UltraLight Luma: A Novel Edge-Deployable Perception Network for Crop-Row Segmentation in Agricultural Robotics
Reliable crop-row perception is essential for autonomous agricultural robots, but low-cost deployment is constrained by computation, memory, power, and inference time.
ProofPaper ↗
Key points
- This paper addresses crop-row detection and navigation-line extraction using UltraLight Luma, a compact encoder-decoder segmentation network with a progressive learning strategy and only 13.1k trainable parameters.
- The predicted crop-row masks are processed using a post-processing algorithm to estimate row alignment for downstream visual servoing.
- UltraLight Luma improves parameter efficiency over U-Net, YOLOv8, and YOLOv26 while maintaining reliable crop-row detection performance.
- The model required only 25.23 mJ per inference, demonstrating its suitability for resource-constrained agricultural robots.
Sources (1)
- [1]UltraLight Luma: A Novel Edge-Deployable Perception Network for Crop-Row Segmentation in Agricultural RoboticsarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 11:47 AM
Reliable crop-row perception is essential for autonomous agricultural robots, but low-cost deployment is constrained by computation, memory, power, and inference time.
This paper addresses crop-row detection and navigation-line extraction using UltraLight Luma, a compact encoder-decoder segmentation network with a progressive learning strategy and only 13.1k trainable parameters.
Extractive summary: sentences quoted from the sources.