Rapid Detection of Wheat Ears in Orthophotos From Unmanned Aerial Vehicles in Fields Based on YOLOX

Abstract

Wheat ears in unmanned aerial vehicles (UAV) orthophotos are characterized by occlusion, small targets, dense distribution, and complex backgrounds. Rapid identification of wheat ears in UAV orthophotos in a field environment is critical for wheat yield prediction. Three improvements were achieved based on YOLOX-m: mosaic optimized, using BiFPN structure, and attention mechanism, then ablation experiments were performed to verify the effect of each improvement. Three scene datasets were established: images were acquired during three different growing periods, at three planting densities, and under three scenarios of UAV flight heights. In ablation experiments, three improvements had increased recognition accuracies on the experimental dataset. Compared the accuracy of the standard model with our improved model on three scene datasets. Our improved model during three different periods, at three planting densities, and under three scenarios of the UAV flight height, obtaining 88.03%, 87.59%, and 87.93% accuracies, which were, respectively, 2.54%, 1.89%, and 2.15% better than the original model. The results of this study showed that the improved YOLOX-m model can achieve UAV orthophoto wheat recognition under different practical scenarios in large fields, and that the best combination were obtained images from the wheat milk stage, low planting density, and low flight altitude.

Winter wheat ear counting based on improved YOLOv7x and Kalman filter tracking algorithm with video streaming

“…In addition, the natural conditions of the field environment (light and wind speed) and the flight status of UAV (speed, altitude, and inclination) can also have an impact on wheat ear detection and counting ( Yao et al., 2022 ). Therefore, increasing training data and optimizing model structure are undertaken to gradually improve the performance and reliability of the model in practical applications.…”

Advancements in Utilizing Image-Analysis Technology for Crop-Yield Estimation

“…A prediction model was established by using DCNN and transfer learning, and a maximum R 2 of 0.84 was obtained, greatly improving the efficiency of wheat spike recognition. Zhaosheng et al [113] applied an improved YOLOXm object-detection algorithm to detect wheat ears and evaluated the prediction accuracy of datasets with different growth stages, planting densities, and drone-flight heights. The highest prediction accuracy obtained through the improved model reached 88.03%, an increase of 2.54% compared to the original.…”

A density map-based method for counting wheat ears

“…To address the problem of vanishing gradients during training ( Li and Wu, 2022 ) adding quadruple downsampling in YOLOv5 to improve the detection effect of small targets and adding the CBAM attention mechanism in the backbone network to solve the gradient disappearance problem during the training process, and the results show that, compared with the other methods, the model has a mAP of 94.3%, an accuracy of 88.5% and a recall of 98.1%, which is an obvious improvement. For rapid detection of wheat ( Zhaosheng et al., 2022 ) proposes a fast method for wheat ears orthophoto detection based on YOLOX algorithm for UAV aerial photography, which adds a channel attention mechanism in the backbone and necks a Bidirectional Convolutional Block Attention Module (BiFPN) structure, which uses learnable weights to learn the importance of different input features. Experimental results show that the method exhibits good accuracy and efficiency in the task of wheat sheaf detection in aerial wheat field images, providing a fast and feasible solution for wheat sheaf detection in aerial UAV wheat fields.…”