# Hardware-Aware YOLO Compression for Low-Power Edge AI on STM32U5 for Weeds Detection in Digital Agriculture

arXiv: https://arxiv.org/abs/2511.07990 · HTML: https://mlsanity.com/paper/2511.07990/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 35 references that are in the map.
- First posted on arXiv 11 Nov 2025.

## Builds on (most cited first, 19 of 19)

- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [To prune, or not to prune: exploring the efficacy of pruning for model compression](https://mlsanity.com/paper/1710.01878/) (2017)
- [A White Paper on Neural Network Quantization](https://mlsanity.com/paper/2106.08295/) (2021)
- [QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving](https://mlsanity.com/paper/2405.04532/) (2024)
- [DepGraph: Towards Any Structural Pruning](https://mlsanity.com/paper/2301.12900/) (2023)
- [Convolutional Neural Network Pruning with Structural Redundancy Reduction](https://mlsanity.com/paper/2104.03438/) (2021)
- [TinyissimoYOLO: A Quantized, Low-Memory Footprint, TinyML Object Detection Network for Low Power Microcontrollers](https://mlsanity.com/paper/2306.00001/) (2023)
- [YOLOv8 to YOLO11: A Comprehensive Architecture In-depth Comparative Review](https://mlsanity.com/paper/2501.13400/) (2025)
- [RL-Pruner: Structured Pruning Using Reinforcement Learning for CNN Compression and Acceleration](https://mlsanity.com/paper/2411.06463/) (2024)
- [Pruning artificial neural networks: a way to find well-generalizing, high-entropy sharp minima](https://mlsanity.com/paper/2004.14765/) (2020)
- [Squeezed Edge YOLO: Onboard Object Detection on Edge Devices](https://mlsanity.com/paper/2312.11716/) (2023)
- [How to keep pushing ML accelerator performance? Know your rooflines!](https://mlsanity.com/paper/2505.16346/) (2025)
- [Toward Robotic Weed Control: Detection of Nutsedge Weed in Bermudagrass Turf Using Inaccurate and Insufficient Training Data](https://mlsanity.com/paper/2106.08897/) (2021)
- [DSORT-MCU: Detecting Small Objects in Real-Time on Microcontroller Units](https://mlsanity.com/paper/2410.16769/) (2024)
- [One Shot vs. Iterative: Rethinking Pruning Strategies for Model Compression](https://mlsanity.com/paper/2508.13836/) (2025)
- [microYOLO: Towards Single-Shot Object Detection on Microcontrollers](https://mlsanity.com/paper/2408.15865/) (2024)
- [MCUBench: A Benchmark of Tiny Object Detectors on MCUs](https://mlsanity.com/paper/2409.18866/) (2024)
- [EcoWeedNet: A Lightweight and Automated Weed Detection Method for Sustainable Next-Generation Agricultural Consumer Electronics](https://mlsanity.com/paper/2502.00205/) (2025)

## Built on by (most cited first, 1 of 1)

- [Affordable Precision Agriculture: A Deployment-Oriented Review of Low-Cost, Low-Power Edge AI and TinyML for Resource-Constrained Farming Systems](https://mlsanity.com/paper/2603.15085/) (2026)

## Abstract (arXiv)

Weeds significantly reduce crop yields worldwide and pose major challenges to sustainable agriculture. Traditional weed management methods, primarily relying on chemical herbicides, risk environmental contamination and lead to the emergence of herbicide-resistant species. Precision weeding, leveraging computer vision and machine learning methods, offers a promising eco-friendly alternative but is often limited by reliance on high-power computational platforms. This work presents an optimized, low-power edge AI system for weeds detection based on the YOLOv8n object detector deployed on the STM32U575ZI microcontroller. Several compression techniques are applied to the detection model, including structured pruning, integer quantization and input image resolution scaling in order to meet strict hardware constraints. The model is trained and evaluated on the CropAndWeed dataset with 74 plant species, achieving a balanced trade-off between detection accuracy and efficiency. Our system supports real-time, in-situ weeds detection with a minimal energy consumption of 51.8mJ per inference, enabling scalable deployment in power-constrained agricultural environments.