Active camera target positioning method based on depth reinforcement learning

Abstract

The invention provides a method carrying out target positioning through active adjustment of a camera in an image acquisition application and belongs to the mode identification technology field and the active camera positioning technology field. The method comprises steps that a depth neural network for evaluating the camera positioning effect is trained; multiple times of target positioning tests are carried out, in a positioning test process, a depth neural network for fitting a reinforcement learning value function is trained, and quality of seven types of operation including upward turn, downward turn, leftward turn, rightward turn, amplification, reduction and no change of the camera is determined through the depth neural network; decision for camera operation is made through employing a decision network according to the image information presently acquired by the camera. Through the method based on depth reinforcement learning, image acquisition quality is improved, different target positioning tasks can be adapted to, the method is an autonomous learning positioning method, artificial participation stages are quite few, and the method refers to a method of active camera learning and autonomous target learning.

Description

technical field [0001] The invention relates to a camera active target positioning method based on deep reinforcement learning, belonging to the technical field of pattern recognition and the technical field of camera active positioning. Background technique [0002] In recent years, cameras have been increasingly used in production and life, such as: security monitoring, vehicle detection, target tracking, face recognition. In current application scenarios, cameras provide image information, and use manual monitoring or target detection algorithms to implement corresponding applications. During the entire camera image acquisition process, the camera is fixed or cyclically adjusts the angle according to the specified route. It cannot actively adjust the field of view and actively locate the target according to the actual scene. [0003] In the existing technical documents, the invention patent "Camera Infrared Active Tracking Device and Camera Control System Using the Devic...

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that it can only be applied to target positioning scenarios that can distinguish infrared signals, and it cannot be adjusted according to different applications.

In addition, this method needs to add an additional infrared device, instead of making adjustments directly based on image information