顾及道路约束条件的动态目标检测与跟踪方法

发布时间：2018-04-14 00:27

本文选题：道路约束条件 + HSV颜色空间　；参考：《测绘通报》2017年05期

【摘要】：智能交通是智慧城市的重要组成部分,面对复杂多变的道路背景,如何能够快速检测、跟踪道路监控影像中的动态目标,是智能交通建设的关键技术难点。本文根据道路监控视频特点,提出了采用道路约束条件与颜色特征集相结合的动态目标跟踪方法,以道路约束条件确定运动目标搜索区域,利用HSV颜色特征集进行特征匹配,然后基于IIR滤波背景法对背景影像进行更新及动态目标的检测,并根据道路约束条件与颜色特征相结合跟踪方法实现对动态目标的跟踪及动作预测。试验结果表明该方法可准确对运动目标进行检测与跟踪,且对慢速运动目标也具有较好的响应能力,实现了对道路动态目标的实时检测与跟踪。
[Abstract]:Intelligent transportation is an important part of intelligent city. In the face of complex and changeable road background, how to quickly detect and track the dynamic target in road monitoring image is the key technology difficulty of intelligent transportation construction.According to the video features of road surveillance, this paper proposes a dynamic target tracking method based on road constraint and color feature set. The search region of moving object is determined by road constraint condition, and the feature matching is carried out by using HSV color feature set.Then the background image is updated and the dynamic target is detected based on the IIR filtering background method, and the tracking method based on road constraints and color features is used to track and predict the dynamic target.The experimental results show that the proposed method can detect and track moving targets accurately, and it also has a good response ability to slow moving targets. It realizes the real-time detection and tracking of dynamic targets on roads.
【作者单位】：河南理工大学矿山空间信息技术国家测绘地理信息局重点实验室;
【基金】：2016年度国家重点研发计划项目(2016YFC0803103) 河南省高校创新团队支持计划项目(14IRTSTHN026) 河南省创新型科技创新团队支持计划
【分类号】：TP391.41;U495

【相似文献】