Object detection method and object detection device

Abstract

An object detection method and an object detection device are provided. The object detection method is used to detect objects placed on a display screen, wherein a background image is displayed on the display screen. The object detection method includes: acquiring a first image, wherein the first image includes a third image on the display screen. a background image and an image of the object; obtaining a second image, wherein the second image includes a second background image on the display screen and an image of the object, and the second background image is the An image generated by shifting the first background image by a predetermined distance in the first direction; and performing image processing on the first image and the second image to detect an object from the display screen. Through the physical detection method and physical detection device according to embodiments of the present invention, objects can be detected on a display screen displaying complex images, thereby effectively identifying and extracting objects, and improving the overall performance of the system.

Description

technical field [0001] The invention relates to an object detection method and an object detection device. Background technique [0002] When the display screen is placed on a flat surface such as a desktop, some additional objects may be placed on the display screen, and at the same time, images may also be displayed on the display screen. [0003] In scenarios such as interactive games, it may be necessary to use a camera to identify the above-mentioned objects that do not belong to the content displayed on the screen from among the images displayed on the display screen. [0004] That is, in the above case, while the background image is displayed on the display screen, the camera needs to recognize and extract the object from the background image. At this time, it is necessary to identify and extract the object by separating the background image. However, due to In this case, the background is generally complex and there is lighting interference, which makes the extracti...

AI Technical Summary

Problems solved by technology

[0004] That is, in the above case, while the background image is displayed on the display screen, the camera needs to recognize and extract the object from the background image. At this time, it is necessary to identify and extract the object by separating the background image. However, due to In this case, the background is generally complex and there is lighting interference, which makes the extraction process difficult

[0005] In the prior art, the camera can be used to capture the image including the background image and the object displayed on the display screen, and then use an algorithm to segment the background from the image captured by the camera, and then obtain the object through binarization, but this is subject to The influence of complex background and lighting is more obvious

[0006] In addition, the image captured by the camera including the background image and the object displayed on the display screen can be differentiated from the background image displayed on the display screen, for example, the above background image can be obtained by taking a screenshot of the display screen, so that by Objects can also be obtained by binarizing the obtained difference map, but this will also be affected by complex backgrounds and lights

Images