BigHand2.2M Benchmark: Hand Pose Dataset and State of the Art Analysis
BigHand2.2M Benchmark: Hand Pose Dataset and State of the Art Analysis
复制标题
DOI：
10.1109/cvpr.2017.279
复制
发表时间：
2017-04
期刊：
影响因子：
--
通讯作者：
Shanxin Yuan;Qianru Ye;B. Stenger;Siddhant Jain;Tae-Kyun Kim
中科院分区：
文献类型：
--
作者：
Shanxin Yuan;Qianru Ye;B. Stenger;Siddhant Jain;Tae-Kyun Kim
在本文中，我们介绍了一个大规模的手部姿势数据集，收集使用一种新的捕获方法。现有的数据集或者是合成生成的，或者是使用深度传感器捕获的：合成数据集与真实的深度图像表现出一定程度的外观差异，而真实的数据集在数量和覆盖范围上受到限制，这主要是由于难以对其进行注释。我们提出了一个跟踪系统与6个6D磁传感器和逆运动学自动获得21关节的手姿势注释的深度图捕获的运动范围的限制最小。捕获协议旨在完全覆盖自然手部姿势空间。如嵌入图所示，与现有基准相比，新数据集显示出更广泛和更密集的手部姿势范围。目前国家的最先进的方法进行评估的数据集，我们证明了跨基准性能的显着改善。我们还展示了在新数据集上训练的CNN在以自我为中心的手部姿势估计方面的显着改进。
In this paper we introduce a large-scale hand pose dataset, collected using a novel capture method. Existing datasets are either generated synthetically or captured using depth sensors: synthetic datasets exhibit a certain level of appearance difference from real depth images, and real datasets are limited in quantity and coverage, mainly due to the difficulty to annotate them. We propose a tracking system with six 6D magnetic sensors and inverse kinematics to automatically obtain 21-joints hand pose annotations of depth maps captured with minimal restriction on the range of motion. The capture protocol aims to fully cover the natural hand pose space. As shown in embedding plots, the new dataset exhibits a significantly wider and denser range of hand poses compared to existing benchmarks. Current state-of-the-art methods are evaluated on the dataset, and we demonstrate significant improvements in cross-benchmark performance. We also show significant improvements in egocentric hand pose estimation with a CNN trained on the new dataset.