基于改进YOLOv7的番茄果实成熟度检测方法

打开文本图片集

中图分类号S126 文献标识码A文章编号 0517-6611（2025）12-0193-03

doi：10.3969/j.issn.0517-6611.2025.12.042

开放科学（资源服务）标识码（OSID）：

MaturityDetection of Tomato Based on Improved YOLOv7

TANRong-yig，iang，LJun-etal（ShlfSartAultureEgiingeiVocaalClgeoflureejing 102442）

AbstractTouratelyentifyeatuityoftoatoargtinfcilitviroents，provetectioefecydaltydchve inteligentharvestingAancdLOodelisroposdfotetigtaturitoftgettoatofruis.sproachce model'sfocusonteagetregiosfputdatabyitegatintheCBAatetiomehasm；eploingtheSof-algoritetiely preventsissdetetiosuetigsitepngetsgsuppesdbyaingetiofoacngte originallossfunctioEOUandeplacing iithIOU，eexperientalsultssowtatteimprovedYOLOodelhasdetectioecision of 93.1% ，a recall rate of 90.8% ，and a mean average precision of 94.8% . Compared with the original YOLOv7 and YOLOv5 models，it hasimprovedindetetionprecision，ecallate，andmanaverageprecision，providingtechicalreferecefortmatoharvestingoplex environments.

Key words Tomato; YOLOv7; Maturity detection; Target recognition

番茄收获过程中，人工采摘成本占据 33%～50% 。（剩余5065字）