Resource-Constrained UAV-Based Weed Detection for Site-Specific Management on Edge Devices

2026-04-25

AI Summary

This study addresses the lack of systematic evaluation of the trade-off between accuracy and real-time performance for weed detection models deployed on edge devices in real-world scenarios. We present an end-to-end weed detection framework tailored for drone-based deployment and conduct the first comprehensive benchmark of YOLOv8–v12 and RT-DETRv1–v2 model families across edge platforms including Jetson Orin Nano, AGX Xavier, and AGX Orin. Experimental results show that RT-DETRv2-R50-M achieves a mAP50 of 79%, while YOLOv10n delivers the fastest inference speed. Notably, YOLOv11s and RT-DETRv2-R50-M strike the best balance between accuracy and latency, offering clear guidance for model selection in resource-constrained settings requiring real-time weed detection.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Object Detection & Categorization
• Search and Optimization: Evaluation and Analysis

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Cloud, edge and content delivery systems for the Web
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Weeds compete with crops for light, water, and nutrients, reducing yield and crop quality. Efficient weed detection is essential for site-specific weed management (SSWM). Although deep learning models have been deployed on UAV-based edge systems, a systematic understanding of how different model architectures perform under real-world resource constraints is still lacking. To address this gap, this study proposes a deployment-oriented framework for real-time UAV-based weed detection on resource-constrained edge platforms. The framework integrates UAV data acquisition, model development, and on-device inference, with a focus on balancing detection accuracy and computational efficiency. A diverse set of state-of-the-art object detection models is evaluated, including convolution-based YOLO models (v8-v12) and transformer-based RT-DETR models (v1-v2). Experiments on three edge devices (Jetson Orin Nano, Jetson AGX Xavier, and Jetson AGX Orin) demonstrate clear trade-offs between accuracy and inference latency across models and hardware configurations. Results show that high-capacity models achieve up to 86.9% mAP50 but suffer from high latency, limiting real-time deployment. In contrast, lightweight models achieve 66%-71% mAP50 with significantly lower latency, enabling real-time performance. Among all models, RT-DETRv2-R50-M achieves competitive accuracy (79% mAP50) with improved efficiency, while YOLOv10n provides the fastest inference speed. YOLOv11s and RT-DETRv2-R50-M offer the best balance between accuracy and speed, making them strong candidates for real-time UAV deployment.

Problem

• UAV-based weed detection
• resource-constrained edge devices
• site-specific weed management
• real-time inference
• model efficiency

Innovation

• UAV-based weed detection
• edge computing
• real-time inference
• model efficiency
• site-specific weed management