A Detection Method for Single Object Removal and Tampering in Surveillance Video

Abstract

The invention discloses a single object removing and tampering detection method for a monitored video. The single object removing and tampering detection method comprises the following steps of: reconstructing high-frequency components obtained by wavelet transform of gray images of monitored images in a monitored video to be detected; then, processing fractal image blocks of reconstructed images; calculating a high-frequency difference degree value of each image block in the reconstructed images; then, forming a high-frequency difference degree value set by high-frequency difference degree values of the image blocks at the same airspace position in the reconstructed images of the high-frequency components of the respective gray images of all the monitored images in the monitored video to be detected, calculating the mean value of all the high-frequency difference degree values concentrated by various high-frequency difference degree values, and thereby, determining a removing and tampering judgement threshold value according to the mean value of all the high-frequency difference degree values concentrated by various high-frequency difference degree values; and judging whether the image blocks are object removing and tampering areas or not according to the removing and tampering judgement threshold value. The method disclosed by the invention is difficultly influenced by quantization coding, and can be used for effectively detecting a relatively small removing and tampering target object.

Description

technical field [0001] The invention relates to a detection technology for removing and tampering with video, in particular to a detection method for removing and tampering with a single object in a surveillance video. Background technique [0002] With the rapid development of video surveillance technology, video security surveillance has become the fourth major investigation technology after criminal science and technology, technical investigation and network investigation technology. As a kind of audio-visual materials, video security monitoring images have become one of the eight statutory evidences, and have shown an increasingly important position in judicial practice and case investigation. However, with the popularization of video tampering software, video surveillance is very easy to be tampered with. If the tampered surveillance video is used as evidence, it will bring immeasurable harm to judicial practice and case investigation. [0003] Object removal tampering...

AI Technical Summary

Problems solved by technology

For example, Yang Jing, Ren Yanzhen, Wang Zhaoxiang, and Cui Xiaoyu proposed a monitoring video tampering detection algorithm based on differential energy. By analyzing the means of deleting and tampering with surveillance video objects, it can be obtained that the tampered video frame of the deleted object has a very high correlation with the video frame that provides the copied content. Using this principle to find matching blocks to achieve the purpose of detection, since this method is based on the operation of pixels, when the surveillance video is in the transmission process, it usually encounters secondary compression, which is Quantization coding noise will be introduced, which will eventually reduce the detection accuracy on a pixel basis

Another example is Liu Yuqing and Huang Tianqiang's video tampering detection and tampering area location based on energy suspiciousness in the space-time domain proposed by Liu Yuqing and Huang Tianqiang. It detects whether there is a loss of high-frequency components in this frame by calculating the energy suspiciousness of each frame. Since this method is based on frames unit, so when the target object is small, the impact on the whole frame after tampering is minimal, and the method will fail at this time; in addition, when the texture of the tampered area is relatively simple, if only the reduction of high frequency is detected, the detection effect will not be good. will be obvious

Images