Browse > Article
http://dx.doi.org/10.9766/KIMST.2022.25.4.381

Occlusion Robust Military Vehicle Detection using Two-Stage Part Attention Networks  

Cho, Sunyoung (Defense AI Technology Center, Agency for Defense Development)
Publication Information
Journal of the Korea Institute of Military Science and Technology / v.25, no.4, 2022 , pp. 381-389 More about this Journal
Abstract
Detecting partially occluded objects is difficult due to the appearances and shapes of occluders are highly variable. These variabilities lead to challenges of localizing accurate bounding box or classifying objects with visible object parts. To address these problems, we propose a two-stage part-based attention approach for robust object detection under partial occlusion. First, our part attention network(PAN) captures the important object parts and then it is used to generate weighted object features. Based on the weighted features, the re-weighted object features are produced by our reinforced PAN(RPAN). Experiments are performed on our collected military vehicle dataset and synthetic occlusion dataset. Our method outperforms the baselines and demonstrates the robustness of detecting objects under partial occlusion.
Keywords
Military Vehicle Detection; Occlusion Robust; Part Attention Networks;
Citations & Related Records
연도 인용수 순위
  • Reference
1 H. Zhu, P. Tang, J. Park, S. Park, A. Yuille, "Robustness of Object Recognition Under Extreme Occlusion in Humans and Computational Models," CoRR, Vol. abs/1905.04598, 2019.
2 A. Fawzi, P. Frossard, "Measuring the Effect of Nuisance Variables on Classifiers," BMVC, 2016.
3 C. Zhou, J. Yuan, "Multi-Label Learning of Part Detectors for Heavily Occluded Pedestrian Detection," ICCV, pp. 3486-3495, 2017.
4 P. F. Felzenszwalb, R. B. Girshick, D. A. McAllester, D. Ramanan, "Object Detection with Discriminatively Trained Part-based Models," TPAMI, Vol. 32, No. 9, pp. 1627-1645, 2010.   DOI
5 C. Zhou, J. Yuan, "Occlusion Pattern Discovery for Object Detection and Occlusion Reasoning," TCSVT, Vol. 30, No. 7, pp. 2067-2080, 2020.
6 S. Ren, K. He, R. Girshick, J. Sun, "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks," NIPS, pp. 91-99, 2015.
7 R. Girshick, "Fast R-CNN," ICCV, pp. 1440-1448, 2015.
8 Y. Pang, J. Xie, M. H. Khan, R. M. Anwer, F. S. Khan, L. Shao, "Mask-Guided Attention Network for Occluded Pedestrian Detection," ICCV, pp. 4967-4975, 2018.
9 Y. Tian, P. Luo, X. Wang, X. Tang, "Deep Learning Strong Parts for Pedestrian Detection," ICCV, pp. 1904-1912, 2015.
10 C. Zhou, J. Yuan, "Bi-Box Regression for Pedestrian Detection and Occlusion Estimation," ECCV, pp. 135-151, 2018.
11 S. Yan, Q. Liu, "Inferring Occluded Features for Fast Object Detection," Signal Processing, Vol. 110, pp. 188-198, 2015.   DOI
12 X. Wang, T. X. Han, S. Yan, "An HOG-LBP Human Detector with Partial Occlusion Handling," ICCV, pp. 32-39, 2009.
13 S. Zhang, L. Wen, X. Bian, Z. Lei, S. Z. Li, "Occlusion-Aware R-CNN: Detecting Pedestrians in a Crowd," ECCV, pp. 657-674, 2018.
14 K. He, X. Zhang, S. Ren, J. Sun, "Deep Residual Learning for Image Recognition," CVPR, pp. 770-778, 2016.
15 J. Wang, L. Xie, A.L. Yuille, Z. Zhang, C. Xie, "Deepvoting: A Robust and Explainable Deep Network for Semantic Part Detection Under Partial Occlusion," CVPR, pp. 1372-1380, 2018.
16 C. Chi, S. Zhang, J. Xing, Z. Lei, S. Z. Li, X. Zou, "PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes," AAAI, pp. 10639-10646, 2020.
17 V. Mnih, N. Heess, A. Graves, K. Kavukcuoglu, "Recurrent Models of Visual Attention," NIPS, pp. 2204-2212, 2014.
18 M. Cimpoi, S. Maji, I. Kokkinos, S. Mohamed, A. Vedaldi, "Describing Textures in the Wild," CVPR, pp. 3606-3613, 2016.
19 T. DeVries, G. W. Taylor, "Improved Regularization of Convolutional Neural Networks with Cutout," arXiv preprint arXiv:1708.04552, 2017.
20 S. Yun, D. Han, S. J. Oh, S. Chun, Y. Yoo, "Cutmix: Regularization Strategy to Train Strong Classifiers with Localizable Features," ICCV, pp. 6023-6032, 2019.
21 C. Zhou, J. Yuan, "Non-Rectangular Part Discovery for Object Detection," BMCV, 2014.