The identification of tomato leaf diseases is easily affected by complex backgrounds, small differences between different diseases, and large differences between the same diseases. Therefore, we propose a novel classification network for tomato leaf disease, the Dense Inception MobileNet-V2 parallel convolutional block attention module network (DIMPCNET). To begin, we collected a total of 1256 original images of 5 tomato leaf diseases and expanded them to 8190 using data enhancement techniques. Next, an improved bilateral filtering and threshold function (IBFTF) algorithm is designed to effectively remove noise. Then, the Dense Inception convolutional neural network module (DI) was designed to alleviate the problem of large intra-class differences and small inter-class differences. Then, a parallel convolutional block attention module (PCBAM) was added to MobileNet-V2 to reduce the impact of complex backgrounds. Finally, the experimental results show that the recognition accuracy and F1-score obtained by DIMPCNET are 94.44% and 0.9475. The loss is approximately 0.28%. This method is the most advanced and provides a new idea for the identification of crop diseases, such as tomatoes, and the development of smart agriculture.
Apple leaf diseases are one of the most important factors that reduce apple quality and yield. The object detection technology based on deep learning can detect diseases in a timely manner and help automate disease control, thereby reducing economic losses. In the natural environment, tiny apple leaf disease targets (a resolution is less than 32 × 32 pixel2) are easily overlooked. To address the problems of complex background interference, difficult detection of tiny targets and biased detection of prediction boxes that exist in standard detectors, in this paper, we constructed a tiny target dataset TTALDD-4 containing four types of diseases, which include Alternaria leaf spot, Frogeye leaf spot, Grey spot and Rust, and proposed the HSSNet detector based on the YOLOv7-tiny benchmark for professional detection of apple leaf disease tiny targets. Firstly, the H-SimAM attention mechanism is proposed to focus on the foreground lesions in the complex background of the image. Secondly, SP-BiFormer Block is proposed to enhance the ability of the model to perceive tiny targets of leaf diseases. Finally, we use the SIOU loss to improve the case of prediction box bias. The experimental results show that HSSNet achieves 85.04% mAP (mean average precision), 67.53% AR (average recall), and 83 FPS (frames per second). Compared with other standard detectors, HSSNet maintains high real-time detection speed with higher detection accuracy. This provides a reference for the automated control of apple leaf diseases.
This paper investigates the application of the YOLOv7 object detection model combined with knowledge distillation techniques in forest fire detection. As an advanced object detection model, YOLOv7 boasts efficient real-time detection capabilities. However, its performance may be constrained in resource-limited environments. To address this challenge, this research proposes a novel approach: considering that deep neural networks undergo multi-layer mapping from the input to the output space, we define the knowledge propagation between layers by evaluating the dot product of features extracted from two different layers. To this end, we utilize the Flow of Solution Procedure (FSP) matrix based on the Gram matrix and redesign the distillation loss using the Pearson correlation coefficient, presenting a new knowledge distillation method termed ILKDG (Intermediate Layer Knowledge Distillation with Gram Matrix-based Feature Flow). Compared with the classical knowledge distillation algorithm, KD, ILKDG achieved a significant performance improvement on a self-created forest fire detection dataset. Specifically, without altering the student network’s parameters or network layers, mAP@0.5 improved by 2.9%, and mAP@0.5:0.95 increased by 2.7%. These results indicate that the proposed ILKDG method effectively enhances the accuracy and performance of forest fire detection without introducing additional parameters. The ILKDG method, based on the Gram matrix and Pearson correlation coefficient, presents a novel knowledge distillation approach, providing a fresh avenue for future research. Researchers can further optimize and refine this method to achieve superior results in fire detection.
In recent years, the production of China’s four major crops has declined due to pests and diseases. This situation poses a serious challenge to food security. Therefore, timely detection and prevention of diseases is essential. First, we apply data enhancement techniques to augment the data to improve the generalization ability of the model. Secondly, to reduce the model parameters and make it easier to deploy on end devices, we use the knowledge distillation method. Finally, a method of dynamically adjusting the parameter T according to the loss value (DYTKD) is proposed to improve the performance of the model further. The experiment shows that knowledge distillation can reduce the number of parameters while ensuring that the accuracy of the student model closely matches that of the teacher model, achieving 98.94% accuracy Meanwhile, data augmentation can also enhance the accuracy of the model by 6.83%. Compared with the basic knowledge distillation method, the accuracy of DYTKD was increased by 1.3% without altering the student network and other parameters, and the accuracy of pest identification and classification was effectively improved. Among 1342 pest pictures, 1221 were correctly identified and accurately classified. Our codes are available at https://github.com/wln130221/DYTKD.