Object recognition method and device based on game scene

Abstract

The invention discloses a game scene-based object recognition method and device. Wherein, the method includes: predetermining the reference area and the non-reference area included in the target to be identified, acquiring the pixel information of the reference area, and the pixel information of the non-reference area and the relative coordinate value of the non-reference area relative to the reference area; During the running of the game, if there is an area matching the pixel information of the reference area in the current running interface, the matching area is determined as the first area; A second area corresponding to the first area; when the pixel information of the second area matches the pixel information of the non-reference area, the object including the first area and the second area in the current running interface is identified as the target object. By adopting this solution, accurate identification of objects in the game scene can be realized, and the requirement for automatic identification of objects in the game scene can be met.

Description

technical field [0001] The present invention relates to the technical field of electronic information, in particular to a game scene-based object recognition method and device. Background technique [0002] With the rapid development of information technology and society, various electronic games have enriched people's entertainment life. When operating a video game, a user often needs to first recognize certain objects in the game scene, and then perform corresponding operations. For example, on the home page of the game, you need to identify icons such as "Start" first, and then click on them to enter the game; or, in the game fighting scene, when you need to "pick up gold coins", you need to first determine the position of the "gold coin". Then perform the appropriate action on it. [0003] However, the inventor found in the process of realizing the present invention that the above-mentioned methods in the prior art have at least the following defects: at present, users...

AI Technical Summary

Problems solved by technology

[0003] However, the inventor found in the process of realizing the present invention that the above-mentioned methods in the prior art have at least the following defects: at present, users often need to determine the target object in the game scene by themselves, especially when the target object is displayed in the game interface. When it is not fixed (such as the "gold coin" icon with an unstable position in the game interface), it will consume a lot of energy for the user to identify the target, thus making the user lose interest in the game and reducing the user experience

Therefore, there is still a lack of a method and device that can accurately and automatically identify objects in a game scene

Images