Next Article in Journal
Extracting Information on Rocky Desertification from Satellite Images: A Comparative Study
Previous Article in Journal
A Fused Radar–Optical Approach for Mapping Wetlands and Deepwaters of the Mid–Atlantic and Gulf Coast Regions of the United States
Previous Article in Special Issue
Novel 3D Imaging Systems for High-Throughput Phenotyping of Plants
Article

Parts-per-Object Count in Agricultural Images: Solving Phenotyping Problems via a Single Deep Neural Network

Department of Industrial Engineering and Management, Faculty of Engineering Sciences, Ben-Gurion University of the Negev, Beer-Sheva P.O. Box 653, Israel
*
Author to whom correspondence should be addressed.
Academic Editor: Sergii Skakun
Remote Sens. 2021, 13(13), 2496; https://0-doi-org.brum.beds.ac.uk/10.3390/rs13132496
Received: 10 March 2021 / Revised: 7 June 2021 / Accepted: 16 June 2021 / Published: 26 June 2021
Solving many phenotyping problems involves not only automatic detection of objects in an image, but also counting the number of parts per object. We propose a solution in the form of a single deep network, tested for three agricultural datasets pertaining to bananas-per-bunch, spikelets-per-wheat-spike, and berries-per-grape-cluster. The suggested network incorporates object detection, object resizing, and part counting as modules in a single deep network, with several variants tested. The detection module is based on a Retina-Net architecture, whereas for the counting modules, two different architectures are examined: the first based on direct regression of the predicted count, and the other on explicit parts detection and counting. The results are promising, with the mean relative deviation between estimated and visible part count in the range of 9.2% to 11.5%. Further inference of count-based yield related statistics is considered. For banana bunches, the actual banana count (including occluded bananas) is inferred from the count of visible bananas. For spikelets-per-wheat-spike, robust estimation methods are employed to get the average spikelet count across the field, which is an effective yield estimator. View Full-Text
Keywords: phenotyping problems; deep learning; parts-per-object count; object detection; robust estimation phenotyping problems; deep learning; parts-per-object count; object detection; robust estimation
Show Figures

Graphical abstract

MDPI and ACS Style

Khoroshevsky, F.; Khoroshevsky, S.; Bar-Hillel, A. Parts-per-Object Count in Agricultural Images: Solving Phenotyping Problems via a Single Deep Neural Network. Remote Sens. 2021, 13, 2496. https://0-doi-org.brum.beds.ac.uk/10.3390/rs13132496

AMA Style

Khoroshevsky F, Khoroshevsky S, Bar-Hillel A. Parts-per-Object Count in Agricultural Images: Solving Phenotyping Problems via a Single Deep Neural Network. Remote Sensing. 2021; 13(13):2496. https://0-doi-org.brum.beds.ac.uk/10.3390/rs13132496

Chicago/Turabian Style

Khoroshevsky, Faina, Stanislav Khoroshevsky, and Aharon Bar-Hillel. 2021. "Parts-per-Object Count in Agricultural Images: Solving Phenotyping Problems via a Single Deep Neural Network" Remote Sensing 13, no. 13: 2496. https://0-doi-org.brum.beds.ac.uk/10.3390/rs13132496

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop