Scene recognition and classification method based on Tiny-Darknet

Abstract

The invention provides a scene recognition and classification method based on Tiny-Darknet, and the method comprises the following steps: constructing a training sample set of a classification model;building a deep learning framework based on a Tiny-darknet network; configuring training parameters, and training a classification model; acquiring equipment monitoring image information; classifyingthe scene images; judging scene changes; completing scene recognition parameter configurations. The beneficial effects of the invention are that the method achieves the automatic switching of parameter configuration through scene recognition, is precise in scene recognition and detection, is high in universality, is suitable for monitoring equipment in any scene, guarantees the quality of a monitoring image of the monitoring equipment, improves the use performance of the equipment, and meets the actual demands.

Description

technical field [0001] The invention relates to the technical field of video detection, in particular to a Tiny-Darknet-based scene recognition and classification method. Background technique [0002] In recent years, the security monitoring industry has developed rapidly, from the original analog system monitoring to digital network high-definition monitoring, and the clarity has been greatly improved. However, in different scene environments, different monitoring equipment parameters need to be applied, and the scene status changes, and the device parameters need to be reconfigured; however, users who do not understand the device parameters often cannot obtain the best quality video surveillance images. [0003] The parameter configuration of traditional video surveillance equipment is selected by technicians according to the installation scene when they are installed on site. This method is relatively simple, and there is no problem under normal circumstances. However, o...

AI Technical Summary

Problems solved by technology

On the one hand, this method can only be applied to static scenes, that is, there is no obvious difference between each frame of the monitoring screen in the same scene, which is obviously not suitable for scenes with strong mobility; on the other hand, this method is applied to monitoring In the device, it takes up a lot of memory, which cannot meet the requirements of real-time performance or low-end monitoring equipment

In order to solve these two types of problems, some scholars have improved the effect from the perspective of optimizing the image feature extraction algorithm, but the effect is only obvious in specific scenarios, and the universality is not strong.

Images