Method for adaptively quantizing optical flow features on complex video monitoring scenes

Abstract

The invention belongs to the technical field of digital image processing and relates to a method for adaptively quantizing optical flow features on complex video monitoring scenes. According to the method, the local statistical features are calculated after probability denoising is performed on video space based on the optical flow features, then, the video space position is adaptively quantized, and the video space is divided into a plurality of micro-block areas; finally, each micro-block area is filtered through a motion complexity threshold value, the quantization number is judged, a visual dictionary is generated, and adaptive quantization is achieved. According to the method, the effectiveness and the diversity of motion on the video monitoring scenes are described based on the local statistical features of optical flow. The effective pixel ratio and the motion complexity features are fused, the liveliness of local motion is described, and then the optical flow feature position can be adaptively quantized. On the basis of the motion complexity features, the diversity of the local motion is described, and then the optical flow feature direction can be adaptively quantized. Better discriminability can be played through adaptive quantization of the optical flow features in the next scene analysis based on a word bag model.

Description

technical field [0001] The invention relates to a method in the technical field of digital image processing, in particular to an adaptive quantization method for optical flow features in complex video monitoring scenes. Background technique [0002] Computer vision technology is becoming more and more important in intelligent video surveillance, such as traffic flow monitoring, event detection or congestion detection. Behavior analysis is a fundamental task in computer vision applications. However, given the complexity of environmental conditions, such as light and weather changes, crowding, etc., behavior analysis still faces some challenges. The current research on behavior analysis is mainly divided into two categories. One is the method based on object tracking features. However, in complex scenes, there is still a lack of reliable multi-target tracking algorithms. In addition, it is difficult for tracking algorithms to adapt to sudden changes in motion in complex sc...

AI Technical Summary

Problems solved by technology

[0004] This fixed quantization method makes it face the following three problems: 1) Reducing the quantization accuracy will cause the loss of spatial position and direction resolution; 2) Improving the quantization accuracy will reduce the loss, but will increase the amount of data; 3) Using a unified Quantization accuracy, without considering the actual motion distribution characteristics in the video surveillance scene

Images