首页 | 本学科首页   官方微博 | 高级检索  
     

空间划分的目标图像识别与跟踪技术
引用本文:张学英1,韩广良2. 空间划分的目标图像识别与跟踪技术[J]. 华侨大学学报(自然科学版), 2017, 0(2): 257-261. DOI: 10.11830/ISSN.1000-5013.201702023
作者姓名:张学英1  韩广良2
作者单位:1. 河北科技师范学院 职教研究院, 河北 秦皇岛 066004;2. 中国科学院 长春光学精密机械与物理研究所, 吉林 长春 130000
摘    要:
针对多目标识别跟踪算法中存在的低效率、高能耗,易产生误检、漏检等问题,以跟踪精确率、能量损耗为评价指标展开研究.对目前定位与跟踪的相关算法进行分析,提出一种基于空间划分的目标图像识别与跟踪算法.利用空间分簇机制,实时收集目标的位置信息,同时,建立目标丢失与恢复机制,显著提高了目标的识别与跟踪精度,减少能量损耗.结果表明:与常规算法相比,所提算法跟踪成功率提高了10%左右,并能有效减少能量消耗,具有一定的实用价值.

关 键 词:空间划分  图像识别  图像定位  跟踪算法  分簇机制

Target Image Recognition and Tracking Technology Based on Space Partition
ZHANG Xueying1,HAN Guangliang2. Target Image Recognition and Tracking Technology Based on Space Partition[J]. Journal of Huaqiao University(Natural Science), 2017, 0(2): 257-261. DOI: 10.11830/ISSN.1000-5013.201702023
Authors:ZHANG Xueying1  HAN Guangliang2
Affiliation:1. Institute of Vocational Education, Hebei Normal University of Science and Technology, Qinhuangdao 066004, China; 2. Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130000, China
Abstract:
Considering multi-object tracking algorithm exists some problem such as low efficiency, high energy loss, easy error-detection and loss dectection, we take the tracking accuracy and energy loss as the evaluation index to develop research. Based on the analysis of the current localization and tracking algorithms, a new method of object localization and tracking algorithm based on space partition is proposed, which uses the spatial clustering mechanism to collect the target location information in real time. At the same time, the object loss and restoration mechanism is established. It can improve the tracking accuracy and reduce the energy loss significantly. The simulation results show that compared with the common algorithm, the tracking success rate in our is increased by 10%, and the energy consumption is decreased effectively in this algorithm effective, and it has application value.
Keywords:space partition  image recognition  image location  tracking algorithm  clustering mechanism
本文献已被 CNKI 等数据库收录!
点击此处可从《华侨大学学报(自然科学版)》浏览原始摘要信息
点击此处可从《华侨大学学报(自然科学版)》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号