ABSTRACT
Scale variation of pedestrian targets is a major challenge in pedestrian detection, which leads to difficulties for pedestrian detection algorithms to accurately capture pedestrian targets at different scales. To address the above problems, this paper proposes a multi-scale pedestrian detection method based on attention mechanism and feature fusion. First, a new feature fusion module is constructed to improve the problem of insufficient semantic information of shallow features, so that the feature information of different scales can be fully fused to strengthen the detector's feature extraction ability for small-scale target pedestrians. Second, we introduce a spatial channel attention mechanism in the network to suppress irrelevant background information and enhance the extraction of key feature information of pedestrian targets. Finally, we optimize the original prior box parameters to generate more suitable prior boxes for detecting pedestrians to improve detection accuracy. Comparison experiment results on Caltech-USA and CityPersons pedestrian detection datasets show that our method achieves very competitive performance with the state-of-the-art methods.
- Dollar, Piotr, "Pedestrian detection: An evaluation of the state of the art." IEEE transactions on pattern analysis and machine intelligence 34.4 (2011): 743-761.Google Scholar
- Ren, Shaoqing, "Faster r-cnn: Towards real-time object detection with region proposal networks." Advances in neural information processing systems 28 (2015).Google Scholar
- Viola, Paul, and Michael Jones. "Rapid object detection using a boosted cascade of simple features." Proceedings of the 2001 IEEE computer society conference on computer vision and pattern recognition. CVPR 2001. Vol. 1. Ieee, 2001.Google Scholar
- Dalal, Navneet, and Bill Triggs. "Histograms of oriented gradients for human detection." 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR'05). Vol. 1. Ieee, 2005.Google Scholar
- Hsu, Wei-Yen, and Wen-Yen Lin. "Adaptive fusion of multi-scale YOLO for pedestrian detection." IEEE Access 9 (2021): 110063-110073.Google ScholarCross Ref
- Pang, Yanwei, "Mask-guided attention network for occluded pedestrian detection." Proceedings of the IEEE/CVF international conference on computer vision. 2019.Google Scholar
- Liu, Wei, "Ssd: Single shot multibox detector." Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14. Springer International Publishing, 2016.Google Scholar
- Hu, Jie, Li Shen, and Gang Sun. "Squeeze-and-excitation networks." Proceedings of the IEEE conference on computer vision and pattern recognition. 2018.Google Scholar
- Woo, Sanghyun, "Cbam: Convolutional block attention module." Proceedings of the European conference on computer vision (ECCV). 2018.Google Scholar
- Zhang S, Benenson R, Schiele B.: Citypersons: A diverse dataset for pedestrian detection. In: the IEEE Conference on Computer Vision and Pattern Recognition. pp. 3213-3221. (2017).Google ScholarCross Ref
- Dollar, Piotr, 2011. Pedestrian detection: An evaluation of the state of the art. In Proceedings of IEEE transactions on pattern analysis and machine intelligence. pp. 743-761. https://doi.org/10.1109/TPAMI.2011.155Google ScholarDigital Library
- Cai, Zhaowei, "A unified multi-scale deep convolutional neural network for fast object detection." Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part IV 14. Springer International Publishing, 2016.Google Scholar
- Wang S, Cheng J, Liu H, PCN: Part and context information for pedestrian detection with CNNs[J]. arXiv preprint arXiv:1804.04483, 2018.Google Scholar
- Du X, El-Khamy M, Lee J, Fused DNN: A deep neural network fusion approach to fast and robust pedestrian detection[C]//2017 IEEE winter conference on applications of computer vision (WACV). IEEE, 2017: 953-961.Google Scholar
- Lin C, Lu J, Wang G, Graininess-aware deep feature learning for pedestrian detection[C]//Proceedings of the European conference on computer vision (ECCV). 2018: 732-747.Google Scholar
- Viola P, Jones M J. Robust real-time face detection[J]. International journal of computer vision, 2004, 57: 137-154.Google ScholarDigital Library
- Dalal N, Triggs B. Histograms of oriented gradients for human detection[C]//2005 IEEE computer society conference on computer vision and pattern recognition (CVPR'05). Ieee, 2005, 1: 886-893.Google ScholarDigital Library
- Zhang, S., Wen, L., Bian, X., Lei, Z., & Li, S. Z., “Occlusion-aware R-CNN: detecting pedestrians in a crowd,” In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 637-653, (2018).Google ScholarDigital Library
- Wang, X., Xiao, T., Jiang, Y., Shao, S., Sun, J., & Shen, C., “Repulsion loss: Detecting pedestrians in a crowd,” In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7774-7783, (2018).Google ScholarCross Ref
- Song, T., Sun, L., Xie, D., Sun, H., & Pu, S., “Small-scale pedestrian detection based on topological line localization and temporal feature aggregation,” In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 536-551, (2018).Google ScholarDigital Library
- Liu, W., Liao, S., Hu, W., Liang, X., & Chen, X., “Learning efficient single-stage pedestrian detectors by asymptotic localization fitting,” In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 618-634, (2018).Google ScholarDigital Library
Recommendations
Semantically Enhanced Multi-scale Feature Pyramid Fusion for Pedestrian Detection
ICMLC '21: Proceedings of the 2021 13th International Conference on Machine Learning and ComputingDetecting multi-scale pedestrians (especially small scale ones) is one of the most challenging problems in computer vision community. At present, most existing pedestrian detectors only adopt single-scale feature map in their backbone network for ...
Pedestrian detection based on channel feature fusion and enhanced semantic segmentation
AbstractAt present, pedestrian detection is widely applied to autonomous driving and intelligent transportation and robots, etc. But the balance between accuracy and speed is still not reached. In complex background with high pedestrian density and ...
An Anomaly Detection and Localization Method Based on Feature Fusion and Attention
Artificial Intelligence Security and PrivacyAbstractIn the context of anomaly detection and localization, the small proportion of anomaly data and its unknown nature increase the difficulty of the model in learning the anomaly information. At the same time, the current mainstream detection methods ...
Comments