SqueezeSlimU-Net : an adaptive and efficient segmentation architecture for real-time UAV weed detection

Machidon, Alina Luminita (author), Krašovec, Andraž (author), Pejović, Veljko (author), Machidon, Octavian-Mihai (author)

The limited processing capacity of computing equipment that is usually mounted on unmanned aerial vehicles (UAVs) often prevents real-time execution of computer vision tasks, such as image segmentation. In this article, we introduce SqueezeSlimU-Net (SSU-Net), an adaptive and efficient deep learning (DL) model designed to enhance UAV capabilities in performing complex image segmentation tasks under resource constraints, thereby advancing real-time UAV vision—a crucial technology in fields, such as precision agriculture. SSU-Net combines benefits of three specialized DL architectures: the semantic segmentation capabilities of the U-Net architecture, the computational efficiency of SqueezeNet's fire modules, and the dynamic adaptability of slimmable neural networks. This integration allows SSU-Net to adjust its network width in real-time, thus striking the balance between inference accuracy and computational load based on the operational parameters such as task requirements and UAV's battery life. To validate SSU-Net's efficacy, we applied it to a weed detection task using two UAV-collected datasets and tested it on an edge computing platform for UAVs. Our experiments show that SSU-Net can reduce inference energy consumption by up to 65% with only a minimal 2% reduction in accuracy. A comparative evaluation with other state-of-the-art DL image segmentation approaches shows that SSU-Net achieves on par weed detection performance while requiring significantly fewer model parameters. In addition, SSU-Net outperforms state-of-the-art network pruning techniques in balancing accuracy and resource usage. Timing benchmarks show SSU-Net fostering real-time weed detection even on low-resource UAVs, making it ideal for UAV remote sensing applications.

• Language: English
• Keywords: adaptive neural networks, computational effciency, image segmentation, precision agriculture, real-time unmanned aerial vehicle vision, UAV, weed detection
• Work type: Article
• Typology: 1.01 - Original Scientific Article
• Organization: FRI - Faculty of Computer and Information Science
• Publication status: Published
• Publication version: Version of Record
• Year: 2025
• Number of pages: Str. 5749-5764
• Numbering: Vol. 18
• PID: 20.500.12556/RUL-171574
• UDC: 004.93:632.51
• ISSN on article: 1939-1404
• DOI: 10.1109/JSTARS.2025.3536175
• COBISS.SI-ID: 228027395
• Publication date in RUL: 28.08.2025

Record is a part of a journal

• Title: IEEE journal of selected topics in applied earth observations and remote sensing
• Shortened title: IEEE journal of select. topic. in appl. earth observ. and remote sensing
• Publisher: Institute of Electrical and Electronics Engineers
• ISSN: 1939-1404
• COBISS.SI-ID: 6747220

Licences

• License: CC BY 4.0, Creative Commons Attribution 4.0 International
• Link: http://creativecommons.org/licenses/by/4.0/
• Description: This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.

Secondary language

• Language: Slovenian
• Keywords: prilagodljive nevronske mreže, računalniška učinkovitost, segmentacija slike, natančno poljedelstvo, vid brezpilotnega letala v realnem času, odkrivanje plevela