Computer Engineering and Applications ›› 2019, Vol. 55 ›› Issue (1): 180-185.DOI: 10.3778/j.issn.1002-8331.1709-0418

Previous Articles     Next Articles

Objects Detection in Different Source Images Based on Evaluation Vector

XI Runping1,2, JIA Gaoyun1,2, ZHANG Yanning1,2, ZHANG Fujun1,2   

  1. 1.School of Computer Science, Northwestern Polytechnical University, Xi’an 710129, China
    2.Shaanxi Provincial Key Laboratory of Speech & Image Information Processing, Xi’an 710129, China
  • Online:2019-01-01 Published:2019-01-07

基于评价向量的异源图像目标检测

郗润平1,2,贾高云1,2,张艳宁1,2,张福俊1,2   

  1. 1.西北工业大学 计算机学院,西安 710129
    2.陕西省语音与图像信息处理重点实验室,西安 710129

Abstract: How to evaluate the reliabilities of different image sensors and their processing result is an important issue in the field of multi-modal objects detection. As single-source sensor in object detection has the disadvantages of high miss rate and mistake rate, this paper proposes a new approach, which can evaluate the reliabilities of the detection results in different source images. Firstly, three evaluation factors of inertia, target number of inertia and target independent integrity are introduced to construct an evaluation vector to assess the quality of motion detection. Secondly, k-means clustering are used to generate the target center vector. Then the cooperative and competitive mechanism are applied to feedback the clustering similarity. Finally, the objects detection in different source images is realized. Simulations on lots of images verify that the new proposed approach is more robust for lower detection error rate and false-negative rate.

Key words: different source images, objects detection, evaluation vector, k-means clustering

摘要: 在异源图像运动目标检测中,对不同源信息处理的可信度量是影响异源协同检测的关键。针对传统单源目标检测中漏检率、误检率高等问题,提出了基于评价向量的异源图像目标检测方法。通过引入目标面积检测惯性、目标数量检测惯性和目标独立完整性三个评价因子,构造出用来评价不同信息源运动检测结果好坏的评价向量,并运用改进的k-means聚类算法产生目标中心向量,最后利用协作与竞争机制对聚类相似度进行反馈,实现了多源图像的协同检测。实验结果表明,相比于传统的单源检测算法和融合检测算法,该算法具有较高的检测精度和较低的漏检率、误检率。

关键词: 异源图像, 目标检测, 评价向量, k-means聚类