arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2304.03602cs.CVcs.AI
收藏

使用游戏引擎从合成数据中进行托盘检测

Pallet Detection from Synthetic Data Using Game Engines

Centre for Automation and Robotic Engineering Science(自动化与机器人工程科学中心);The University of Auckland(奥克兰大学)

Jouveer Naidoo, Nicholas Bates, Trevor Gee, Mahla Nejati

AI总结:

本研究提出利用游戏引擎自动生成3D模型的合成训练数据用于托盘分割,并使用Mask R-CNN流水线实现了86%的AP50,验证了合成数据在自主仓储机器视觉中的有效性。

摘要:

本研究旨在评估在托盘分割背景下,使用游戏引擎生成合成训练数据用于机器学习的可行性。先前研究已证明,使用合成数据是训练神经网络的可行方法,并且由于减少了手动图像标注的需求,可节省大量人工。随着行业加速自主仓储技术的开发,用于托盘检测的机器视觉可从合成数据中受益。根据我们的方法,我们开发了一种工具,能够以像素级精度和远快于手动方法的速度,从3D模型自动生成大量带标注的训练数据。在图像分割方面,使用了Mask R-CNN流水线,对单个托盘实现了86%的AP50。

英文摘要:

This research sets out to assess the viability of using game engines to generate synthetic training data for machine learning in the context of pallet segmentation. Using synthetic data has been proven in prior research to be a viable means of training neural networks and saves hours of manual labour due to the reduced need for manual image annotation. Machine vision for pallet detection can benefit from synthetic data as the industry increases the development of autonomous warehousing technologies. As per our methodology, we developed a tool capable of automatically generating large amounts of annotated training data from 3D models at pixel-perfect accuracy and a much faster rate than manual approaches. Regarding image segmentation, a Mask R-CNN pipeline was used, which achieved an AP50 of 86% for individual pallets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