WeedVision: Multi-Stage Growth and Classification of Weeds using DETR and RetinaNet for Precision Agriculture

TL;DR

This paper develops and compares advanced object detection models, DETR and RetinaNet, for identifying and classifying 16 weed species across growth stages, demonstrating RetinaNet's superior accuracy and speed for real-time agricultural weed management.

Contribution

It introduces a large, labeled dataset and applies state-of-the-art detection models to improve weed identification across growth stages, highlighting RetinaNet's effectiveness for real-time applications.

Findings

RetinaNet achieved a mean Average Precision of 0.904 on test data.

RetinaNet outperformed DETR in inference speed at 7.28 FPS.

Both models showed increased accuracy as weeds matured.

Abstract

Weed management remains a critical challenge in agriculture, where weeds compete with crops for essential resources, leading to significant yield losses. Accurate detection of weeds at various growth stages is crucial for effective management yet challenging for farmers, as it requires identifying different species at multiple growth phases. This research addresses these challenges by utilizing advanced object detection models, specifically, the Detection Transformer (DETR) with a ResNet50 backbone and RetinaNet with a ResNeXt101 backbone, to identify and classify 16 weed species of economic concern across 174 classes, spanning their 11 weeks growth stages from seedling to maturity. A robust dataset comprising 203,567 images was developed, meticulously labeled by species and growth stage. The models were rigorously trained and evaluated, with RetinaNet demonstrating superior performance, achieving a mean Average Precision (mAP) of 0.907 on the training set and 0.904 on the test set, compared to DETR's mAP of 0.854 and 0.840, respectively. RetinaNet also outperformed DETR in recall and inference speed of 7.28 FPS, making it more suitable for real time applications. Both models showed improved accuracy as plants matured. This research provides crucial insights for developing precise, sustainable, and automated weed management strategies, paving the way for real time species specific detection systems and advancing AI-assisted agriculture through continued innovation in model development and early detection accuracy.