Shadow removal method and apparatus

Abstract

The present invention discloses a shadow removal method and apparatus. The method includes the following steps that: an inputted image to be detected is pre-segmented through using a super pixel algorithm, and seed points are allocated for pre-segmented super pixels; the distance measure of each pixel point in the pre-segmented super pixels and the seed points of adjacent pre-segmented super pixels is obtained, the minimum value of the distance measure is adopted as the class label of the pixels, and the coordinate mean values of pixels in each class label are obtained, and the coordinate mean values are adopted as new seed points; the distance measure is iteratively calculated by using the weights of color distance and spatial distance until new seed points no longer change, and the new seed points are determined as final seed points and are adopted as super pixels; material classification is performed on the super pixels, and a shadow material is removed. According to the method, the complexity of background information is not considered, the material in the image is directly decomposed into the super pixels; and the super pixels are described based on the fusion of various features, the super pixels containing shadow are removed from pixel classes; and therefore, the accurate coordinate position of a target can be obtained.

Description

Technical field [0001] This application relates to the field of image processing technology, and in particular to a shadow removal method. The application also relates to a shadow removal device. Background technique [0002] Video surveillance is an important part of the road safety protection system. Traditional surveillance systems include front-end cameras, transmission cables, and video surveillance platforms. Cameras can be divided into network digital cameras and analog cameras, which can be used as front-end video image signal collection. It is a comprehensive system with strong defense capabilities. Video surveillance is widely used in many occasions for its intuitive, accurate, timely and rich information content. [0003] Video surveillance is an indispensable and important part of the intelligent transportation system that is getting more and more attention. In the actual application of road and park monitoring, disturbing shadows, such as shade of trees, shadows o...

AI Technical Summary

Problems solved by technology

In the practical application of road and park monitoring, disturbed shadows, such as tree shade, shadows of targets (vehicles, pedestrians, etc.) are often mistaken for targets or part of targets, thus affecting the positioning of target size and position, and affecting Proper Control of Intelligent Transportation Systems

For example, a disturbed shade of a tree can cause hundreds of false alarms, causing significant disruption to both storage and event viewing

And the target moving in the shadow may miss the target because it is connected with the shadow

[0004] The applicant found in the process of implementing this application that the important prerequisite for applying the current shadow removal method is to be able to extract a reliable background, in order to use the foreground and background to extract effective feature vectors. For the monitoring of actual scenes, due to the complexity of the environment , which often leads to inaccurate background established by traditional background modeling methods, which affects the final classification judgment

The mixed Gaussian background model as described in the prior art is only suitable for low-speed long-distance large scenes, and the background reliability for short-distance real-time small scene monitoring is greatly reduced. In addition, in the prior art, for single or significant Weak shadow features will affect the accuracy of shadow judgment, and it is difficult to ensure the integrity of the final target extraction, thus affecting the positioning of the exact position of the object

Images