Image shooting splicing method and system

Abstract

The invention provides an image shooting splicing method and system, and the method comprises a camera installation step: carrying out the calibration and approaching installation of a plurality of cameras, and enabling the calibration and approaching installation to maintain the nearest physical installation distance of two adjacent cameras during the installation of the cameras, thereby guaranteeing the nearest optical center distance of the two cameras; a mapping table acquisition step: establishing a mapping table of pixel points of images acquired by the plurality of cameras according tothe positions of the plurality of installed cameras; and an image splicing step: determining an image splicing relationship corresponding to the image according to the established mapping table of thepixel points of the image, and carrying out image splicing processing according to the images respectively shot by the plurality of cameras at the same moment to obtain a spliced image. According tothe invention, the image information is obtained through two or more cameras, and the vision field is expanded. A calibration setting scheme of the camera is provided by performing calibration settingon the position relationship of two or more than two cameras.

Description

technical field [0001] The present invention relates, in particular, to an image capture and stitching method and system. Background technique [0002] With the implementation of technology, capital, relevant laws and regulations and other factors, self-driving vehicles will gradually be mass-produced and ultimately serve consumers. Self-driving vehicles must be equipped with a large number of sensors to identify relevant factors such as scenes and obstacles, and the information collected by each sensor is fused through the information fusion module, and finally the fused information is delivered to the calculation decision module for path planning and Body Motion Control. [0003] In the process of scene and obstacle recognition, the camera plays a very important role as one of the key sensors. However, based on its own configuration, a single camera has a relatively narrow field of view. If an autonomous vehicle wants to drive on the road, it needs to understand its surro...

AI Technical Summary

Problems solved by technology

When the above scheme is implemented, there will be two problems. One is the large amount of calculation, and the other is that it is difficult to stitch images when there is no overlapping area.

Images