视觉传感网中基于二次规划的图像压缩感知

为降低视觉传感网络中图像压缩感知算法的计算复杂度,提出一种基于二次规划的网络图像恢复算法。该算法将压缩感知重构中的欠定线性方程组求解问题,转化为有界约束二次规划问题,在此基础上结合阿米霍步长准则,设计一种压缩感知图像恢复算法,通过求解二次规划问题对网络图像数据进行恢复。理论分析和仿真结果表明,与传统图像压缩感知算法相比,该算法可减少约1/3的图像数据恢复运算时间,且图像重构质量提高3 dB~6 dB,有效提高了视觉传感器网络图像恢复算法的实时性。

Image Compressed Sensing Based on Quadratic Programming in Visual Sensor Networks

For reducing the computational complexity of Compressed Sensing（CS） in Visual Sensor Networks（VSN）, an image recovery algorithm based on quadratic programming is proposed. The under-determined linear equations in CS recovery are solved by bound-constrained quadratic programming, and an image recovery algorithm is designed based on the armijo rule. Theory analysis and experimental results show that the proposed algorithm can reduce 1/3 operation time of image recovery, and enhance the recovery quality by 3 dB-6 dB, thus significantly improve the real-time performance of image recovery in VSN.