Vehicle Detection with Occlusion Handling, Tracking, and OC-SVM Classification: A High Performance Vision-Based System.
Vehicle Detection with Occlusion Handling, Tracking, and OC-SVM Classification: A High Performance Vision-Based System.
复制标题
DOI：
10.3390/s18020374
复制
发表时间：
2018-01-27
期刊：
影响因子：
--
通讯作者：
Romero-Delgado M
中科院分区：
文献类型：
--
作者：
Velazquez-Pupo R;Sierra-Romero A;Torres-Roman D;Shkvarko YV;Santiago-Paz J;Gómez-Gutiérrez D;Robles-Valdez D;Hermosillo-Reynoso F;Romero-Delgado M
提出了一种基于单静态摄像机的高性能视觉交通监控系统，实现了基于遮挡处理、跟踪、计数和单类支持向量机分类的运动车辆检测。在该方法中，首先使用自适应高斯混合模型(GMM)将运动目标从背景中分割出来。然后提取车辆面积、高度、宽度、质心、包围盒等几何特征。由于遮挡的存在，实现了一种减少遮挡的算法。跟踪采用自适应卡尔曼滤波。最后，不同的分类器使用选定的几何特征：估计面积、高度和宽度，以便将车辆分为三类：小型、中型和大型。在8个真实交通视频上的大量实验结果表明，改进后的系统可以在遮挡指数为0.312的情况下实时运行，对车辆的全局检测率或召回率、准确率和F度量高达98.190%，对中型车辆的F度量高达99.051%。
This paper presents a high performance vision-based system with a single static camera for traffic surveillance, for moving vehicle detection with occlusion handling, tracking, counting, and One Class Support Vector Machine (OC-SVM) classification. In this approach, moving objects are first segmented from the background using the adaptive Gaussian Mixture Model (GMM). After that, several geometric features are extracted, such as vehicle area, height, width, centroid, and bounding box. As occlusion is present, an algorithm was implemented to reduce it. The tracking is performed with adaptive Kalman filter. Finally, the selected geometric features: estimated area, height, and width are used by different classifiers in order to sort vehicles into three classes: small, midsize, and large. Extensive experimental results in eight real traffic videos with more than 4000 ground truth vehicles have shown that the improved system can run in real time under an occlusion index of 0.312 and classify vehicles with a global detection rate or recall, precision, and F-measure of up to 98.190%, and an F-measure of up to 99.051% for midsize vehicles.
登录
查看更多内容
影响因子：
--
作者：
Cherkassky, V
通讯作者：
Cherkassky, V
DOI：
10.1109/6979.994794
发表时间：
2002-03-01
影响因子：
8.5
作者：
Gupte, S;Masoud, O;Papanikolopoulos, NP
通讯作者：
Papanikolopoulos, NP
影响因子：
2.7
作者：
Kamkar, Shiva;Safabakhsh, Reza
通讯作者：
Safabakhsh, Reza
DOI：
10.3390/s151027201
发表时间：
2015-10-26
期刊：
Sensors (Basel, Switzerland)
影响因子：
--
作者：
Lamas-Seco JJ;Castro PM;Dapena A;Vazquez-Araujo FJ
通讯作者：
Vazquez-Araujo FJ
DOI：
10.1109/tcsvt.2010.2087812
发表时间：
2011-01-01
影响因子：
8.4
作者：
Huang, Shih-Chia
通讯作者：
Huang, Shih-Chia