The invention discloses a visual navigation method for an intelligent carrier, which comprises the following steps of calibrating a camera, processing a video to obtain a frame image, preprocessing the obtained image by adopting an image enhancement method based on active illumination, and performing target identification on the image based on a YOLOv4 network target detection method so as to obtainthe image category and the image location information. The target detection algorithm is constructed based on the YOLOv4 network, the target object can be detected, the pre-selected frame can be framed, and a foundation is laid for subsequent stereo matching to obtain depth information and avoid obstacles. According to the method, only matching operation is carried out on the pre-selected frameimage, so that the size of the stereo matching image is reduced, the calculation efficiency of the stereo matching is greatly improved, and a beneficial effect is achieved for improving the real-timeperformance of target detection.
本发明公开了一种智能搬运车视觉导航方法,包括以下步骤:对摄像机进行标定,对视频进行处理得到帧图,采用基于主动光照的图像增强的方法对得到的图像进行预处理,基于YOLOv4网络目标检测的方法,对图像进行目标识别,得到图像的类别与图像的位置信息,本发明目标检测算法基于YOLOv4网络构建,不仅可以检测出目标物,还可以框出预选框,为后续立体匹配获取深度信息以及避障打下了基础。由于本发明方法只对预选框图像进行匹配运算,减少了立体匹配的图片大小,也大大提高了立体匹配的计算效率,为提高目标检测实时性起到有益效果。
Visual navigation method for intelligent carrier
智能搬运车视觉导航方法
2021-04-02
Patent
Electronic Resource
Chinese
Intelligent Visual Navigation System of High Accuracy
IEEE | 2019
|European Patent Office | 2021
|Intelligent laser guide carrier based on visual positioning and positioning method
European Patent Office | 2023
European Patent Office | 2020
|