计算机科学 ›› 2020, Vol. 47 ›› Issue (8): 208-212.doi: 10.11896/jsjkx.191000165
姚兰1, 赵永恒1, 施雨晴1, 于明鹤2
YAO Lan1, ZHAO Yong-heng1, SHI Yu-qing1, YU Ming-he2
摘要： 交通领域的异常事件检测对于预防和及时处理交通事故有着重要作用。当前大多数交通异常事件检测都是通过人工完成的, 耗费了大量的人力, 同时实时性也较差。文中针对高速公路的交通场景特点, 利用深度学习中的目标检测算法, 对视频中的车辆目标进行提取, 提出了结合运动特征和表观特征的多目标追踪算法;在此基础上, 又提出了一种基于车辆轨迹特征的异常事件检测方法, 其中的追踪算法减少了轨迹提取过程对背景环境变化的依赖。在异常事件检测算法中充分结合高速公路实际场景, 加入滑动窗口机制, 提升了对远距离和复杂场景下异常事件的检测能力。利用面向真实交通视频的数据, 与现有的事件检测算法进行对比, 实验结果证明, 所提方法在事件检测的准确率、召回率和F值指标方面都有良好的性能表现, 能够有效地完成高速场景下的交通异常事件检测。
中图分类号:
| [1] REDMON J, FARHADI A.YOLOv3:An incremental improvement [J].arXiv:1804.02767, 2018. [2] SIMON J J, JEFFREY K U.New extension of the Kalman filter to nonlinear systems [C]∥International Society for Optics and Photonics (SPIE), 1997. [3] LUO W H, JUN L X, XIAO Q Z, et al.Multiple object tracking:a review [J].arXiv:1409.7618, 2014. [4] CHANHO K, FUXIN L, ARRIDHANA C, et al.Multiple hy-pothesis tracking revisited [C]∥IEEE International Conference on Computer Vision (ICCV).2015:4696-4704. [5] XIANG Y, ALAHI A, SAVARESE S.Learning to track:online multi-object tracking by decision making [C]∥2015 IEEE International Conference on Computer Vision (ICCV).2015:4705-4713. [6] LEAL T L, FERRER C C, SCHINDLER K.Learning by trac-king:siamesecnn for robust target association [J].CV-PR Workshops, 2016:418-425. [7] SI Y T, BJOERN A, MYKHAYLO A, et al.Multi-person trackingby multicut and deep matching [M].Computer Vision－ECCV 2016 Workshops, 2016:100-111. [8] AMIR S, ALEXANDRE A, SILVIO S.Tracking the untrac-kable:learning to track multiple cues with long-term dependencies [J].ICCV, 2017:300-311. [9] WEIMING H, TIENIU T, LIANG W, et al.A survey on visual surveillance of object motion and behaviors [J].IEEE Trans.Systems, Man, and Cybernetics, 2004, 34(3):334-352. [10]ROLLER D, DANILDIS K, NAGEL H H.Model-based objecttracking in monocular image sequences of road traffic scenes:[J].International Journal of Computer Vision, 1993, 10(3):257-281. [11]MARGRIT B, ESIN H, LARRY S D.Real-time multiple vehicledetection and tracking from a moving vehicle [J].Machine Vision and Applications, 2000, 12(2):69-83. [12] MAKSAI A, PASCAL F.Eliminating exposure bias and metricmismatch in multiple object tracking[C]∥IEEE Conference on Computer Vision and Pattern Recognition (CVPR).2019:4639-4648. [13]REN W, DANIEL B W.Interactive multiple model ensembleKalman filter for traffic estimation and incident detection [C]∥International IEEE Conference on Intelligent Transportation Systems (ITSC).2014:804-809. [14]ZHAO M, ZHANG B, TANG Y, et al.Video detection algorithm for expressway violation parking in open air scene[J].Computer Measurement & Control, 2014, 22(2):489-492. [15]QIU L Y, HAN J, GU M.A method for detecting abnormal be-havior of highway vehicles based on lane model [J].Journal of Computer Applications, 2014, 34(5):1378-1382. [16]ZHAO Y T, LI X Y, LUO D H.Research on automatic detectionmethod of traffic events based on video vehicle trajectory model [J].Journal of Sun Yatsen University(Natural Science), 2011, 50(4):56-60. [17]YUAN Y Q, XIE C L.Research on traffic detecting method based on machine vision [J].Computer Simulation, 2013, 30(10):189-193. [18]SUI L, DANG J W.Research on detection algorithm of highway abnormal events based on moving target trajectory [J].Compu-ter Applications and Software, 2018, 35(1):246-252. [19]GRIGORIOS T, IOANNIS K, IOANNIS V.Mining multi-label data[M]∥Data Mining and Knowledge Discovery Handbook.Boston:Springer, 22009:667-686. |
