TY - JOUR
T1 - Monocular Camera Based Fruit Counting and Mapping with Semantic Data Association
AU - Liu, Xu
AU - Chen, Steven W.
AU - Liu, Chenhao
AU - Shivakumar, Shreyas S.
AU - Das, Jnaneshwar
AU - Taylor, Camillo J.
AU - Underwood, James
AU - Kumar, Vijay
N1 - Funding Information:
Manuscript received September 10, 2018; accepted January 23, 2019. Date of publication February 27, 2019; date of current version March 15, 2019. This letter was recommended for publication by Associate Editor J. Sanchez-Medina and Editor Y. Choi upon evaluation of the reviewers’ comments. This work was supported in part by the Army Research Laboratory, Distributed and Collaborative Intelligent Systems and Technology Collaborative Research Alliance under Grant W911NF-17-2-0181, in part by the Army Research Office under Grant W911NF-13-1-0350, in part by the United States Department of Agriculture under Grant 2015-67021-23857, in part by the National Science Foundation under Grant IIS-1138847, Qualcomm Research, C-BRIC (a Semiconductor Research Corporation Joint University Microelectronics Program cosponsored by DARPA), and in part by the Australian Centre for Field Robotics, The University of Sydney. (Corresponding author: Xu Liu.) X. Liu, S. W. Chen, C. Liu, S. S. Shivakumar, C. J. Taylor, and V. Kumar are with the GRASP Lab, University of Pennsylvania, Philadelphia, PA 19104 USA (e-mail:, liuxu@seas.upenn.edu; chenste@seas.upenn.edu; liuch13@ seas.upenn.edu; sshreyas@seas.upenn.edu; cjtaylor@seas.upenn.edu; kumar@ seas.upenn.edu).
Publisher Copyright:
© 2016 IEEE.
PY - 2019/7
Y1 - 2019/7
N2 - In this letter, we present a cheap, lightweight, and fast fruit counting pipeline. Our pipeline relies only on a monocular camera, and achieves counting performance comparable to a state-of-the-art fruit counting system that utilizes an expensive sensor suite including a monocular camera, LiDAR and GPS/INS on a mango dataset. Our pipeline begins with a fruit and tree trunk detection component that uses state-of-the-art convolutional neural networks (CNNs). It then tracks fruits and tree trunks across images, with a Kalman Filter fusing measurements from the CNN detectors and an optical flow estimator. Finally, fruit count and map are estimated by an efficient fruit-as-feature semantic structure from motion algorithm that converts two-dimensional (2-D) tracks of fruits and trunks into 3-D landmarks, and uses these landmarks to identify double counting scenarios. There are many benefits of developing such a low cost and lightweight fruit counting system, including applicability to agriculture in developing countries, where monetary constraints or unstructured environments necessitate cheaper hardware solutions.
AB - In this letter, we present a cheap, lightweight, and fast fruit counting pipeline. Our pipeline relies only on a monocular camera, and achieves counting performance comparable to a state-of-the-art fruit counting system that utilizes an expensive sensor suite including a monocular camera, LiDAR and GPS/INS on a mango dataset. Our pipeline begins with a fruit and tree trunk detection component that uses state-of-the-art convolutional neural networks (CNNs). It then tracks fruits and tree trunks across images, with a Kalman Filter fusing measurements from the CNN detectors and an optical flow estimator. Finally, fruit count and map are estimated by an efficient fruit-as-feature semantic structure from motion algorithm that converts two-dimensional (2-D) tracks of fruits and trunks into 3-D landmarks, and uses these landmarks to identify double counting scenarios. There are many benefits of developing such a low cost and lightweight fruit counting system, including applicability to agriculture in developing countries, where monetary constraints or unstructured environments necessitate cheaper hardware solutions.
KW - Robotics in agriculture and forestry
KW - deep learning in robotics and automation
KW - mapping
KW - object detection
KW - segmentation and categorization
KW - visual tracking
UR - http://www.scopus.com/inward/record.url?scp=85063575627&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85063575627&partnerID=8YFLogxK
U2 - 10.1109/LRA.2019.2901987
DO - 10.1109/LRA.2019.2901987
M3 - Article
AN - SCOPUS:85063575627
SN - 2377-3766
VL - 4
SP - 2296
EP - 2303
JO - IEEE Robotics and Automation Letters
JF - IEEE Robotics and Automation Letters
IS - 3
M1 - 8653965
ER -