1.Research Center of Internet of Things (Perception Mine), China University of Mining and Technology, Xuzhou , China;2.School of Information and Control Engineering, China University of Mining and Technology, Xuzhou , China;3.Xuhai College, China University of Mining and Technology, Xuzhou , China

According to a quick energy consumption of the sensor nodes caused by the high information transmission, the reduced equipment service life and other problems of the wireless sensor network in the underground coal mine, based on the analysis on image features and wavelet transform coefficient layer features of the underground coal mine, a processing algorithm of the compressed perception and sparse images was provided based on the wavelet transform that was blocking sparse algorithm. A bior4.4 wavelet transform was applied to the blocking sparse transform on the images and signals in the underground coal mine. The measurement matrix was applied to the measurement of the spares image data, the measured data were obtained and then the ROMP algorithm was applied to the restructure of the spares transform images. The simulation experiment results showed that in comparison with the traditional compressed perception algorithm, the processing algorithm could not only obtain the high quality restructured image effect with a lower sampling rate, but could compress the image size and could rapidly restore the images.