Object detection method and related equipment

Abstract

The embodiment of the invention discloses an object detection method and related equipment, and the method comprises the steps: obtaining a to-be-detected depth image, and segmenting a foreground region from the depth image according to the depth values of pixel points in the depth image; because the target object has a foreground area which is more likely to be in the depth image, the corresponding point cloud can be generated for the foreground area. Therefore, whether the depth image includes the target object is detected according to the generated point cloud. According to the method, thepoint cloud is generated from the foreground area which may more possibly include the target object in the depth image and is further detected, and the background area which may not include the targetobject is eliminated, that is, the point cloud is not generated from the areas, so that the calculation amount is reduced, and the object detection efficiency and the detection real-time performanceare improved.

Description

technical field [0001] The present application relates to the field of computer vision, in particular to an object detection method and related equipment. Background technique [0002] Object detection is widely used in modern life. The objects here are human bodies, etc. In shopping malls, stations, homes, etc., object detection algorithms can provide data for many applications such as security, entertainment, and precision services. In the dark scene, the object detection algorithm based on the color image fails, while the object detection algorithm based on the depth image performs well, which makes up for the deficiency of the color image. [0003] At present, the method of object detection based on the depth image mainly includes the detection algorithm of the point cloud, by first preprocessing the depth image and converting it into a point cloud, and then determining the ground point cloud according to the prior information, so as to extract the non-ground point cloud...

AI Technical Summary

Problems solved by technology

[0004] Since this method needs to generate point clouds for scenes that do not include the target object in the depth image, such as the ground, and calculate these point clouds, the object detection efficiency is low and the real-time performance is not good.

Images