实测发现光照和背景干扰让水果识别准确率从100%降至69.15%
Sensing-based Robustness Challenges in Agricultural Robotic Harvesting
- 用YOLOv8替代HSV检测水果，提升复杂环境适应性
- 户外直射阳光下平均识别准确率仅69.15%
- 适合研究农业机器人感知鲁棒性的研究人员
本文探讨了农业机器人采摘器在不同环境干扰下检测与定位水果所面临的挑战。实验室环境下采用传统HSV变换与YOLOv8深度学习模型进行对比实验；户外仅使用YOLOv8，因HSV无法准确勾勒水果轮廓。实验包含十种不同水果排列模式，含六颗苹果与六颗橙子。通过网格结构的单应性（透视）变换，将检测到的中点转换为三维世界坐标。结果表明：室内条件下YOLOv8实现100%检测准确率；而户外环境下，受光照与背景干扰影响，准确率显著下降，尤其在直射阳光下平均仅为69.15%。研究揭示真实场景中光照变化、背景干扰及果实颜色形状差异带来的重大限制，强调需进一步优化算法与传感器以提升农业机器人采摘系统的鲁棒性。
原文摘要 · Abstract (English)
This paper presents the challenges agricultural robotic harvesters face in detecting and localising fruits under various environmental disturbances. In controlled laboratory settings, both the traditional HSV (Hue Saturation Value) transformation and the YOLOv8 (You Only Look Once) deep learning model were employed. However, only YOLOv8 was utilised in outdoor experiments, as the HSV transformation was not capable of accurately drawing fruit contours. Experiments include ten distinct fruit patterns with six apples and six oranges. A grid structure for homography (perspective) transformation was employed to convert detected midpoints into 3D world coordinates. The experiments evaluated detection and localisation under varying lighting and background disturbances, revealing accurate performance indoors, but significant challenges outdoors. Our results show that indoor experiments using YOLOv8 achieved 100% detection accuracy, while outdoor conditions decreased performance, with an average accuracy of 69.15% for YOLOv8 under direct sunlight. The study demonstrates that real-world applications reveal significant limitations due to changing lighting, background disturbances, and colour and shape variability. These findings underscore the need for further refinement of algorithms and sensors to enhance the robustness of robotic harvesters for agricultural use.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。