Tomato ripeness detection and fruit segmentation based on instance segmentation

• Published in: Frontiers in plant science Vol. 16; p. 1503256
• Main Authors: Wei, Jinfan, Sun, Yu, Luo, Lan, Ni, Lingyun, Chen, Mengchao, You, Minghui, Mu, Ye, Gong, He
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Media S.A 2025
• Subjects: ACP-tomato-seg; adaptive feature extraction; complex field environments; multi-scale features; self-attention mechanism; tomato instance segmentation; self-attention mechanism; complex field environments; multi-scale features; tomato instance segmentation; adaptive feature extraction; ACP-tomato-seg

In order to meet the urgent need of fruit contour information for robot precision picking in complex field environments (such as light changes, occlusion and fruit overlap, etc.), this paper proposes an improved YOLOv8s-seg method for tomato instance segmentation, named ACP-Tomato-Seg. The method pr...