Night monitoring and identification method and system based on neural network enhancement

Abstract

The invention discloses a night monitoring and identification method based on neural network enhancement. The night monitoring and identification method includes the steps: firstly, obtaining neighborhood information of pixels in a night monitoring image; carrying out adaptive enhancement on the image based on the quadratic Taylor series; obtaining adaptive enhanced images, extracting regional features and edge features from the self-adaptive enhanced image and respectively inputting the regional features and the edge features into corresponding neural networks; and performing significance calculation on a feature recognition result output by the neural network, fusing the calculated significance region images to obtain a comprehensive significance image, finally segmenting the comprehensive significance image by using a maximum entropy method to obtain a binary image, and extracting a target image from the adaptive enhanced image based on the binary image. According to the night monitoring and identification method, the contrast of the image can be improved, and self-adaptive image enhancement is performed for the problem of uneven illumination of each part of the image, and the generated saliency map can effectively cover the boundary of the target area and well inhibit the saliency of the background area.

Description

technical field [0001] The present application relates to the technical field of video surveillance, in particular to a night surveillance recognition method and system based on neural network enhancement. Background technique [0002] Video surveillance plays an important role in people's daily life. For example, monitoring cameras will be installed at traffic road intersections and on the way to detect illegal behaviors such as speeding and not wearing seat belts, and to monitor the occurrence of traffic accidents as evidence to help determine the responsibility of the accident. For another example, surveillance cameras will also be installed on roads in office areas, in office buildings, on roads in residential areas, and in residential buildings for security monitoring, so as to prevent property theft and gang fights in a timely manner. For example, cameras are mounted on drones for aerial inspections. [0003] The current video surveillance system can realize automati...

AI Technical Summary

Problems solved by technology

[0007] Based on this, in order to improve the defects of poor brightness, contrast, and clarity of the nighttime monitoring picture, and to efficiently and accurately perform image enhancement on the nighttime monitoring picture for easy target recognition, this application discloses the following technical solutions

Images