吉林大学学报(信息科学版) ›› 2025, Vol. 43 ›› Issue (5): 1078-1084.

• • 上一篇    下一篇

复杂背景下无线传感器网络图像显著性目标辨识算法

薛晶晶a,b, 徐摇翔c   

  1. 延安大学a. 物理与电子信息学院;b. 陕西省能源大数据智能处理省市共建实验室;c. 宣传部,陕西延安716000
  • 收稿日期:2023-12-08 出版日期:2025-09-28 发布日期:2025-11-20
  • 作者简介:薛晶晶(1990— ), 女, 陕西延安人, 延安大学讲师, 主要从事无线传感器网络研究, (Tel)86-15991562616(E-mail) x15991562616@163. com。
  • 基金资助:
    陕西省能源大数据智能处理省市共建重点实验室开放基金资助项目(IPBED1; IPBED11); 陕西省教育厅科研项目自然 科学专项基金资助项目(23JK0727) 

Recognition Algorithm of Image Saliency Target for Wireless Sensor Networks in Complex Backgrounds 

XUE Jingjinga,b, XU Xiang   

  1. a. School of Physics and Electronic Information; b. Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data; c. Publicity Department, Yan’an University, Yanan 716000, China
  • Received:2023-12-08 Online:2025-09-28 Published:2025-11-20

摘要: 针对复杂背景下的图像可能包含大量干扰信息,难以精准提取图像特征矢量的问题,提出了复杂背景下无线传感器网络图像显著性目标辨识算法。 利用均值漂移算法聚类目标后实现图像分割,获得若干块分割图像特征矢量。 通过融合规则处理图像金字塔各层塔形,结合图像金字塔序列实现图像重构。 根据图像重构结果与直方图统计确定像素点的图像显著性,通过像素次序扩展与排序实现图像显著性目标辨识。 实验结果表明, 所提算法能准确辨识复杂背景下无线传感器网络图像显著性目标, 且画面纹理细节清晰, 实际应用效果好。

关键词: 无线传感器网络, 复杂背景图像, 显著性目标辨识, 图像分割, 低通滤波

Abstract: Images in complex backgrounds may contain a large amount of interference information, making it difficult to accurately extract image feature vectors. Therefore, a salient target recognition algorithm for wireless sensor network images in complex backgrounds is proposed. Mean shift algorithm is used to cluster targets and achieve image segmentation, obtaining several segmented image feature vectors. By fusing rules, the pyramid shapes of each layer in the image pyramid are prosessed, and the image pyramid sequence is combined to achieve image reconstruction. The image saliency of pixels is determined based on the results of image reconstruction and histogram statistics, and image saliency target recognition is achieved through pixel order expansion and sorting. The experimental results show that the proposed algorithm can accurately identify salient targets in wireless sensor network images under complex backgrounds, and the texture details of the image are clear, with good practical application effects. 

Key words: wireless sensor network, complex background images, significance target identification, image segmentation, low pass filtering

中图分类号: 

  • TP37