Open AccessResearch on Fruit Recognition and Positioning Based on you only look once version4 (YOLOv4)
Author(s) -
Kong Dexiao,
Junqiu Li,
Jeffrey Zheng,
Jiale Xu,
Qinghui Zhang
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2005/1/012020
Subject(s) - correctness , computer science , artificial intelligence , computer vision , set (abstract data type) , pixel , stability (learning theory) , image (mathematics) , training set , pattern recognition (psychology) , test set , machine learning , algorithm , programming language
The recognition and spatial coordinate positioning is an important part of picking equipment of fruits. This paper introduced a method of target detection and pixel learning positioning of fruits based on the Darknet depth framework YOLOv4. We utilized GPU training in Ubuntu 19.10, and used 2000 images of various fruits as the training set for recognition model training, and performed and verified tests in the GPU environment. The results showed that the accuracy of fruit recognition is above 94%, the detection time of a single image is 12.3ms, and the detection rate of the video is 17f/s. The actual test showed that the system has good stability, real-time performance, and correctness of picking objects.