arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.11991cs.CVcs.AI
收藏

基于合成训练数据的二维刀具界标实时的检测

Real-time Detection of 2D Tool Landmarks with Synthetic Training Data

Hasselt University(哈瑟尔特大学);tUL(林堡大学学院);Flanders Make(法兰德斯制造研究院)

Bram Vanherle, Jeroen Put, Nick Michiels, Frank Van Reeth

摘要:

本文提出了一种深度学习架构,可以实时的检测物理工具(如锤子或螺丝刀)的某些地标的2D位置。为了避免人工标记的劳动,网络在综合生成的数据上进行训练。在计算机生成的图像上训练计算机视觉模型,同时仍然在真实图像上实现良好的准确性,由于域的差异,这是一个挑战。所提出的方法使用先进的渲染方法结合迁移学习和中间监督架构来解决这个问题。结果表明,本文提出的模型,命名为中间热图模型(IHM),推广到真实图像时,训练的合成数据。为了避免需要一个确切的纹理的3D模型的工具的问题,它表明,该模型将概括为一个看不见的工具时,训练一组不同的3D模型相同类型的工具。IHM相比,现有的两种方法来检测关键点,它表明,它优于那些在检测工具地标,训练合成数据。

英文摘要:

In this paper a deep learning architecture is presented that can, in real time, detect the 2D locations of certain landmarks of physical tools, such as a hammer or screwdriver. To avoid the labor of manual labeling, the network is trained on synthetically generated data. Training computer vision models on computer generated images, while still achieving good accuracy on real images, is a challenge due to the difference in domain. The proposed method uses an advanced rendering method in combination with transfer learning and an intermediate supervision architecture to address this problem. It is shown that the model presented in this paper, named Intermediate Heatmap Model (IHM), generalizes to real images when trained on synthetic data. To avoid the need for an exact textured 3D model of the tool in question, it is shown that the model will generalize to an unseen tool when trained on a set of different 3D models of the same type of tool. IHM is compared to two existing approaches to keypoint detection and it is shown that it outperforms those at detecting tool landmarks, trained on synthetic data.

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。

↑