Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Counting Plants Using Deep Learning

Abstract: 

In this paper we address the task of counting crop plants in a field using CNNs. The number of plants in an Unmanned Aerial Vehicle (UAV) image of the field is estimated using regression instead of classification. This avoids to need to know (or guess) the maximum expected number of plants. We also describe a method to extract images of sections or "plots" from an orthorectified image of the entire crop field. These images will be used for training and evaluation of the CNN. Our experiments show that we can obtain a Mean Absolute Percentage Error as low as 6.7 % with the Inception-v3 CNN architecture.

up
0 users have voted:

Paper Details

Authors:
Yuhao Chen, Christopher Boomsma, Edward Delp
Submitted On:
19 November 2017 - 12:46pm
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Javier Ribera
Paper Code:
1065
Document Year:
2017
Cite

Document Files

counting_plants_using_deep_learning_globalsip2017

(40 downloads)

Subscribe

[1] Yuhao Chen, Christopher Boomsma, Edward Delp, "Counting Plants Using Deep Learning", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2364. Accessed: Dec. 17, 2017.
@article{2364-17,
url = {http://sigport.org/2364},
author = {Yuhao Chen; Christopher Boomsma; Edward Delp },
publisher = {IEEE SigPort},
title = {Counting Plants Using Deep Learning},
year = {2017} }
TY - EJOUR
T1 - Counting Plants Using Deep Learning
AU - Yuhao Chen; Christopher Boomsma; Edward Delp
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2364
ER -
Yuhao Chen, Christopher Boomsma, Edward Delp. (2017). Counting Plants Using Deep Learning. IEEE SigPort. http://sigport.org/2364
Yuhao Chen, Christopher Boomsma, Edward Delp, 2017. Counting Plants Using Deep Learning. Available at: http://sigport.org/2364.
Yuhao Chen, Christopher Boomsma, Edward Delp. (2017). "Counting Plants Using Deep Learning." Web.
1. Yuhao Chen, Christopher Boomsma, Edward Delp. Counting Plants Using Deep Learning [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2364