Deep Regression versus Detection for Counting in Robotic Phenotyping

Salazar Gomez, Adrian, Aptoula, E, Parsons, Simon and Bosilj, Simon (2021) Deep Regression versus Detection for Counting in Robotic Phenotyping. IEEE Robotics and Automation Letters, 6 (2). pp. 2902-2907. ISSN 2377-3766

Full content URL: https://doi.org/10.1109/LRA.2021.3062586

Documents
Deep Regression versus Detection for Counting in Robotic Phenotyping
Accepted Manuscript
[img]
[Download]
[img]
Preview
PDF
ALiCAT_RAL.pdf - Whole Document

1MB
Item Type:Article
Item Status:Live Archive

Abstract

Work in robotic phenotyping requires computer vision methods that estimate the number of fruit or grains in an image. To decide what to use, we compared three methods for counting fruit and grains, each method representative of a class of approaches from the literature. These are two methods based on density estimation and regression (single and multiple column), and one method based on object detection. We found that when the density of objects in an image is low, the approaches are comparable, but as the density increases, counting by regression becomes steadily more accurate than counting by detection. With more than a hundred objects per image, the error in the count predicted by detection-based methods is up to 5 times higher than when using regression-based ones.

Keywords:Computer vision, Agriculture, Plant phenotyping
Subjects:G Mathematical and Computer Sciences > G740 Computer Vision
Divisions:College of Science > School of Computer Science
ID Code:44001
Deposited On:26 Feb 2021 09:51

Repository Staff Only: item control page