Search

Wheat ear counting is crucial for calculating wheat phenotypic parameters and scientifically managing fields, which is essential for estimating wheat field yield. In wheat fields, detecting wheat ears can be challenging due to factors such as changes in illumination, wheat ear growth posture, and the appearance color of wheat ears. To improve the accuracy and efficiency of wheat ear detection and meet the demands of intelligent yield estimation, this study proposes an efficient model, Generalized Focal Loss WheatNet (GFLWheatNet), for wheat ear detection. This model precisely counts small, dense, and overlapping wheat ears. Firstly, in the feature extraction stage, we discarded the C4 feature layer of the ResNet50 and added the Convolutional block attention module (CBAM) to this location. This step maintains strong feature extraction capabilities while reducing redundant feature information. Secondly, in the reinforcement layer, we designed a skip connection module to replace the multi-scale feature fusion network, expanding the receptive field to adapt to various scales of wheat ears. Thirdly, leveraging the concept of distribution-guided localization, we constructed a detection head network to address the challenge of low accuracy in detecting dense and overlapping targets. Validation on the publicly available Global Wheat Head Detection dataset (GWHD-2021) demonstrates that GFLWheatNet achieves detection accuracies of 43.3% and 93.7% in terms of mean Average Precision (mAP) and A P 50 (Intersection over Union (IOU) = 0.5), respectively. Compared to other models, it exhibits strong performance in terms of detection accuracy and efficiency. This model can serve as a reference for intelligent wheat ear counting during wheat yield estimation and provide theoretical insights for the detection of ears in other grain crops. [ABSTRACT FROM AUTHOR]

Winter jujube is a popular fresh fruit in China for its high vitamin C nutritional value and delicious taste. In terms of winter jujube object detection, in machine learning research, small size jujube fruits could not be detected with a high accuracy. Moreover, in deep learning research, due to the large model size of the network and slow detection speed, deployment in embedded devices is limited. In this study, an improved Yolov5s (You Only Look Once version 5 small model) algorithm was proposed in order to achieve quick and precise detection. In the improved Yolov5s algorithm, we decreased the model size and network parameters by reducing the backbone network size of Yolov5s to improve the detection speed. Yolov5s's neck was replaced with slim-neck, which uses Ghost-Shuffle Convolution (GSConv) and one-time aggregation cross stage partial network module (VoV-GSCSP) to lessen computational and network complexity while maintaining adequate accuracy. Finally, knowledge distillation was used to optimize the improved Yolov5s model to increase generalization and boost overall performance. Experimental results showed that the accuracy of the optimized Yolov5s model outperformed Yolov5s in terms of occlusion and small target fruit discrimination, as well as overall performance. Compared to Yolov5s, the Precision, Recall, mAP (mean average Precision), and F1 values of the optimized Yolov5s model were increased by 4.70%, 1.30%, 1.90%, and 2.90%, respectively. The Model size and Parameters were both reduced significantly by 86.09% and 88.77%, respectively. The experiment results prove that the model that was optimized from Yolov5s can provide a real time and high accuracy small winter jujube fruit detection method for robot harvesting. [ABSTRACT FROM AUTHOR]

• The 3 σ criterion is used to remove gross errors and improve prediction accuracy. • Stratified sampling is used to eliminate the influence of data structure. • A DCNN without pooling layers is constructed to avoid information loss. • A method for RUL prediction improves the prediction accuracy and generalization. With the purpose of improving the prediction accuracy and generalization ability of remaining useful life (RUL) prediction models, this paper proposes a new method to predict the RUL of bearings based on the convolutional neural network (CNN). First, the 3 sigma criterion is applied to denoise the original data and remove gross errors. Subsequently, the frequency features are obtained from the original data by the fast Fourier transform (FFT), and the root mean square is employed as the tracking metric. Then, stratified sampling, which differs from the traditional time series data partitioning method, is applied to data partitioning to completely learn the data features. A deep convolutional neural network (DCNN) model without a pooling layer, which consists of three convolutional layers and two fully connected layers, is constructed to avoid feature loss. Finally, the NASA IMS dataset is utilized to assess the preprocessing method, DCNN accuracy and generalization ability. The experimental results show the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Using intelligent agricultural machines in paddy fields has received great attention. An obstacle avoidance system is required with the development of agricultural machines. In order to make the machines more intelligent, detecting and tracking obstacles, especially the moving obstacles in paddy fields, is the basis of obstacle avoidance. To achieve this goal, a red, green and blue (RGB) camera and a computer were used to build a machine vision system, mounted on a transplanter. A method that combined the improved You Only Look Once version 3 (Yolov3) and deep Simple Online and Realtime Tracking (deep SORT) was used to detect and track typical moving obstacles, and figure out the center point positions of the obstacles in paddy fields. The improved Yolov3 has 23 residual blocks and upsamples only once, and has new loss calculation functions. Results showed that the improved Yolov3 obtained mean intersection over union (mIoU) score of 0.779 and was 27.3% faster in processing speed than standard Yolov3 on a self-created test dataset of moving obstacles (human and water buffalo) in paddy fields. An acceptable performance for detecting and tracking could be obtained in a real paddy field test with an average processing speed of 5–7 frames per second (FPS), which satisfies actual work demands. In future research, the proposed system could support the intelligent agriculture machines more flexible in autonomous navigation. [ABSTRACT FROM AUTHOR]

• Combining CNN and Transformer to overcome their limitations in wheat ear detection task. • Introducing a dual-branch Feature Processing Module to fuse multi-scale features. • Proposing Multi-Branch Self-Attention module captures local dependencies and global features. • Quad Attention is used to reduce self-attention's computational cost, enhancing model efficiency. Wheat ear detection is an indispensable step in wheat field yield estimation and is crucial for achieving scientific field management. However, wheat ears in the field vary in shape, frequent overlap, and are susceptible to illumination variations, posing significant challenges for wheat ear detection tasks. To meet the requirements of field yield estimation and improve wheat ear detection accuracy, this paper proposes the CTWheatNet model, which integrates CNN and Transformer to overcome their respective limitations in wheat ear detection tasks and achieve precise detection of wheat ears in the field. Firstly, a CNN feature extraction module is proposed to obtain multi-scale wheat ear features, avoiding the loss of wheat ear edge information caused by patch cutting. The Feature Processing Module is designed with a dual-branch structure to interactively fuse multi-scale features. Secondly, the output of the CNN feature extraction module is inputted into the Transformer feature extraction module to capture global wheat ear features. The Multi-Branch Self-Attention module of the dual-branch attention mechanism simultaneously focuses on low/high-resolution features to obtain both local dependencies and global features. The Quad Attention is proposed to reduce the computational cost of the self-attention module and improve the model's applicability. Finally, the proposed model is validated on the public wheat ear dataset (GWHD-2021). The experimental results show that CTWheatNet achieves a detection accuracy of 52.7% AP and 93.0% A P 50. Compared with other advanced models, CTWheatNet also performs well. This model can provide technical support and theoretical reference for intelligent counting in the process of wheat field yield estimation and detection of other cereal crops. [ABSTRACT FROM AUTHOR]