Convolution network arithmetic unit, reconfigurable convolution neural network processor and image de-noising method of reconfigurable convolution neural network processor

Abstract

The invention discloses a convolution network arithmetic unit, a reconfigurable convolution neural network processor and an image de-noising method of the reconfigurable convolution neural network processor. The reconfigurable convolution neural network processor comprises a bus interface, a preprocessing unit, a reconfigurable hardware controller, an SRAM, an SRAM control module, an input caching module, an output caching module, a memory, a data memory controller and the convolution network arithmetic unit. The processor is featured by few resources and rapid speed and can be applicable to common convolution neural network architecture. According to the unit, the processor and the method provided by the invention, convolution neural networks can be realized; the processing speed is rapid; transplanting is liable to be carried out; the resource consumption is little; an image or a video polluted by raindrops and dusts can be recovered; and raindrop and dust removing operations can be taken as preprocessing operations for providing help in follow-up image identification or classification.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a convolutional network operation unit, a reconfigurable convolutional neural network processor and a method for realizing image denoising processing. Background technique [0002] Image raindrop and dust removal is of great significance for image processing applications, especially video surveillance and navigation systems. It can be used to restore images or videos polluted by raindrops and dust, and can also be used as a pre-processing operation to help subsequent image recognition or classification. [0003] Most of the current image noise removal methods are completed by Gaussian filtering, median filtering, and bilateral filtering. These methods have poor processing effects and often cannot meet the needs of specific image processing applications. Therefore, a better method is needed to remove image noise, and the method of convolutional neural network becomes a good choice...

AI Technical Summary

Problems solved by technology

[0004] Most of the current deep learning networks run on GPUs, but GPUs are expensive and consume high power, which is not suitable for large-scale and wide-ranging applications.

However, the running speed on the CPU is slow, and the efficiency of running a large-scale deep learning network is low, which cannot meet the performance requirements.

[0005] It can be seen that the current technology for the application of convolutional neural networks, the main problems are: large processor area, high cost, high power consumption, poor performance and other issues

Images