To meet the needs of transportation systems for smart scenic security services,real-time detection and identification of traffic anomalies with high accuracy is essential.Based on the multi-objective sparse optical fl...To meet the needs of transportation systems for smart scenic security services,real-time detection and identification of traffic anomalies with high accuracy is essential.Based on the multi-objective sparse optical flow estimation method based on KLT algorithm,an improved algorithm for robust sparse optical flow is designed.The Forward-Backward error calculation method was used to eliminate the error optical flow generated by the KLT algorithm and the robustness of optical flow was improved.The proposed algorithm was verified by the actual traffic scene monitoring example,and the anomaly detection accuracy is above 80%.Furthermore,it has good detection effect on the benchmark dataset.展开更多
针对在特定电力系统监控场景下的目标跟踪问题,提出了一种基于光流特征点的目标跟踪算法。首先,对Kanade-Lucas-Tomasi(KLT)跟踪算法提取到的特征点进行背景特征点滤除,分离出关键特征点;其次,利用Density Based Spatial Clustering of ...针对在特定电力系统监控场景下的目标跟踪问题,提出了一种基于光流特征点的目标跟踪算法。首先,对Kanade-Lucas-Tomasi(KLT)跟踪算法提取到的特征点进行背景特征点滤除,分离出关键特征点;其次,利用Density Based Spatial Clustering of Applications with Noise(DBSCAN)聚类方法对关键光流特征点进行聚类处理,区分出不同运动目标;最后,在KLT跟踪算法中引入Kalman滤波器对因遮挡导致的跟踪目标识别不全甚至目标丢失进行了优化。仿真实验结果表明:提出的算法能够在电力系统监控视频中实现对多目标的有效跟踪,并对跟踪目标遮挡情况有较高的鲁棒性。展开更多
基金Xaar Network Next Generation Internet Technology Innovation Project(No.NGII20180901)the Major special project of science and technology of Guangxi(No.AA18118047-7).
摘要To meet the needs of transportation systems for smart scenic security services,real-time detection and identification of traffic anomalies with high accuracy is essential.Based on the multi-objective sparse optical flow estimation method based on KLT algorithm,an improved algorithm for robust sparse optical flow is designed.The Forward-Backward error calculation method was used to eliminate the error optical flow generated by the KLT algorithm and the robustness of optical flow was improved.The proposed algorithm was verified by the actual traffic scene monitoring example,and the anomaly detection accuracy is above 80%.Furthermore,it has good detection effect on the benchmark dataset.
摘要针对在特定电力系统监控场景下的目标跟踪问题,提出了一种基于光流特征点的目标跟踪算法。首先,对Kanade-Lucas-Tomasi(KLT)跟踪算法提取到的特征点进行背景特征点滤除,分离出关键特征点;其次,利用Density Based Spatial Clustering of Applications with Noise(DBSCAN)聚类方法对关键光流特征点进行聚类处理,区分出不同运动目标;最后,在KLT跟踪算法中引入Kalman滤波器对因遮挡导致的跟踪目标识别不全甚至目标丢失进行了优化。仿真实验结果表明:提出的算法能够在电力系统监控视频中实现对多目标的有效跟踪,并对跟踪目标遮挡情况有较高的鲁棒性。