Please wait a minute...
FITEE
Front. Inform. Technol. Electron. Eng.  2015, Vol. 16 Issue (5): 346-357    DOI: 10.1631/FITEE.1500026
    
基于高清监控图像的工程车辆检测算法
Xun Liu, Yin Zhang, San-yuan Zhang, Ying Wang, Zhong-yan Liang, Xiu-zi Ye
College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China; College of Mathematics and Information Science, Wenzhou University, Wenzhou 325035, China
Detection of engineering vehicles in high-resolution monitoring images
Xun Liu, Yin Zhang, San-yuan Zhang, Ying Wang, Zhong-yan Liang, Xiu-zi Ye
College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China; College of Mathematics and Information Science, Wenzhou University, Wenzhou 325035, China
 全文: PDF 
摘要： 目的：基于监控图像，设计一种工程车辆检测算法，使其能快速高效地对工程车辆等组件可变铰链式刚体进行识别与检测。
创新点：模拟人类视觉检测过程，把检测算法分为粗提取与精确分类两个阶段。第一阶段提出“颜色频率”特征并用其优化HOG描述子。第二阶段改进一种显著性提取算法并用改进的算法来改善dense SIFT算子。两阶段结合，得到整体高效的检测算法。
方法：监控图像的特点是高空广角监控，工程车辆像素面积小，模拟人类视觉从复杂多样的物体中检测目标物体的过程，把检测过程分为粗提取阶段与精确分类阶段。人类在寻找目标物体时，一般会快速浏览这些复杂多样的物体群，遇到拟似目标物体，会多停留几秒来确认是否为真正的目标物体。粗提取阶段，加入“颜色频率”的HOG描述子(图3)和线性SVM分类器，快速扫描整张监控图像，从中提取出拟似工程车辆区域。这一阶段的目的是低漏检率快速提取拟似目标区域。精确分类阶段是采用显著性蒙版化的dense SIFT算子(图8)，去除第一阶段提取出的非工程车辆区域，得到最终的低漏检率低错检率的快速检测算法(图1)。
结论：针对监控图像的工程车辆等组件可变的铰链式刚体，提出一种先大范围粗提取后小范围精确分类的检测算法。算法不仅高效快速，且具有一定泛化性能。
关键词： 目标检测;  梯度直方图;  稠密度SIFT;  显著性检测;  组件模型;  工程车辆    
Abstract: This paper presents a novel formulation for detecting objects with articulated rigid bodies from high-resolution monitoring images, particularly engineering vehicles. There are many pixels in high-resolution monitoring images, and most of them represent the background. Our method first detects object patches from monitoring images using a coarse detection process. In this phase, we build a descriptor based on histograms of oriented gradient, which contain color frequency information. Then we use a linear support vector machine to rapidly detect many image patches that may contain object parts, with a low false negative rate and a high false positive rate. In the second phase, we apply a refinement classification to determine the patches that actually contain objects. In this stage, we increase the size of the image patches so that they include the complete object using models of the object parts. Then an accelerated and improved salient mask is used to improve the performance of the dense scale-invariant feature transform descriptor. The detection process returns the absolute position of positive objects in the original images. We have applied our methods to three datasets to demonstrate their effectiveness.
Key words: Object detection    Histogram of oriented gradient (HOG)    Dense scale-invariant feature transform (dense SIFT)    Saliency    Part models    Engineering vehicles
收稿日期: 2015-01-20 出版日期: 2015-05-05
CLC:  TP391.41  
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　
Xun Liu
Yin Zhang
San-yuan Zhang
Ying Wang
Zhong-yan Liang
Xiu-zi Ye

引用本文:

Xun Liu, Yin Zhang, San-yuan Zhang, Ying Wang, Zhong-yan Liang, Xiu-zi Ye. Detection of engineering vehicles in high-resolution monitoring images. Front. Inform. Technol. Electron. Eng., 2015, 16(5): 346-357.

链接本文:

http://www.zjujournals.com/xueshu/fitee/CN/10.1631/FITEE.1500026    或    http://www.zjujournals.com/xueshu/fitee/CN/Y2015/V16/I5/346

[1] Jing-li Gao, Cheng-lin Wen, Zhe-jing Bao, Mei-qin Liu. 基于时域滤波和关联策略的红外慢速目标检测[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(11): 1176-1185.
[2] Ji-chuan Li, Xiao-de Lu, Hui Zhang, Peng-cheng Yang, Yu Liu, Mao-sheng Xiang. 无源雷达倒谱动目标检测方法[J]. Front. Inform. Technol. Electron. Eng., 2015, 16(9): 785-795.
[3] Xiao Lin, Ying-lan Ma, Li-zhuang Ma, Rui-ling Zhang. 图像缩放方法综述[J]. Front. Inform. Technol. Electron. Eng., 2014, 15(9): 697-716.