Method and device for correcting camera preset position

Abstract

The invention provides a camera preset position correction method. The camera preset position correction method comprises the following steps: A, acquiring a standard image and a plurality of images to be detected; B, preprocessing the standard image and each to-be-detected image; C, acquiring each feature vector; D, acquiring the offset of the to-be-detected image relative to the standard image in the x direction and the y direction; E, obtaining a relation curve between the offset and the rotation angle; F, determining the current rotation angle of the camera; G, the holder corrects part ofthe value of the current rotation angle, obtains a new image to be detected after correction rotation, obtains the offset of the new image to be detected, enters the step H if the offset is smaller than the offset obtained in the step F, and otherwise, enters the step I; H, the holder continues to correct 100% of the current rotation angle; i, re-determining the current rotation angle of the camera, and repeating the step G; the invention further provides a device for correcting the preset position of the camera. The method is high in calculation precision, high in speed and high in detectionefficiency.

Description

technical field [0001] The invention relates to a camera preset position correction method and device. Background technique [0002] In order to quickly and accurately locate the target point in the video surveillance system, it is necessary to adopt the method of pre-positioning the pan-tilt camera system. The monitoring personnel aim the PTZ camera at the target position in advance, and set this position as the preset position. When the monitoring personnel need to locate the target position, they only need to send a command to the PTZ control system to locate the preset position, and then they can quickly locate the target position and find the target accurately. [0003] The main part that affects the precision of the preset position is the quality of the motor, the performance of the slip ring and the control of the circuit. The large rotational inertia of the load carried by the gimbal determines that the torque of the gimbal drive motor must be large. The distance b...

AI Technical Summary

Problems solved by technology

The two images are superimposed to directly obtain the position of the image boundary; the existing research uses the drawn ruler spline detection to obtain the offset position of the target image. The matching of this method uses line matching, the matching accuracy is low, and the detection The accuracy of the obtained position offset is low; while comparing the entire frame images of the two images, performing block matching or obtaining the phase correlation function through fast Fourier transform to obtain the offset; this method matches almost every pixel Both are processed or transformed, with a large amount of calculation and low processing speed