Bad weather such as rainy days will seriously affect the image quality and the accuracy of visual processing algorithm. In order to improve the image deraining quality, a multi-scale fusion self attention generation adversarial network (MSFSA-GAN) is proposed. This network uses different scales to extract input characteristics of rain lines. First, Gaussian pyramid rain maps with different scales are generated by Gaussian algorithm. Then, in order to extract the features of rain lines with different scales, the coarse fusion module and fine fusion module are designed respectively. Next, the extracted features are fused at different scales. In this process, the self attention mechanism is introduced to make the network focus on the extracted features of different scales. And before the fusion, the rain pattern reconstruction operation is also carried out, so that the network can reproduce the input image more perfectly. Finally, it is input into the discriminator network with dense blocks to obtain the image that removes the rain lines. We used R100H and R100L datasets to train and test our network. The results show that our method as high as 27.79 in PSNR and UQI is 0.94, which is superior to the existing methods in performance. Meanwhile, we also compared the cost of time, the result of our network is only 0.02s.INDEX TERMS Rain removal, MSFSA-GAN, self attention, dense block.

No abstract

No abstract

In order to detect the fault signal of rolling bearing, the fault diagnosis of rolling bearings is carried out by using discrete wavelet transform. The practical vibration speed signals measured from rolling bearings are decomposed and reconstructed by Mallat algorithm. Then an envelope analysis is made to the signal. The fault of rolling bearing component is diagnosed by extracting fault feature from envelop frequency spectrum figure. The experiments results showed that mutation signal can be easily found from detail signals after Ndecomposition of the vibration signal of rolling bearing. The existence of fault points can be judged accurately by detecting the characteristic frequency of fault signals from the power spectrum after Hilbert envelop.

No abstract