Rapid Detection and Counting of Wheat Ears in the Field Using YOLOv4 with Attention Module

Abstract

The detection and counting of wheat ears are very important for crop field management, yield estimation, and phenotypic analysis. Previous studies have shown that most methods for detecting wheat ears were based on shallow features such as color and texture extracted by machine learning methods, which have obtained good results. However, due to the lack of robustness of these features, it was difficult for the above-mentioned methods to meet the detection and counting of wheat ears in natural scenes. Other studies have shown that convolutional neural network (CNN) methods could be used to achieve wheat ear detection and counting. However, the adhesion and occlusion of wheat ears limit the accuracy of detection. Therefore, to improve the accuracy of wheat ear detection and counting in the field, an improved YOLOv4 (you only look once v4) with CBAM (convolutional block attention module) including spatial and channel attention model was proposed that could enhance the feature extraction capabilities of the network by adding receptive field modules. In addition, to improve the generalization ability of the model, not only local wheat data (WD), but also two public data sets (WEDD and GWHDD) were used to construct the training set, the validation set, and the test set. The results showed that the model could effectively overcome the noise in the field environment and realize accurate detection and counting of wheat ears with different density distributions. The average accuracy of wheat ear detection was 94%, 96.04%, and 93.11%. Moreover, the wheat ears were counted on 60 wheat images. The results showed that R2 = 0.8968 for WD, 0.955 for WEDD, and 0.9884 for GWHDD. In short, the CBAM-YOLOv4 model could meet the actual requirements of wheat ear detection and counting, which provided technical support for other high-throughput parameters of the extraction of crops.

Lightweight and efficient neural network with SPSA attention for wheat ear detection

“…Relevant studies are successful in applying deep learning models in wheat ear detection. Based on the image processing and deep learning technology, the EfficientDet algorithm ( Tan, Pang & Le, 2020 ) was used to detect the wheat ear image by Cao et al (2020) , the final accuracy rate reached 92.92% and the test time of the single sheet was 0.2 s. An improved YOLOv4 with CBAM (convolutional block attention module) ( Woo et al, 2018 ) including spatial and channel attention model was proposed by Yang et al (2021) . This strategy could enhance the feature extraction capabilities of the network by adding receptive field modules.…”

“… Xu et al (2020) used the K-means clustering method for automatic segmentation of wheat ear images and sent the segmented image tags to the convolutional neural network model for training and testing. Although much progress ( Cao et al, 2020 ; Yang et al, 2021 ; Xu et al, 2020 ) has been made, there are still problems such as low efficiency, insufficient robustness, and poor performance. Simultaneously, the above-mentioned deep learning-based detection methods often need to sacrifice accuracy to ensure the inference speed of the detector because of the limitation of hardware in practice.…”

Identification and Classification of Mechanical Damage During Continuous Harvesting of Root Crops Using Computer Vision Methods

“…In our opinion, such adaptive systems have a serious drawback, they cannot be customized to the individual characteristics of each root crop. In digital agriculture [10,11], computer vision systems are used to quickly detect and count plants [12][13][14][15], to determine their ripeness and diseases [16][17][18][19][20], as part of systems to protect against weeds and pests [21,22], to determine the position of cattle [23]. In recent years publications have shown that the problem of identifying diseased or mechanically damaged fetuses on transportation systems such as conveyor belts, drums, turbines and etc.…”

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

“… Sadeghi-Tehran et al (2019) constructed wheat feature models and fed the models into convolutional neural networks to achieve semantic segmentation and automatic counting of wheat. In addition, TasselNetv2 ( Xiong et al, 2019 ), mobileNetV2 ( Khaki et al, 2021 ), YOLOV4 ( Yang et al, 2021 ), EfficientDet ( Wang et al, 2021 ), LPNet ( Misra et al, 2020 ), and other deep-learning networks have shown advantages in wheat counting.…”