| [1] | 刘冬梅, 徐洋, 吴泽彬, 刘倩, 宋斌, 韦志辉. 基于边框距离度量的增量目标检测方法 Incremental Object Detection Method Based on Border Distance Measurement 计算机科学, 2022, 49(8): 136-142. https://doi.org/10.11896/jsjkx.220100132 |
| [2] | 王灿, 刘永坚, 解庆, 马艳春. 基于软标签和样本权重优化的Anchor Free目标检测算法 Anchor Free Object Detection Algorithm Based on Soft Label and Sample Weight Optimization 计算机科学, 2022, 49(8): 157-164. https://doi.org/10.11896/jsjkx.210600240 |
| [3] | 孙奇, 吉根林, 张杰. 基于非局部注意力生成对抗网络的视频异常事件检测方法 Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection 计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061 |
| [4] | 祝文韬, 兰先超, 罗唤霖, 岳彬, 汪洋. 改进Faster R-CNN的光学遥感飞机目标检测 Remote Sensing Aircraft Target Detection Based on Improved Faster R-CNN 计算机科学, 2022, 49(6A): 378-383. https://doi.org/10.11896/jsjkx.210300121 |
| [5] | 马宾, 付永康, 王春鹏, 李健, 王玉立. 基于GDIoU损失函数的YOLOv4绝缘子高效定位算法 High Performance Insulators Location Scheme Based on YOLOv4 with GDIoU Loss Function 计算机科学, 2022, 49(6A): 412-417. https://doi.org/10.11896/jsjkx.210600089 |
| [6] | 陈永平, 朱建清, 谢懿, 吴含笑, 曾焕强. 基于外接圆半径差损失的实时安全帽检测算法 Real-time Helmet Detection Algorithm Based on Circumcircle Radius Difference Loss 计算机科学, 2022, 49(6A): 424-428. https://doi.org/10.11896/jsjkx.220100252 |
| [7] | 陈佳舟, 赵熠波, 徐阳辉, 马骥, 金灵枫, 秦绪佳. 三维城市场景中的小物体检测 Small Object Detection in 3D Urban Scenes 计算机科学, 2022, 49(6): 238-244. https://doi.org/10.11896/jsjkx.210400174 |
| [8] | 胡伏原, 万新军, 沈鸣飞, 徐江浪, 姚睿, 陶重犇. 深度卷积神经网络图像实例分割方法研究进展 Survey Progress on Image Instance Segmentation Methods of Deep Convolutional Neural Network 计算机科学, 2022, 49(5): 10-24. https://doi.org/10.11896/jsjkx.210200038 |
| [9] | 徐涛, 陈奕仁, 吕宗磊. 基于改进YOLOv3的机坪工作人员反光背心检测研究 Study on Reflective Vest Detection for Apron Workers Based on Improved YOLOv3 Algorithm 计算机科学, 2022, 49(4): 239-246. https://doi.org/10.11896/jsjkx.210200119 |
| [10] | 张侣, 周博文, 吴亮红. 基于改进卷积注意力模块与残差结构的SSD网络 SSD Network Based on Improved Convolutional Attention Module and Residual Structure 计算机科学, 2022, 49(3): 211-217. https://doi.org/10.11896/jsjkx.201200019 |
| [11] | 赫晓慧, 邱芳冰, 程淅杰, 田智慧, 周广胜. 基于边缘特征融合的高分影像建筑物目标检测 High-resolution Image Building Target Detection Based on Edge Feature Fusion 计算机科学, 2021, 48(9): 140-145. https://doi.org/10.11896/jsjkx.200800002 |
| [12] | 袁磊, 刘紫燕, 朱明成, 马珊珊, 陈霖周廷. 融合改进密集连接和分布排序损失的遥感图像检测 Improved YOLOv3 Remote Sensing Target Detection Based on Improved Dense Connection and Distributional Ranking Loss 计算机科学, 2021, 48(9): 168-173. https://doi.org/10.11896/jsjkx.200800001 |
| [13] | 夏中, 向敏, 黄春梅. 基于CHBL的P2P视频监控网络分层管理机制 Hierarchical Management Mechanism of P2P Video Surveillance Network Based on CHBL 计算机科学, 2021, 48(9): 278-285. https://doi.org/10.11896/jsjkx.201200056 |
| [14] | 龚浩田, 张萌. 基于关键点检测的无锚框轻量级目标检测算法 Lightweight Anchor-free Object Detection Algorithm Based on Keypoint Detection 计算机科学, 2021, 48(8): 106-110. https://doi.org/10.11896/jsjkx.200700161 |
| [15] | 屈立成, 吕娇, 屈艺华, 王海飞. 基于模糊神经网络的运动目标智能分配定位算法 Intelligent Assignment and Positioning Algorithm of Moving Target Based on Fuzzy Neural Network 计算机科学, 2021, 48(8): 246-252. https://doi.org/10.11896/jsjkx.200600050 |
|
||
首页