Unsupervised learning-based approach for detecting 3D edges in depth maps.
Unsupervised learning-based approach for detecting 3D edges in depth maps.
复制标题
DOI：
10.1038/s41598-023-50899-3
复制
发表时间：
2024-01-08
影响因子：
4.6
通讯作者：
中科院分区：
文献类型：
--
作者：
3D边缘特征表示3D场景中不同对象或表面之间的边界，对于许多计算机视觉任务至关重要，包括对象识别，跟踪和分割。它们在机器人领域也有许多实际应用，例如视觉引导的物体抓取和操纵。为了在嘈杂的真实世界深度数据中提取这些特征，可靠的3D边缘检测器是必不可少的。然而，目前可用的3D边缘检测方法要么是高度参数化的，要么需要地面实况标记，这使得它们在实际应用中具有挑战性。为此，我们提出了一种新的三维边缘检测方法，使用无监督分类。我们的方法使用编码器-解码器网络从三个不同尺度的深度图中学习特征，从中提取特定于边缘的特征。然后使用学习将这些边缘特征聚类，以将每个点分类为边缘或不是边缘。所提出的方法有两个主要优点。首先，它消除了手动微调数据特定超参数的需要，并自动选择边缘分类的阈值。其次，该方法不需要任何标记的训练数据，不像许多最先进的方法需要使用大量手工标记的数据集进行监督训练。所提出的方法进行了评估的五个基准数据集与单和多目标场景，并与四个国家的最先进的边缘检测方法从文献中进行比较。结果表明，所提出的方法实现了有竞争力的性能，尽管不使用任何标记的数据或依赖于手动调整的关键参数。
3D edge features, which represent the boundaries between different objects or surfaces in a 3D scene, are crucial for many computer vision tasks, including object recognition, tracking, and segmentation. They also have numerous real-world applications in the field of robotics, such as vision-guided grasping and manipulation of objects. To extract these features in the noisy real-world depth data, reliable 3D edge detectors are indispensable. However, currently available 3D edge detection methods are either highly parameterized or require ground truth labelling, which makes them challenging to use for practical applications. To this extent, we present a new 3D edge detection approach using unsupervised classification. Our method learns features from depth maps at three different scales using an encoder–decoder network, from which edge-specific features are extracted. These edge features are then clustered using learning to classify each point as an edge or not. The proposed method has two key benefits. First, it eliminates the need for manual fine-tuning of data-specific hyper-parameters and automatically selects threshold values for edge classification. Second, the method does not require any labelled training data, unlike many state-of-the-art methods that require supervised training with extensive hand-labelled datasets. The proposed method is evaluated on five benchmark datasets with single and multi-object scenes, and compared with four state-of-the-art edge detection methods from the literature. Results demonstrate that the proposed method achieves competitive performance, despite not using any labelled data or relying on hand-tuning of key parameters.
登录
查看更多内容
影响因子：
--
作者：
KULLBACK, S;LEIBLER, RA
通讯作者：
LEIBLER, RA
影响因子：
8
作者：
HADDON, JF
通讯作者：
HADDON, JF
影响因子：
3.9
作者：
Munir, Mohsin;Siddiqui, Shoaib Ahmed;Ahmed, Sheraz
通讯作者：
Ahmed, Sheraz
影响因子：
8
作者：
Affeldt, Severine;Labiod, Lazhar;Nadif, Mohamed
通讯作者：
Nadif, Mohamed
DOI：
10.1109/tpami.2020.2992393
发表时间：
2021-11-01
影响因子：
23.6
作者：
Jing, Longlong;Tian, Yingli
通讯作者：
Tian, Yingli