Abstract
In this work, we present a new dataset to advance the state-of-the-art in fruit detection, segmentation, and counting in orchard environments. While there has been significant recent interest in solving these problems, the lack of a unified dataset has made it difficult to compare results. We hope to enable direct comparisons by providing a large variety of high-resolution images acquired in orchards, together with human annotations of the fruit on trees. The fruits are labeled using polygonal masks for each object instance to aid in precise object detection, localization, and segmentation. Additionally, we provide data for patch-based counting of clustered fruits. Our dataset contains over 41'0000 annotated object instances in 1000 images. We present a detailed overview of the dataset together with baseline performance analysis for bounding box detection, segmentation, and fruit counting as well as representative results for yield estimation. We make this dataset publicly available and host a CodaLab challenge to encourage a comparison of results on a common dataset. To download the data and learn more about the MinneApple dataset, please see the project website: http://rsn.cs.umn.edu/index.php/MinneApple. Up to date information is available online.
| Original language | English (US) |
|---|---|
| Article number | 8954630 |
| Pages (from-to) | 852-858 |
| Number of pages | 7 |
| Journal | IEEE Robotics and Automation Letters |
| Volume | 5 |
| Issue number | 2 |
| DOIs | |
| State | Published - Apr 2020 |
Bibliographical note
Funding Information:Manuscript received September 10, 2019; accepted December 23, 2019. Date of publication January 9, 2020; date of current version January 27, 2020. This letter was recommended for publication by Associate Editor Dr. I. Rekleitis and Editor Y. Choi upon evaluation of the reviewers’ comments. This work was supported by USDA under Grant NIFA MIN-98-G02. (Corresponding author: Nicolai Häni.) The authors are with the Department of Computer Science and Engineering, University of Minnesota, Minneapolis, MN, 55455 USA (e-mail: haeni001@ umn.edu; royxx268@umn.edu; isler@umn.edu). Digital Object Identifier 10.1109/LRA.2020.2965061 Fig. 1. MinneApple contains precise semantic object instance annotations, from which one can extract bounding boxes for detection 1(a) and semantic labels 1(b). We also provide an additional dataset to evaluate patch based counting of overlapping fruits 1(c). MinneApple contains data from 17 different tree rows sporting large variety 1(d).
Publisher Copyright:
© 2016 IEEE.
Keywords
- Agricultural automation
- object detection
- robotics in agriculture and forestry
- segmentation and categorization