An automatic target reporting method based on video analysis

Abstract

The invention relates to an automatic target scoring method based on video analysis. The method comprises image correction, target surface parameter modeling, shooting determination and bullet hole positioning. Before shooting, a collected target surface image is corrected to obtain a corrected target surface image, and a target surface parameter model is established in the corrected target surface image; and in the shooting process, a collected target surface image sequence is analyzed in real time, shooting determination is carried out to determine whether shooting is carried out, and when a shooting behavior occurs, a bullet hole is positioned, and the score of the bullet hole is determined according to the target surface parameter model. According to the method, distortion of the target surface image is removed via geometric correct; the target surface parameter model is more accurate by improving a loop boundary point searching method; the bullet hole is positioned accurately via a classification method, the dynamic change feature of a bullet hole area is utilized fully, and the accuracy of automatic target scoring is improved; and the collected video sequence is analyzed in real time to implement shooting determination and bullet hole positioning, so that the automatic degree of target scoring is improved.

Description

technical field [0001] The invention belongs to the field of video analysis and image processing, and in particular relates to an automatic target reporting method based on video analysis. Background technique [0002] Live ammunition shooting is an indispensable link in military training. At present, in the live ammunition shooting training of our country, the army mainly adopts artificial target reporting, that is, when some soldiers shoot, the other part of the soldiers hides under the target trench. Some specific tools (such as telescopes or cameras) are used to determine the number of target rings, and then target reporting is performed according to the requirements of the range managers. The traditional target reporting method seriously affects the development of shooting, a basic training subject, restricts the quality and efficiency of soldier training, and also does not meet the requirements of scientific and technological training. Therefore, the development of an...

AI Technical Summary

Problems solved by technology

Although the automatic target reporting system based on image processing technology has achieved certain results, most of the current methods only recognize and judge according to the brightness of the ring line and the bullet hole.

In Chinese Patent Publication No. CN2831033Y "Automatic Recognition Target Reporting Device" such as Zheng Xiaoshi thinks that the front and rear images overlap completely in the shooting process, and only adopts a simple threshold method to judge the point of impact; Xu Hongwei et al. In "Automatic Target Recognition Method of Processing Technology", the bullet hole is determined only by the difference between the circle line and the bullet hole size, and when the circle fitting method is used to model the target surface parameters, the method of searching the boundary points of the circle line from left to right is too ideal. The incompleteness of the ring line in the binarized target surface image in practical applications is not considered

[0005] To sum up, live ammunition shooting training is mostly carried out outdoors, the environment is complex, and the natural lighting conditions vary greatly, which requires high robustness of the target reporting system. However, most current target reporting systems based on image processing technology only The accuracy of target recognition is low, and it is difficult to adapt to the complex outdoor environment under natural light conditions, and the system is not highly automated in the collection, processing and analysis of target surface information, which cannot meet the requirements of practical applications.

Images