Image stitching method and monitoring camera device therefor

Abstract

The invention discloses an image splicing method which can effectively reduce the number of sampling points, and is applied to a partially overlapping first monitoring image and a second monitoring image generated by a monitoring camera device. The image stitching method includes obtaining a first sampling point and a second sampling point respectively in the first monitoring image and the second monitoring image, detecting respective first specific parameters of the first monitoring image and the second monitoring image, and a second specific parameter, according to the first specific parameter and the second specific parameter to determine whether the first sampling point is paired with the second sampling point, and determine whether to use the first sampling point and the second sampling point to splicing according to the matching result The first monitoring image and the second monitoring image. The image stitching method and the monitoring camera device of the present invention utilize space limitation, time limitation, speed limitation or path limitation to eliminate sampling points that do not meet the preset conditions, and greatly improve the instruction cycle and accuracy of image stitching by reducing the number of wrong sampling points. sex.

Description

technical field [0001] The invention relates to an image splicing method and a monitoring camera device thereof, in particular to an image splicing method and a monitoring camera device thereof which can reduce the number of sampling points to reduce the amount of computation to improve performance. Background technique [0002] With the advancement of technology, surveillance cameras can be equipped with multiple image capture devices at the same time, which can shoot large-scale surveillance scenes from different angles of view, obtain multiple small-scale surveillance images, and stitch them into wide-angle surveillance images. The surveillance images of these small-scale surveillance images will partially overlap, and the image splicing technology detects the overlapping areas of the surveillance images, from which the same feature points that appear in adjacent small-scale surveillance images are searched for splicing of the surveillance images. Surveillance cameras are...

AI Technical Summary

Problems solved by technology

Surveillance cameras are mostly installed in areas with heavy traffic. There will be a large number of pedestrians and vehicles in the surveillance images. Each pedestrian and each vehicle can be regarded as a feature point; different objects may form feature points on the image coordinates at different times. A large number of feature points will reduce the computational efficiency of image stitching

Images