To address the real-time detection challenge of deploying deep learning-based tomato leaf disease detection algorithms on embedded devices, an improved tomato leaf disease detection algorithm based on YOLOv8n is proposed in a recently published paper. This algorithm aims to achieve efficient, real-time detection of tomato leaf diseases while maintaining the model's lightweight requirements.
The algorithm incorporates the LMSM (Lightweight Multi-Scale Module) and ALSA (Attention Lightweight Subsampling Module) to improve the ability to extract lightweight and multi-scale semantic information. These innovations cater specifically to the unique characteristics of tomato leaf disease, which include irregular spot size and lush tomato leaves.
Furthermore, the head network was redesigned utilizing partial and group convolution along with a parameter-sharing method. To further enhance performance, scalable auxiliary bounding box and loss function optimization strategies were introduced.
After undergoing the pruning technique, computation decreased by 61.7%, the model size decreased by 55.6%, and the FPS (Frames Per Second) increased by 44.8%, all while maintaining a high level of accuracy. A detection speed of 19.70FPS on the Jetson Nano was obtained after undergoing TensorRT quantization, showing a 64.85% improvement compared to the initial detection speed.
This method met the high real-time performance and small model size requirements for embedded tomato leaf disease detection systems, indirectly reducing the energy consumption of online detection. It provided an effective solution for the online detection of tomato leaf disease, demonstrating significant improvements in detection speed and efficiency while ensuring the system's applicability in real-world agricultural settings.
Read more at MDPI.