Target searching method of visual robot and robot

Abstract

The invention provides a target searching method of a visual robot and the robot and relates to the technical field of robot searching. The target searching method comprises the steps that search target information is obtained, wherein the search target information comprises target features and a belonging target type; a visual camera is started to shoot to obtain a visual field image, the visualfield image is preprocessed to generate a detection image according to the detection image size requirement of a target detection neural network model corresponding to the belonging target type, the detection image is input to the corresponding target detection neural network model to perform target detection, the detection image is formed by splicing a plurality of images which have different resolutions and are related to the visual field image; and a target detection result is obtained, and whether a search target exists in the target detection result is judged according to the target features. On the basis of ensuring the real-time accuracy of far and near target search, the requirement of far and near target search on the computing power of equipment is reduced.

Description

technical field [0001] The invention relates to the technical field of robot search. Background technique [0002] The search for targets by intelligent mobile robots is widely used in search and rescue services, scene monitoring and object finding, target detection and other fields, and has broad application prospects. [0003] The search for targets by mobile robots may involve multiple fields such as computer vision and pattern recognition. Among them, for computer vision, the purpose is to simulate the human visual mechanism, calculate the importance of information in the visual scene, and extract the salient features or target object features of interest in the image. The process of robot target search based on vision usually includes image acquisition, target detection and target confirmation. With the rapid development of artificial intelligence and deep learning technology, object detection methods based on convolutional neural network (CNN) algorithms have been wi...

AI Technical Summary

Problems solved by technology

[0004] However, on the one hand, although the convolutional neural network algorithm improves the real-time accuracy of tracking, because the convolutional neural network-based target detection algorithm usually contains a large number of calculation-intensive operations, the requirements for real-time detection computing power and bandwidth are very high.

Images