arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1312.6826cs.CV
收藏

基于判别学习的3D兴趣点检测

3D Interest Point Detection via Discriminative Learning

Stevens Institute of Technology(史蒂文斯理工学院)

Leizer Teran, Philippos Mordohai

摘要:

在3D网格中检测兴趣点的任务通常由几何方法处理。这些方法虽然很好地描述了人类的偏好,但可能无法处理人类反应的多样性和主观性。不同的任务对兴趣点检测有不同的要求;有些任务可能需要高精度,而有些任务可能需要高召回率。有时,具有高曲率的点可能是期望的,而在其他情况下,高曲率可能是噪声的指示。几何方法缺乏适应这种变化所需的灵活性。因此,兴趣点检测似乎非常适合机器学习方法,这些方法可以被训练以匹配应用于注释的训练数据的标准。在本文中,我们制定了兴趣点检测作为一个监督的二元分类问题,使用随机森林作为我们的分类器。在其他挑战中,我们面临着一个不平衡的学习问题,由于兴趣点和非兴趣点之间的先验知识的实质性差异。我们通过重新采样训练集来解决这个问题。我们验证了我们的方法的准确性,并将我们的结果与一个新的标准基准上的五种最先进的方法进行比较。

英文摘要:

The task of detecting the interest points in 3D meshes has typically been handled by geometric methods. These methods, while greatly describing human preference, can be ill-equipped for handling the variety and subjectivity in human responses. Different tasks have different requirements for interest point detection; some tasks may necessitate high precision while other tasks may require high recall. Sometimes points with high curvature may be desirable, while in other cases high curvature may be an indication of noise. Geometric methods lack the required flexibility to adapt to such changes. As a consequence, interest point detection seems to be well suited for machine learning methods that can be trained to match the criteria applied on the annotated training data. In this paper, we formulate interest point detection as a supervised binary classification problem using a random forest as our classifier. Among other challenges, we are faced with an imbalanced learning problem due to the substantial difference in the priors between interest and non-interest points. We address this by re-sampling the training set. We validate the accuracy of our method and compare our results to those of five state of the art methods on a new, standard benchmark.

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。

↑