TY - JOUR
T1 - Improved crop row detection with deep neural network for early-season maize stand count in UAV imagery
AU - Pang, Yan
AU - Shi, Yeyin
AU - Gao, Shancheng
AU - Jiang, Feng
AU - Veeranampalayam-Sivakumar, Arun Narenthiran
AU - Thompson, Laura
AU - Luck, Joe
AU - Liu, Chao
N1 - Publisher Copyright:
© 2020 Elsevier B.V.
PY - 2020/11
Y1 - 2020/11
N2 - Stand counts is one of the most common ways farmers assess plant growth conditions and management practices throughout the season. The conventional method for early-season stand count is through manual inspection, which is time-consuming, laborious, and spatially limited in scope. In recent years, Unmanned Aerial Vehicles (UAV) based remote sensing has been widely used in agriculture to provide low-altitude, high spatial resolution imagery to assist decision making. In this project, we designed a system that uses geometric descriptor information with deep neural networks to determine early-season maize stands from relatively low spatial resolution (10 to 25 mm) aerial data, which covers a relatively large area (10 to 25 hectares). Instead of detecting individual crops in a row, we process the entire row at one time, which significantly reduces the requirements for the clarity of the crops. Besides, our new MaxArea Mask Scoring RCNN algorithm could segment crop-rows out in each patch image, regardless of the terrain conditions. The robustness of our scheme was tested on data collected at two different fields in different years. The accuracy of the estimated emergence rate reached up to 95.8%. Due to the high processing speed of the system, it has the potential for real-time applications in the future.
AB - Stand counts is one of the most common ways farmers assess plant growth conditions and management practices throughout the season. The conventional method for early-season stand count is through manual inspection, which is time-consuming, laborious, and spatially limited in scope. In recent years, Unmanned Aerial Vehicles (UAV) based remote sensing has been widely used in agriculture to provide low-altitude, high spatial resolution imagery to assist decision making. In this project, we designed a system that uses geometric descriptor information with deep neural networks to determine early-season maize stands from relatively low spatial resolution (10 to 25 mm) aerial data, which covers a relatively large area (10 to 25 hectares). Instead of detecting individual crops in a row, we process the entire row at one time, which significantly reduces the requirements for the clarity of the crops. Besides, our new MaxArea Mask Scoring RCNN algorithm could segment crop-rows out in each patch image, regardless of the terrain conditions. The robustness of our scheme was tested on data collected at two different fields in different years. The accuracy of the estimated emergence rate reached up to 95.8%. Due to the high processing speed of the system, it has the potential for real-time applications in the future.
KW - Deep learning
KW - Plant population
KW - RCNN
KW - Remote sensing
KW - UAS
UR - http://www.scopus.com/inward/record.url?scp=85090410202&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85090410202&partnerID=8YFLogxK
U2 - 10.1016/j.compag.2020.105766
DO - 10.1016/j.compag.2020.105766
M3 - Article
AN - SCOPUS:85090410202
VL - 178
JO - Computers and Electronics in Agriculture
JF - Computers and Electronics in Agriculture
SN - 0168-1699
M1 - 105766
ER -