challenges of designing computer vision-based pedestrian detector for supporting autonomous driving. In Proc. IEEE MASS, pages 28--36, 2019.
40. P. Sun and A. Boukerche. Ai-assisted data dissemination methods for supporting intelligent transportation systems. Internet Technol. Lett., page e169, 2020. Early access, DOI: https://doi.org/10.1002/itl2.169.
41. P. Sun and A. Boukerche. A novel internet-of-vehicles assisted collaborative low-visible pedestrian detection approach. In Proc. IEEE Globecom, 2020. accepted.
42. P. Sun, A. Boukerche, and R. W. L. Coutinho. A novel cloudlet-dwell-time estimation method for assisting vehicular edge computing applications. In Proc. Globecom, pages 1--6, 2019.
43. P. Sun and N. Samaan. Random node failures and wireless networks connectivity: Theoretical analysis. IEEE Wireless Commun. Lett., 4(5):461--464, 2015.
44. T. Tan, F. Bao, Y. Deng, A. Jin, Q. Dai, and J. Wang. Cooperative deep reinforcement learning for large-scale traffic grid signal control. IEEE Trans. Cybern., pages 1--14, 2019. Early Access.
45. Z. Tang and A. Boukerche. An improved algorithm for road markings detection with svm and roi restriction: Comparison with a rule-based model. In Proc. ICC, pages 1--6, 2018.
46. The Insurance Corporation of British Columbia. Crashes involving. [Online]. Available: https://www.icbc.com/about-icbc/newsroom/Documents/crashes-involving.pdf, 2019. Accessed on: June., 2020.
47. Y. Tian, P. Luo, X. Wang, and X. Tang. Pedestrian detection aided by deep learning semantic tasks. In Proc. IEEE/CVF CVPR, pages 5079--5087, 2015.
48. U.S. Department of Transportation. Congestion pricing - a primer: Overview. [Online]. Available: https://ops.fhwa.dot.gov/publications/fhwahop08039/cp_prim1_02.htm, Feb. 2017. Accessed on: May, 2019.
49. U.S. National Highway Traffic Safety Administration. 2017 pedestrians traffic safety fact sheet. [Online]. Available: https://crashstats.nhtsa.dot.gov/Api/Public/ViewPublication/812681, 2019. Accessed on: April., 2020.
50. S. Walk, N. Majer, K. Schindler, and B. Schiele. New features and insights for pedestrian detection. In Proc. IEEE CVPR, pages 1030--1037, 2010.
51. S. Wang. Pcn: Part and context information for pedestrian detection with cnns. In Proc. BMVC, pages 34:1--34:13, 2017.
52. X. Wang, T. X. Han, and S. Yan. An hog-lbp human detector with partial occlusion handling. In Proc. ICCV, pages 32--39, 2009.
53. X. Wang, T. Xiao, Y. Jiang, S. Shao, J. Sun, and C. Shen. Repulsion loss: Detecting pedestrians in a crowd. In Proc. IEEE/CVF CVPR, pages 7774--7783, 2018.
54. C. Wojek and B. Schiele. A performance evaluation of single and multi-feature people detection. In G. Rigoll, editor, Proc. DAGM, volume 5096, pages 82--91, 2008.
55. M. D. Zeiler and R. Fergus. Visualizing and understanding convolutional networks. In Proc. ECCV, pages 818--833, 2014.
56. L. Zhang, G. Zeng, D. Li, H.-J. Huang, H. E. Stanley, and S. Havlin. Scale-free resilience of real traffic jams. Proceedings of the National Academy of Sciences, 116(18):8673--8678, 2019.
57. S. Zhang, L. Wen, X. Bian, Z. Lei, and T. Z. Li. Occlusion-aware r-cnn: Detecting pedestrians in a crowd. In Proc. ECCV, pages 657--674. Springer, 2018.
58. S. Zhang, J. Yang, and B. Schiele. Occluded pedestrian detection through guided attention in cnns. In Proc. IEEE/CVF CVPR, pages 6995--7003, 2018.
59. X. Zhang, L. Cheng, B. Li, and H. Hu. Too far to see? not really!-pedestrian detection with scale-aware localization policy. IEEE Trans. Image Process., 27(8):3703--3715, 2018.
60. D. Zhao, Y. Chen, and L. Lv. Deep reinforcement learning with visual attention for vehicle classification. IEEE Trans. Cogn. Devel. Syst., 9(4):356--367, 2017.
61. C. Zhou and J. Yuan. Bi-box regression for pedestrian detection and occlusion estimation. In Proc. ECCV, pages 138--154. Springer, 2018.
62. Z. Zou, Z. Shi, Y. Guo, and J. Ye. Object detection in 20 years: A survey. [Online]. Available: https://arxiv.org/abs/1905.05055, 2019.

Index Terms

• Computing methodologies

  • Artificial intelligence

    • Distributed artificial intelligence

      • Cooperation and coordination

• Information systems

  • Information systems applications

• Networks

  • Network types

    • Ad hoc networks

      • Mobile ad hoc networks