Image processing method and device

Abstract

The invention discloses an image processing method and device, and the method comprises the steps: obtaining the first pixel point information of a to-be-matched first target object in a first image,and obtaining the second pixel point information of a to-be-matched second target object in a second image; determining a first characteristic value of the first target object based on the parameter information of two camera devices and the first pixel point information; determining a second characteristic value of the second target object based on the parameter information of the two camera devices and the second pixel point information; and if the first characteristic value is matched with the second characteristic value, determining that the first target object and the second target objectare the same target object. The characteristic value of the target object is determined through the relatively stable pixel point information and the parameter information of the corresponding cameradevices without being affected by external use conditions, and compared with the prior art, the characteristic value is used for matching the target object, so that the matching result is more stable,and the accuracy is higher.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to an image processing method and device. Background technique [0002] In the application field of machine vision, it is necessary to obtain the surrounding environmental information through images, and usually use cameras at different positions and different perspectives to collect multi-angle and multi-scale visual information of target objects in the environment. In this process, it is necessary to match the same target object from the environmental images collected by different camera devices, so as to obtain the visual information of the target object in different camera devices, so as to better construct the surrounding environment. [0003] Existing target object matching methods include image feature matching method, distance matching method, etc. By extracting features from image target objects and then matching and filtering the features, the processing steps are relati...

AI Technical Summary

Problems solved by technology

[0003] The existing target object matching methods include image feature matching method, distance matching method, etc., by extracting features from the target object in the image and then matching and filtering the features, the processing steps are relatively complicated

However, both target object matching methods have limitations. For example, the image feature matching method is not suitable for situations where the angles of multiple cameras are greatly different, and the matching accuracy will be reduced; the distance matching method is too dependent on the accuracy of ranging

[0004] It can be seen that when using the existing target object matching method to match the target object, there is a problem of low matching accuracy

Images