View in EDS

Efficient Deployment of Peanut Leaf Disease Detection Models on Edge AI Devices

Saved in:
Bibliographic Details
Title: Efficient Deployment of Peanut Leaf Disease Detection Models on Edge AI Devices
Authors: Zekai Lv, Shangbin Yang, Shichuang Ma, Qiang Wang, Jinti Sun, Linlin Du, Jiaqi Han, Yufeng Guo, Hui Zhang
Source: Agriculture ; Volume 15 ; Issue 3 ; Pages: 332
Publisher Information: Multidisciplinary Digital Publishing Institute
Publication Year: 2025
Collection: MDPI Open Access Publishing
Subject Terms: YOLOX-Tiny, Jetson board, peanut leaf diseases, TensorRT, TensorFlow Lite, efficient deployment optimization
Subject Geographic: agris
Description: The intelligent transformation of crop leaf disease detection has driven the use of deep neural network algorithms to develop more accurate disease detection models. In resource-constrained environments, the deployment of crop leaf disease detection models on the cloud introduces challenges such as communication latency and privacy concerns. Edge AI devices offer lower communication latency and enhanced scalability. To achieve the efficient deployment of crop leaf disease detection models on edge AI devices, a dataset of 700 images depicting peanut leaf spot, scorch spot, and rust diseases was collected. The YOLOX-Tiny network was utilized to conduct deployment experiments with the peanut leaf disease detection model on the Jetson Nano B01. The experiments initially focused on three aspects of efficient deployment optimization: the fusion of rectified linear unit (ReLU) and convolution operations, the integration of Efficient Non-Maximum Suppression for TensorRT (EfficientNMS_TRT) to accelerate post-processing within the TensorRT model, and the conversion of model formats from number of samples, channels, height, width (NCHW) to number of samples, height, width, and channels (NHWC) in the TensorFlow Lite model. Additionally, experiments were conducted to compare the memory usage, power consumption, and inference latency between the two inference frameworks, as well as to evaluate the real-time video detection performance using DeepStream. The results demonstrate that the fusion of ReLU activation functions with convolution operations reduced the inference latency by 55.5% compared to the use of the Sigmoid linear unit (SiLU) activation alone. In the TensorRT model, the integration of the EfficientNMS_TRT module accelerated post-processing, leading to a reduction in the inference latency of 19.6% and an increase in the frames per second (FPS) of 20.4%. In the TensorFlow Lite model, conversion to the NHWC format decreased the model conversion time by 88.7% and reduced the inference latency by 32.3%. These three ...
Document Type: text
File Description: application/pdf
Language: English
Relation: Digital Agriculture; https://dx.doi.org/10.3390/agriculture15030332
DOI: 10.3390/agriculture15030332
Availability: https://doi.org/10.3390/agriculture15030332
Rights: https://creativecommons.org/licenses/by/4.0/
Accession Number: edsbas.29B6CF5E
Database: BASE
Description
Abstract:The intelligent transformation of crop leaf disease detection has driven the use of deep neural network algorithms to develop more accurate disease detection models. In resource-constrained environments, the deployment of crop leaf disease detection models on the cloud introduces challenges such as communication latency and privacy concerns. Edge AI devices offer lower communication latency and enhanced scalability. To achieve the efficient deployment of crop leaf disease detection models on edge AI devices, a dataset of 700 images depicting peanut leaf spot, scorch spot, and rust diseases was collected. The YOLOX-Tiny network was utilized to conduct deployment experiments with the peanut leaf disease detection model on the Jetson Nano B01. The experiments initially focused on three aspects of efficient deployment optimization: the fusion of rectified linear unit (ReLU) and convolution operations, the integration of Efficient Non-Maximum Suppression for TensorRT (EfficientNMS_TRT) to accelerate post-processing within the TensorRT model, and the conversion of model formats from number of samples, channels, height, width (NCHW) to number of samples, height, width, and channels (NHWC) in the TensorFlow Lite model. Additionally, experiments were conducted to compare the memory usage, power consumption, and inference latency between the two inference frameworks, as well as to evaluate the real-time video detection performance using DeepStream. The results demonstrate that the fusion of ReLU activation functions with convolution operations reduced the inference latency by 55.5% compared to the use of the Sigmoid linear unit (SiLU) activation alone. In the TensorRT model, the integration of the EfficientNMS_TRT module accelerated post-processing, leading to a reduction in the inference latency of 19.6% and an increase in the frames per second (FPS) of 20.4%. In the TensorFlow Lite model, conversion to the NHWC format decreased the model conversion time by 88.7% and reduced the inference latency by 32.3%. These three ...
DOI:10.3390/agriculture15030332