FIGURE 13 - available via license: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Content may be subject to copyright.
Confusion matrix diagrams under the two models, (a) Confusion matrix diagram of VFNet model; (b) Confusion matrix diagram of SAFFPest model.
Source publication
To address the problem that existing deep learning methods are not sufficiently accurate to detect rice pests with changeable shapes or similar appearances, a self-attention feature fusion model for rice pest detection (SAFFPest) was proposed. The model was based on VarifocalNet. First, a deformable convolution module was added to the feature extra...
Similar publications
Object detection on very high resolution (VHR) remote sensing images is a crucial task that has seen remarkable progress in developing deep learning techniques. However, deep learning-based methods rely heavily on the quality and quantity of labeled data. Although few-shot object detection (FSOD) can mitigate this dependency, existing methods still...
![Fig. 6. Some sample images from the VisDrone dataset [11].](publication/375215647/figure/fig4/AS:11431281202642492@1698936421981/Some-sample-images-from-the-VisDrone-dataset-11_Q320.jpg)
In this paper we revisit the efficacy of knowledge distillation as a function matching and metric learning problem. In doing so we verify three important design decisions, namely the normalisation, soft maximum function, and projection layers as key ingredients. We theoretically show that the projector implicitly encodes information on past example...
Citations
... The model consists of eleven trainable layers, achieving 100% accuracy in 10 classes of pests. Li et al. [10] proposed the SAFFPest that implements a deformable convolution to detect pests in rice plants. Nanni et al. [11] developed approaches based on CNNs for pest identification. ...
Pest control is essential for agricultural success, and rapid and accurate pest identification through computer vision and machine learning enables effective pest management. This paper proposes an approach to evaluate nine customizations of the IP102 dataset. Considering the extensive range of sub-datasets, a comparative analysis was conducted between different deep learning models, including ResNet and AlexNet Convolutional Neural Networks (CNNs), and Vision Transform (ViT). We carried out tests considering training from scratch and fine-tuning. Our experimental results demonstrate that ViT outperforms CNN models for the problem investigated and benefits significantly from data augmentation strategies. Our study provides valuable insights for efficient pest classification, paving the way for future research and advancements in precision agriculture.
... Zhang et al. (2022) realized the detection and recognition of maize pests based on the YOLOv4 model by integrating multi-scale ideas. Li et al. (2022) proposed SAFFPest, a self-attention feature fusion model inspired by VarifocalNet, which can be well applied to the recognition of rice pests. Couliably et al. (2022) built an interpretable deep convolutional neural network, which can be applied to pest recognition and detection. ...
Tomato crop yield can be negatively impacted by various diseases and pests. The application of computer vision to diagnose tomato diseases and pests presents two significant challenges. Firstly, the collected dataset of tomato pests and diseases is often imbalanced, leading to poor model performance. Secondly, mainstream models struggle to balance the relationship between training efficiency and accuracy. In this paper, we propose a novel method for diagnosing tomato pests and diseases using a lightweight network. Specifically, we develop Squeeze and SE Net (SSNet), a new convolutional neural network (CNN) based on SqueezeNet and SENet. We evaluate the performance of SSNet through comparative experiments for diagnosing tomato pests and diseases. Additionally, we examine the impact of dataset balance, data volume, and hyperparameters on model performance. Our results demonstrate that SSNet achieves model accuracies of 98.80% and 98.39% for tomato pests and diseases, respectively, with only 0.398 M parameters. This approach provides a promising and lightweight alternative to existing models.
In this work, we perform a systematic literature review of Open Data and Public Domain datasets in Agriculture. We use the PRISMA method to analyze the existing academic literature about open data in agriculture, concretely 1401 papers from the IEEE Xplore and Web of Science collections, published from 2012 to 2022. Many of these articles use or make available datasets of very different typologies, like sensor data, statistical data or satellite images, among others kinds. Some papers talk about different relevant topics that influence the use of open data, like the lack of open data for research purposes, barriers to adopting or sharing data, privacy concerns, data-sharing recommendations and guidelines. In addition, with the help of a script created ad-hoc for this research work, we analyze the degree of compliance within the FAIR principles of all the public domain or open datasets that we have been able to identify from the literature, concretely 104 datasets. The script can check the compliance of Gen2 maturity indicators of a list of resources. Using these metrics, we have been able to identify those open datasets that might be at risk of stopping to be available and started a “rescue operation”. For those datasets whose terms permitted it, we migrated those Open Data datasets to Zenodo, a repository that complies with the availability principles. This will ensure the future survival of valuable data in Agriculture.
The agricultural industry has enormous potential to meet the world's growing need for nutritious and healthful food. However, pests destroy a significant portion of the harvest and reduce quality; thus, farmers struggle to discover pests on their farms. Traditional pest identification methods require scientists with extensive field experience correctly identify pests based on their physical characteristics. Pesticides harm food and agriculture. IoT technology uses many affordable sensor devices to collect real-time data on pest-related agricultural development characteristics. The research paper aims to develop an AI-enabled real-time, IoT-based automatic pest detection system using sound pest analytics and IoT networks in the sizeable agricultural field. The proposed method used audio pre-processing techniques in sound analytics such as HPF, Hann window, hop window, FFT, DFT, STFT, and MFCC algorithm for denoising the pest sound, removing the spectral leakage, converting overlapping to non-overlapping frames, converting the time to the frequency domain, determining frequency spectrum, detecting sinusoidal frequency and internal component, extracting the MFCCs feature respectively. The characteristics and other statistical metrics were collected from 500 pest sounds and trained, validated, and evaluated using the CNN, LSTM, Bi-LSTM, and CNN-Bi-LSTM network models. The extracting features and different statistical measurements were compared during the testing process. The proposed system integrated the CNN and Bi-LSTM techniques called CNN-Bi-LSTM model for training, validating, and testing. From the experimental results, it has been observed that, the proposed CNN-Bi-LSTM model achieved 98.91 % accuracy, 96.8 % sensitivity, 97.96 % specificity, 98.54 % recall, 98.63 % precision, and 98.58 % F1 score, which is better compared to CNN, LSTM, Bi-LSTM and also existing ANN, DCNN, and VGG-16 state-of-the-art techniques.
Accurate and fast pest detection is crucial for ensuring high crop yield and quality in modern agriculture. However, there are significant challenges in using deep learning for pest detection, such as the small proportion of pest individuals in the image area, complex backgrounds in light-trapped pest images, and an unbalanced distribution of pest species. To address these problems, we propose MFSPest, a multi-scale feature selection network for detecting agricultural pests in trapping scenes. We design a novel selective kernel spatial pyramid pooling structure (SKSPP) in the feature extraction stage to enhance the network’s feature extraction ability for key regions and reduce its focus on irrelevant background information. Furthermore, we present the equalized loss to increase the loss weights of rare categories and improve the distribution imbalance among pest categories. Finally, we build LAPD, a light-trapping agricultural pest dataset containing nine pest categories. We conducted experiments on this dataset and demonstrated that our proposed method achieves state-of-the-art performance, with Accuracy, Recall, and mean Average Precision (mAP) of 89.9%, 92.8%, and 93.6%, respectively. Our method satisfies the requirements of pest detection applications in practical scenarios and has practical value and economic benefits for use in agricultural pest trapping and management.
