Detecting volunteer cotton plants in a corn field with deep learning on UAV remote-sensing imagery

Authors: YADAV, PAPPU - Texas A&M University; THOMASSON, J - Mississippi State University; HARDIN, ROBERT - Texas A&M University; SEARCY, STEPHEN - Texas A&M University; BRAGA-NETO, ULISSES - Texas A&M University; POPESCU, SORIN - Texas A&M University; Martin, Daniel - Dan; RODRIGUEZ, ROBERTO - Animal And Plant Health Inspection Service (APHIS); MEZA, KAREM - Utah State University; ENCISCO, JUAN - Texas A&M University; DIAZ, JORGE - Texas A&M University; WANG, TIANYI - Texas A&M University

Submitted to: Computers in Agriculture
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 12/3/2022
Publication Date: 12/15/2022
Citation: Yadav, P.K., Thomasson, J.A., Hardin, R., Searcy, S.W., Braga-Neto, U., Popescu, S.C., Martin, D.E., Rodriguez, R., Meza, K., Encisco, J., Diaz, J.S., Wang, T. 2022. Detecting volunteer cotton plants in a corn field with deep learning on UAV remote-sensing imagery. Computers in Agriculture. https://doi.org/10.1016/j.compag.2022.107551.
DOI: https://doi.org/10.1016/j.compag.2022.107551

Interpretive Summary: The cotton boll weevil is a serious pest to the U.S. cotton industry that has cost more than 16 billion USD in damages since it entered the United States from Mexico in the late 1800s. ARS scientists, in collaboration with Texas A&M University, used aerial photos at three different spatial resolutions to detect volunteer cotton plants in corn fields. Results showed that the images with the lowest resolution detected volunteer cotton plants with the same level of success as with the use of higher resolution images. The capture and use of lower resolution imagery provides for quicker image acquisition and processing times at reduced costs improving the efficiency and effectiveness of boll weevil control in the U.S.

Technical Abstract: The cotton boll weevil, Anthonomus grandis Boheman is a serious pest to the U.S. cotton industry that has cost more than 16 billion USD in damages since it entered the United States from Mexico in the late 1800s. This pest has been nearly eradicated; however, southern part of Texas still faces this issue and is always prone to the pest reinfestation each year due to its sub-tropical climate where cotton plants can grow year-round. Feral or volunteer cotton (VC) plants growing in the fields of inter-seasonal crops, like corn during the winter, can serve as hosts to these pests once they reach pin-head square stage (5-6 leaf stage) and therefore need to be detected, located, and destroyed or sprayed . In this paper, we present a study to detect VC plants in a corn field using YOLOv3 convolution neural network (CNN) on three band aerial images collected by unmanned aircraft system (UAS). The two-fold objectives of this paper were : (i) to determine whether YOLOv3 can be used for VC detection in a corn field using RGB (red, green, and blue) aerial images collected by UAS and (ii) to investigate the behavior of YOLOv3 on images at three different scales (320 x 320, S1; 416 x 416, S2; and 512 x 512, S3 pixels) based on average precision (AP), mean average precision (mAP) and F1-score at 95% confidence level. No significant differences existed for mAP among the three scales, while a significant difference was found for AP between S1 and S3 (p = 0.04) and S2 and S3 (p = 0.02). A significant difference was also found for F1-score between S2 and S3 (p = 0.02). The overall goal of this study was to minimize the boll weevil pest infestation by maximizing the true positive detection of VC plants in a corn field which is represented by the mAP values. The lack of significant differences of these at all the three scales indicated that the trained YOLOv3 model can be used on a computer vision-based remotely piloted aerial application system (RPAAS) for VC detection and spray application in near real-time. This has the potential to speed up the mitigation efforts for boll weevil pest control irrespective of the three input image sizes.