Cotton Stand Counting from Unmanned Aerial System Imagery Using MobileNet and CenterNet Deep Learning Models

Abstract

An accurate stand count is a prerequisite to determining the emergence rate, assessing seedling vigor, and facilitating site-specific management for optimal crop production. Traditional manual counting methods in stand assessment are labor intensive and time consuming for large-scale breeding programs or production field operations. This study aimed to apply two deep learning models, the MobileNet and CenterNet, to detect and count cotton plants at the seedling stage with unmanned aerial system (UAS) images. These models were trained with two datasets containing 400 and 900 images with variations in plant size and soil background brightness. The performance of these models was assessed with two testing datasets of different dimensions, testing dataset 1 with 300 by 400 pixels and testing dataset 2 with 250 by 1200 pixels. The model validation results showed that the mean average precision (mAP) and average recall (AR) were 79% and 73% for the CenterNet model, and 86% and 72% for the MobileNet model with 900 training images. The accuracy of cotton plant detection and counting was higher with testing dataset 1 for both CenterNet and MobileNet models. The results showed that the CenterNet model had a better overall performance for cotton plant detection and counting with 900 training images. The results also indicated that more training images are required when applying object detection models on images with different dimensions from training datasets. The mean absolute percentage error (MAPE), coefficient of determination (R2), and the root mean squared error (RMSE) values of the cotton plant counting were 0.07%, 0.98 and 0.37, respectively, with testing dataset 1 for the CenterNet model with 900 training images. Both MobileNet and CenterNet models have the potential to accurately and timely detect and count cotton plants based on high-resolution UAS images at the seedling stage. This study provides valuable information for selecting the right deep learning tools and the appropriate number of training images for object detection projects in agricultural applications.

Seeding Crop Detection Framework Using Prototypical Network Method in UAV Images

“…Our method has no limitations in terms of the input image size. The seedling cotton plants detected by Lin et al [30] can be multiscale, but our method is not yet able to detect multiscale objects. For multiscale detection, the proposed method needs to be improved continuously.…”

“…We use the SLIC method [15] in superpixel segmentation to segment an image for candidate region extraction and then use the prototypical network for a classification to help locate chilies. Lin et al [30] detected cotton plants from UAV images using deep learning models. General object detection networks based on deep learning are limited in terms of the input image size.…”

“…They used a comprehensive approach by combining a pixel-based CCL algorithm with morphological image operations to detect each plant individually using rectangles. Lin et al [30] used a deep learning model to detect and count cotton plants at a seedling stage using UAV images. The dimensions of the training images were 300 × 400 pixels.…”

An Adaptive Attention Fusion Mechanism Convolutional Network for Object Detection in Remote Sensing Images

“…He et al [33] managed to find the approximate locations and rough sizes of the sunspot groups on the solar full images based on Cornnet-Saccade. Liu et al [34] and Lin et al [35] achieved high accuracy with a real-time detection speed based on CenterNet.…”

Application of Mathematical Models to Assess the Impact of the COVID-19 Pandemic on Logistics Businesses and Recovery Solutions for Sustainable Development

“…To evaluate the quality and fit of the GM (1, 1) model used in this study, the authors used MAPE to calculate error. MAPE is calculated according to the following formula [28]:…”