基于SSPENet的圣女果成熟度检测算法

打开文本图片集

中图分类号：S641.2 文献标志码：A 文章编号：1673-2871（2025）12-052-11

Detectionmethod ofcherry tomato fruit ripenessbasedon SSPENet

DUAN Xin'e'， ZHANG Zhiwang， ZHOU Qingxing （1.Shanxisitelolo Finance&Eogalefftieedingl UniversityJihong80，i，a）

Abstract：To achieve rapid andaccurate identification of cherry tomato fruit ripeness in greenhouse environment，this study proposedaripenessdetectionalgorithm basedonthe stereoscopic spatial pyramid atentionnetwork（SSPENet）. First，aspatial stereoscopic atention mechanism（SSAM）was constructed to enhance the perception of fruit features by adaptivelyfocusingon keyregions.Second，a local atention pyramid module（LAPM）was incorporated into theneck network tostrengthen the feature fusionof small-scale cherry tomato，therebyimproving detectionaccuracy for small-scale targets.Finally，an efficient geometric regression loss function ⟨LEGR⟩ was proposed to optimize the geometric properties ofbounding boxes，furtherimproving the localizationaccuracyforsmallscalecherytomatoes.The experimental results showed that SSPENet achieved 96.1% mAP on the cherry tomato ripeness dataset，representing a 5.1 percentage point improvement over the baseline model，with an inference speed of 94.7 frames per second.This achieved a good balance betweendetectionaccuracyandcomputational eficiency.This studyprovides aneficientand scalable technical solution for cherry tomato ripeness detection in greenhouse environment， with broad application prospects.

Keywords：Cherry tomato;Maturity;SSPENet;Loss function; Small scale target

圣女果作为一种具有高营养价值的小型番茄品种，近年来在全球范围内的种植面积和市场需求持续增长[。（剩余17000字）