Object detection method based on depth reinforcement learning

Abstract

The invention provides an object detection method based on depth reinforcement learning, and belongs to the mode identification technical field and active object detection technical field; the methodcomprises the following steps: firstly building a depth reinforcement learning nerve network; carrying out multi object detection tests for a robot, obtaining training data to train the nerve network,thus obtaining a trained nerve network; in the usage phase, the robot obtains a present time image and an envelope box of a to-be-detected object in the image, and inputs same into the trained nervenetwork; the network outputs a motion to-be-executed by the robot in the next moment; the robot executes the motion to obtain a new present time envelope box, and uses an identification function for determination; if the identification credibility of the to-be-detected object in the envelope box is higher than a set identification threshold, the object detection succeeds. The method uses the reinforcement learning technology to control the robot motions, and uses the robot visual angle changes to obtain better observation images, thus obtaining a better object detection result.

Description

technical field [0001] The invention proposes an object detection method based on deep reinforcement learning, which belongs to the technical field of pattern recognition and the technical field of active object detection. Background technique [0002] As one of the main research contents of robotics and computer vision systems, object detection is widely used in video surveillance, unmanned driving and multimedia processing. Most of the current object detection methods are aimed at static images with good shooting conditions, but in practical applications, such images are often difficult to obtain, especially in robotic applications, where occlusions, partial shots, and small scales often appear in the captured pictures. defect. But in robot applications, the shooting angle can be changed by adjusting the pose of the robot to obtain an image more suitable for detection, so as to realize the active object detection of the robot. [0003] Related published patents such as 1...

AI Technical Summary

Problems solved by technology

This existing technology uses a reinforcement learning method to operate a single image to obtain a better object positioning effect, but for a robot, a single image may have problems such as occlusion or partial shooting, and the existing methods cannot effectively solve this problem

Images