基于压缩感知的矿井图像采集方法

Mining Image Acquisition Method Based on Compressed Sensing

为了减少矿井监控在感知层终端节点的数据存储空间,降低感知层终端节点的功耗,减轻数据的传输压力,改善矿井图像的清晰度,提出了一种基于压缩感知的矿井图像采集方法。该方法突破传统数据采集模式,在井下感知层终端节点直接采集压缩后的图像数据,然后在地面图像接收端利用正交匹配追踪(OMP)算法重构图像。实验结果表明,在较大噪声干扰的情况下,图像仍可成功重构,且重构图像的峰值信噪比(PSNR)大于32 dB,重构时间不超过22 s。

In order to reduce the data storage space of mine monitoring at the perception layer terminal nodes,reduce the power consumption of the perception layer terminal nodes,alleviate the transmission pressure of data,and improve the clarity of mine images,a mine image acquisition method based on compressed sensing is proposed.This method breaks through the traditional data acquisition mode by directly collecting compressed image data at the underground perception layer terminal node,and then reconstructing the image at the ground image receiver using the orthogonal matching pursuit(OMP)algorithm.The experimental results show that the image can still be successfully reconstructed in the presence of large noise interference,and the peak signal-to-noise ratio(PSNR)of the reconstructed image is ensured to be greater than 32 dB,and the reconstruction time is less than 22 s.