Plant Counting of Cotton from UAS Imagery Using Deep Learning-Based Object Detection Framework

• Published in: Remote sensing (Basel, Switzerland) Vol. 12; no. 18; p. 2981
• Main Authors: Oh, Sungchan, Chang, Anjin, Ashapure, Akash, Jung, Jinha, Dube, Nothabo, Maeda, Murilo, Gonzalez, Daniel, Landivar, Juan
• Format: Journal Article
• Language: English
• Published: MDPI AG 01.09.2020
• Subjects: agriculture; algorithms; automation; canopy; China; cotton; data collection; detection; geometry; information; labor; lighting; measurement; photogrammetry; plant count; plant population assessment; planting; population; remote sensing; seedlings; unmanned aerial vehicles; unmanned aircraft systems; variability; China
• DOI: 10.3390/rs12182981
• ISSN: 2072-4292

Assessing plant population of cotton is important to make replanting decisions in low plant density areas, prone to yielding penalties. Since the measurement of plant population in the field is labor intensive and subject to error, in this study, a new approach of image-based plant counting is proposed, using unmanned aircraft systems (UAS; DJI Mavic 2 Pro, Shenzhen, China) data. The previously developed image-based techniques required a priori information of geometry or statistical characteristics of plant canopy features, while also limiting the versatility of the methods in variable field conditions. In this regard, a deep learning-based plant counting algorithm was proposed to reduce the number of input variables, and to remove requirements for acquiring geometric or statistical information. The object detection model named You Only Look Once version 3 (YOLOv3) and photogrammetry were utilized to separate, locate, and count cotton plants in the seedling stage. The proposed algorithm was tested with four different UAS datasets, containing variability in plant size, overall illumination, and background brightness. Root mean square error (RMSE) and R2 values of the optimal plant count results ranged from 0.50 to 0.60 plants per linear meter of row (number of plants within 1 m distance along the planting row direction) and 0.96 to 0.97, respectively. The object detection algorithm, trained with variable plant size, ground wetness, and lighting conditions generally resulted in a lower detection error, unless an observable difference of developmental stages of cotton existed. The proposed plant counting algorithm performed well with 0–14 plants per linear meter of row, when cotton plants are generally separable in the seedling stage. This study is expected to provide an automated methodology for in situ evaluation of plant emergence using UAS data.