发表机构
Faculty of Computing, Sri Lanka Institute of Information Technology（斯里兰卡信息技术学院计算机学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出UltraLight Luma网络，用于农业机器人作物行分割，参数仅13.1k，推理功耗25.23mJ，参数效率优于U-Net、YOLOv8等，适配边缘部署。
AI 中文摘要
可靠的作物行感知对自主农业机器人至关重要，但低成本部署受限于计算、内存、功耗和推理时间。本文采用UltraLight Luma（一种紧凑的编码器-解码器分割网络，采用渐进式学习策略，仅含13100个可训练参数）解决作物行检测与导航线提取问题。对预测的作物行掩码采用后处理算法，以估计下游视觉伺服的行对齐。UltraLight Luma相比U-Net、YOLOv8和YOLOv26提升了参数效率，同时保持可靠的作物行检测性能，每次推理仅需25.23毫焦，证明其适用于资源受限的农业机器人。
英文摘要
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. 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.
CommentsThis work has been accepted for publication in IECON 2026. The final published version will be available via IEEE Xplore
