본문 바로가기

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

문서 유형
연구출판물 · 학술지 논문
등재
SCIEScopus
저널 순위
JCR Q1Scopus Q1
저널
SENSORS20(7) · 2020
피인용
Web of Science 335Scopus 448
FWCI (Scopus)
0
JCR IF
JCR 2019 3.275
ISSN
1424-3210

저자

  1. 류궈쉬제1저자Department of Electronics Engineering, Pusan National University, Busan 46241, Korea
  2. 누와지 조제프 크리스티앙Department of Electronics Engineering, Pusan National University, Busan 46241, Korea
  3. 투코 엠부오웸브 필리프 리오넬Department of Electronics Engineering, Pusan National University, Busan 46241, Korea
  4. 김재호교신저자Department of Electronics Engineering, Pusan National University, Busan 46241, Korea

초록

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-Tomatowas compared to several state-of-the-art detection methods and it had the best detection performance.

키워드

tomato detectionharvesting robotsdense architecturedeep learningIMAGE-ANALYSISVISIONFRUITLOCALIZATIONMACHINEAPPLESSCENES

식별자

Scopus EID
2-s2.0-85083408449
WoS UID
000537110500341