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 2306.15919cs.CVcs.AI
收藏

细粒度3D物体识别:一种方法与实验

Fine-grained 3D object recognition: an approach and experiments

University of Groningen(格罗宁根大学)

Junhyung Jo, Hamidreza Kasaei

AI总结:

本文针对开放域3D物体识别问题,比较了手工设计与深度学习特征方法,发现深度学习特征更适合开放环境,且拼接两类特征能提升分类准确率。

摘要:

三维(3D)物体识别技术正作为汽车自动驾驶等先进技术的核心技术被使用。3D物体识别有两类方法:(i)手工设计的方法,如Global Orthographic Object Descriptor(GOOD),以及(ii)基于深度学习的方法,如MobileNet和VGG。然而,在已知类别数量随时间增加的开放域中,系统需要使用少量训练样本学习新物体类别,因此有必要了解这些方法中哪一种表现更好。在本文中,我们首先实现了一个离线3D物体识别系统,该系统以物体视图作为输入并生成类别标签作为输出。在离线阶段,使用基于实例的学习(IBL)来形成新类别,并使用K折交叉验证来评估所获得的物体识别性能。然后,我们通过将代码集成到模拟教师测试中,以在线方式测试所提出的方法。结果,我们得出结论,使用深度学习特征的方法更适合开放环境。此外,我们观察到将手工设计和深度学习特征进行拼接可以提高分类准确率。

英文摘要:

Three-dimensional (3D) object recognition technology is being used as a core technology in advanced technologies such as autonomous driving of automobiles. There are two sets of approaches for 3D object recognition: (i) hand-crafted approaches like Global Orthographic Object Descriptor (GOOD), and (ii) deep learning-based approaches such as MobileNet and VGG. However, it is needed to know which of these approaches works better in an open-ended domain where the number of known categories increases over time, and the system should learn about new object categories using few training examples. In this paper, we first implemented an offline 3D object recognition system that takes an object view as input and generates category labels as output. In the offline stage, instance-based learning (IBL) is used to form a new category and we use K-fold cross-validation to evaluate the obtained object recognition performance. We then test the proposed approach in an online fashion by integrating the code into a simulated teacher test. As a result, we concluded that the approach using deep learning features is more suitable for open-ended fashion. Moreover, we observed that concatenating the hand-crafted and deep learning features increases the classification accuracy.

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。

↑