多媒体传感器网络中基于颜色空间的图像融合方案

An Image Fusion Method Based on Color Space for Multimedia Sensor Networks

基于彩色图像的YUV颜色空间和相邻节点间的视角相关性,将同一场景的监控任务分配给3个相关度较大的传感器节点,每个节点仅需处理亮度分量或色度分量.使用深度信息模型,以及基于自适应四叉树分割和分块空间变换的方法,对解码后的亮度和色度分量进行融合,实现监控场景的彩色图像重构.仿真实验结果表明,该方法有效可行,在视频传感器节点存储量、传输量和场景监控质量之间能取得良好的折中.

The monitor task of the same scene was assigned to three highly-correlated video sensor nodes based on YUV color space and the view correlation of adjacent nodes. Each sensor node only needed to take charge of compressing and transmitting luminance or chrominance part. With the proposed depth information model, luminance and chrominance parts were fused using fusion method based on adaptive quadtree partitioning and space transform. And then the color image of the scene was reconstructed. The experimental and simulation results show that our method is effective and feasible. A well tradeoff is achieved between store,transmission cost and scene monitoring quality.