• Home
  • Search
  • Aerial-Based Weed Detection Using Low-Cost and Lightweight Deep Learning Models on an Edge Platform
  • Cite Icon2
  • https://doi.org/10.13031/ja.15413Copy DOI Icon

Aerial-Based Weed Detection Using Low-Cost and Lightweight Deep Learning Models on an Edge Platform

Show More
  • Abstract
  • Literature Map
  • Citations
  • Similar Papers
Abstract

Highlights Lightweight deep learning models were trained on an edge device to identify weeds in aerial images. A customized configuration file was setup to train the models. These models were deployed to detect weeds in aerial images and videos (near real-time). CSPMobileNet-v2 and YOLOv4-lite are recommended models for weed detection using edge platform. Abstract. Deep learning (DL) techniques have proven to be a successful approach in detecting weeds for site-specific weed management (SSWM). In the past, most of the research work has trained and deployed pre-trained DL models on high-end systems coupled with expensive graphical processing units (GPUs). However, only a limited number of research studies have used DL models on an edge system for aerial-based weed detection. Therefore, while focusing on hardware cost minimization, eight DL models were trained and deployed on an edge device to detect weeds in aerial-image context and videos in this study. Four large models, namely CSPDarkNet-53, DarkNet-53, DenseNet-201, and ResNet-50, along with four lightweight models, CSPMobileNet-v2, YOLOv4-lite, EfficientNet-B0, and DarkNet-Ref, were considered for training a customized DL architecture. Along with trained model performance scores (average precision score, mean average precision (mAP), intersection over union, precision, and recall), other model metrics to assess edge system performance such as billion floating-point operations/s (BFLOPS), frame rates/s (FPS), and GPU memory usage were also estimated. The lightweight CSPMobileNet-v2 and YOLOv4-lite models outperformed others in detecting weeds in aerial image context. These models were able to achieve a mAP score of 83.2% and 82.2%, delivering an FPS of 60.9 and 61.1 during near real-time weed detection in aerial videos, respectively. The popular ResNet-50 model achieved a mAP of 79.6%, which was the highest amongst all the large models deployed for weed detection tasks. Based on the results, the two lightweight models, namely, CSPMobileNet-v2 and YOLOv4-lite, are recommended, and they can be used on a low-cost edge system to detect weeds in aerial image context with significant accuracy. Keywords: Aerial image, Deep learning, Edge device, Precision agriculture, Weed detection.

Similar Papers
  • Research Article
  • Citations17

Lightweight Deep Learning Models For Edge Devices—A Survey

  • Jan 06, 2025
  • International Journal of Computer Information Systems and Industrial Management Applications
  • Aminu Musa +5
  • Research Article
  • Citations8

Lightweight Deep Learning Models For Edge Devices—A Survey

  • Jan 06, 2025
  • International Journal of Computer Information Systems and Industrial Management Applications
  • Aminu Musa +5
  • Conference Article
  • Citations8

OpenWeedGUI: an open-source graphical user interface for weed imaging and detection

  • Jun 13, 2023
  • Jiajun Xu +1
  • Research Article
  • Citations28

Field-based multispecies weed and crop detection using ground robots and advanced YOLO models: A data and model-centric approach

  • Aug 16, 2024
  • Smart Agricultural Technology
  • Sunil G C +7
  • Research Article
  • Citations31

Efficient Hardware Acceleration Techniques for Deep Learning on Edge Devices: A Comprehensive Performance Analysis

  • Aug 01, 2023
  • KHWARIZMIA
  • M.A Burhanuddin
  • PDF
  • Research Article
  • Citations1

Exploration and research about key technologies concerning Deep Learning models targeting Mobile Terminals

  • Jul 01, 2022
  • Journal of Physics Conference Series
  • Yang Wang +2
  • Research Article
  • Citations4

Enhanced fingerprint pattern classification: Integrating attention modules with lightweight deep learning models

  • Apr 15, 2024
  • Engineering Reports
  • Esther Mukoya +2
  • Research Article
  • Citations17

Self Distillation for Improving the Generalizability of Retinal Disease Diagnosis Using Optical Coherence Tomography Images

  • Jul 01, 2023
  • IEEE Journal of Selected Topics in Quantum Electronics
  • Naveen Paluru +3
  • PDF
  • Research Article
  • Citations9

A Forest Fire Smoke Monitoring System Based on a Lightweight Neural Network for Edge Devices

  • Jun 24, 2024
  • Forests
  • Jingwen Huang +3
  • Conference Article
  • Citations56

Performance Evaluation of Deep Learning Compilers for Edge Inference

  • Jun 01, 2021
  • Gaurav Verma +3
  • Research Article
  • Citations2

Optimization of Dechlorination Experiment Design Using Lightweight Deep Learning Model

  • Jun 25, 2022
  • Computational Intelligence and Neuroscience
  • Jianghua Peng +1
  • PDF
  • Research Article
  • Citations3

DelayNet: Enhancing Temporal Feature Extraction for Electronic Consumption Forecasting with Delayed Dilated Convolution

  • Nov 20, 2023
  • Energies
  • Le Hoang Anh +4
  • Research Article
  • Citations52

Analysis of Stable Diffusion-derived fake weeds performance for training Convolutional Neural Networks

  • Oct 21, 2023
  • Computers and Electronics in Agriculture
  • Hugo Moreno +4
  • PDF
  • Research Article
  • Citations6

Computer Vision for Site-Specific Weed Management in Precision Agriculture: A Review

  • Nov 04, 2025
  • Agriculture
  • Puranjit Singh +2
  • Conference Article
  • Citations38

Detecting weeds from crops under complex field environments based on Faster RCNN

  • Jan 13, 2021
  • Vi Nguyen Thanh Le +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.