A target measuring method in ball machine video images

Abstract

The invention discloses a target measuring method in ball machine video images. The method comprises the following steps: S0) obtaining visual field angle and optical axis deviation value of each ball machine under each multiplying power, and enabling the visual field angles, the optical axis deviation values and variable power subdivision steps of the ball machine to be generated into enquiry forms respectively, which are stored to a ball machine end; S1) obtaining a monitoring image, and then, obtaining a two-dimension coordinate of two points of a target needing to be subjected to height measurement or length measurement in the monitoring image, the two-dimension coordinate being a pixel coordinate in the monitoring image; S2) obtaining the current variable power subdivision step according to the current multiplying power of the ball machine, obtaining the current visual field angle and the optical axis deviation value from the enquiry forms and converting the two-dimension coordinate into a three-dimensional coordinate according to the visual field angle, the optical axis deviation value and PTZ information of the ball machine; and S3) measuring the length and height of the target according to the three-dimensional coordinate. The method is low in cost, wide in monitoring measurement surface and high in accuracy, can both measure the height of the target, but also measure the length thereof.

Description

technical field [0001] The invention relates to the field of video monitoring, in particular to a method for measuring objects in video images of dome cameras. Background technique [0002] Video surveillance is the physical basis for real-time monitoring of key departments or important places in various industries. Management departments can obtain effective data, images or sound information through it, and monitor and remember the process of sudden abnormal events in time to provide Efficient and timely command and processing means. Faced with the increasingly complex social security situation, public security issues have become increasingly prominent, and new requirements have been put forward for video surveillance. For example, in emergencies, it is necessary to know the height of the person involved, or in a traffic accident, it is necessary to know the length of the vehicle, brake marks, etc. [0003] At present, the methods for measuring the targets in the squadron...

AI Technical Summary

Problems solved by technology

However, the shortcomings of this method are that, firstly, the operation is cumbersome and the cooperation of personnel is high; secondly, it can only be measured afterwards, and the height of the human body cannot be measured in real time; thirdly, the occasions for use are limited, and it is necessary to A fixed occasion, and the camera must be fixed, if it is changed midway, it will cause inaccurate measurement and poor reliability;

For example, the invention patent with the application number of 201310192474.6 discloses a human body height measurement method and its device based on binocular vision technology. The disadvantages of this method are: first, the cost is doubled by using two cameras for the same monitoring point ; Second, it can only measure the height of the participants, and cannot effectively measure other objects in the video screen; Third, the measurement method is limited by geographical terrain, resulting in low measurement accuracy. For example, the ground in the monitoring scene is often Unevenness, undulations, or slopes with a certain angle will affect the measurement results; Fourth, because the camera installation height and angle and other information are measured manually, the error is uncontrollable and will cause errors in the actual results. , even if the calculation parameters can be deduced from the actual height, the height of the ground in the video range may be different due to the fluctuation of the ground, which will cause a large error

Images