YOLO-Tomato: A Robust Algorithm for Tomato Detection Based on YOLOv3

TLDR

Automatic fruit detection is vital for harvesting robots, yet it is hampered by illumination changes, occlusion by branches and leaves, and tomato overlap. The study proposes YOLO‑Tomato, an enhanced YOLOv3‑based model designed to overcome these detection challenges. YOLO‑Tomato adds a dense feature‑reuse architecture and replaces rectangular bounding boxes with circular ones to improve localization accuracy. These changes produce tighter bounding boxes, higher IoU, fewer prediction coordinates, and, as shown by ablation and benchmark tests, outperform state‑of‑the‑art detectors.

Abstract

Automatic fruit detection is a very important benefit of harvesting robots. However, complicated environment conditions, such as illumination variation, branch, and leaf occlusion as well as tomato overlap, have made fruit detection very challenging. In this study, an improved tomato detection model called YOLO-Tomato is proposed for dealing with these problems, based on YOLOv3. A dense architecture is incorporated into YOLOv3 to facilitate the reuse of features and help to learn a more compact and accurate model. Moreover, the model replaces the traditional rectangular bounding box (R-Bbox) with a circular bounding box (C-Bbox) for tomato localization. The new bounding boxes can then match the tomatoes more precisely, and thus improve the Intersection-over-Union (IoU) calculation for the Non-Maximum Suppression (NMS). They also reduce prediction coordinates. An ablation study demonstrated the efficacy of these modifications. The YOLO-Tomato was compared to several state-of-the-art detection methods and it had the best detection performance.