基于BING和HOG-LSS特征的行人检测算法研究
Research on Pedestrian Detection Algorithm Based on BING and HOG-LSS Feature
DOI: 10.12677/JISP.2017.61005, PDF, HTML, XML, 下载: 1,663  浏览: 5,541 
作者: 赵朝华*：四川大学计算机学院，四川 成都；视觉合成图形图像技术国家重点学科实验室，四川 成都
关键词: 行人检测；BING特征；HOG-LSS特征；数据轨迹融合；Pedestrian Detection； BING Feature； HOG-LSS Feature； Data Association
摘要: 近年来，基于计算机视觉技术的行人检测方法一直是智能交通领域研究的热点问题之一。基于HOG和局部自相似(LSS)特征融合的行人检测算法在检测效果上优于传统HOG特征的行人检测算法，但是同时也存在如下挑战：1) 算法检测的速度不够快；2) 在遮挡面积过大的情况下，无法有效地进行处理。针对这些挑战问题，本文提出了一种使用BING特征、HOG-LSS特征和数据轨迹融合的行人检测优化框架，并通过对实验结果进行验证可知，检测效果优于HOG-LSS特征的行人检测方法。
Abstract: In recent years, pedestrian detection, based on computer vision, has been one of the hottest topics in the field of intelligent transportation. The pedestrian detection algorithm, based on HOG and local self-similarity (LSS) feature fusion, is better than the traditional HOG detection algorithm, and also it has the following challenges: 1) low efficiency; 2) failing to effectively handle the occlusion problem. Aiming at these challenges, this paper proposes a pedestrian detection optimization framework based on BING feature, HOG-LSS feature and data trajectory fusion. It is proved that the detection result is superior to the HOG-LSS pedestrian detection method.
文章引用：赵朝华. 基于BING和HOG-LSS特征的行人检测算法研究[J]. 图像与信号处理, 2017, 6(1): 37-43. http://dx.doi.org/10.12677/JISP.2017.61005

参考文献

[1] Dalal, N. and Triggs, B. (2005) Histograms of Oriented Gradients for Human Detection. 2005 IEEE Conference on Computer Vision and Pattern Recognition, San Diego, 886-893. https://doi.org/10.1109/CVPR.2005.177
[2] 王孝艳, 张艳珠, 董慧颖, 等. 运动目标检测的三帧差法算法研究[J]. 沈阳理工大学学报, 2011, 30(6): 82-85, 91.
[3] Yan, J.J., Zhen, L., Dong, Y. and Li, Z.S. (2012) Multi-Pedestrian Detection in Crowded Scenes: A Global View. 2012 IEEE Conference on Computer Vision and Pattern Recognition, Rhode Island, 3124-3129.
[4] Shao, H., Chen, S., et al. (2015) Face Recognition Based on Subset Selection via Metric Learning on Manifold. Frontiers of Information Technology & Electronic Engineering, 16, 1046-1058. https://doi.org/10.1631/FITEE.1500085
[5] Yao, S.H., Pan, S.M., et al. (2015) A New Pedestrian Detection Method Based on Combined HOG and LSS Features. Neurocomputing, 151, 1006-1014. https://doi.org/10.1016/j.neucom.2014.08.080
[6] Maji, S., Berg, A.C. and Malik, J. (2013) Efficient Classification for Additive Kernel SVMs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35, 66-77. https://doi.org/10.1109/TPAMI.2012.62
[7] 种衍文, 匡湖林, 李清泉. 一种基于多特征和机器学习的分级行人检测方法[J]. 自动化学报, 2012, 38(3): 375- 381.
[8] Cheng, M.M., Zhang, Z., Lin, W.Y., et al. (2014) BING: Binarized Normed Gradients for Objectness Estimation at 300 fps. 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3286-3293. https://doi.org/10.1109/CVPR.2014.414
[9] Zhang, L., Li, Y. and Nevatia, R. (2008) Global Data Association for Multi-Object Tracking Using Network Flows. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Anchorage, 24-26 June 2008, 1-8. https://doi.org/10.1109/cvpr.2008.4587584
[10] Gold, S. and Rangarajan, A. (1996) Softmax to Softassign: Neural Network Algorithms for Combinatorial Optimization. Journal of Artificial Neural Networks, 2, 381-399.