Discriminative Recognition of Point Cloud Gesture Classes through One-Shot Learning
Discriminative Recognition of Point Cloud Gesture Classes through One-Shot Learning
复制标题
DOI：
10.1109/robio49542.2019.8961778
复制
发表时间：
2019-12
期刊：
影响因子：
--
通讯作者：
Joshua Owoyemi;Naoya Chiba;K. Hashimoto
中科院分区：
文献类型：
--
作者：
Joshua Owoyemi;Naoya Chiba;K. Hashimoto
在本文中，我们介绍了一个一次性的学习方法，以扩展学习的点云手势类别识别新引入的类别后，训练原始模型。这种方法是基于学习点云数据的手势类别之间的区分，从而可以在不重新训练原始深度神经网络（DNN）模型的情况下识别新类别。我们开发了PointNet模型的时间变体，称为Temporal PointNet或TPointNet，它使用来自低成本深度传感器的原始点云序列并输出序列的类。我们使用多任务策略，其中模型学习点云序列的分类以及分类序列与不同类别的另一个序列之间的欧几里得空间区分。新模型能够将点云序列输入分类并映射到欧几里得空间中，其中手势序列之间的距离对应于手势相似性。我们目前的点云数据集和MSR Action 3D数据集上的结果显示了新的手势类别的高精度的歧视。
In this paper, we introduce a one-shot learning approach to extend learned point cloud gesture categories into recognizing newly introduced categories after training the original model. This approach is based on learning the discrimination between gesture classes of point cloud data, making it possible to recognize new classes without retraining the original deep neural network (DNN) model. We develop a temporal variant of the PointNet model referred to as Temporal PointNet or TPoinNet, which consumes a sequence of raw point clouds from a low-cost depth sensor and outputs the class of the sequence. We use a multitask strategy where the model learns the classification of a point cloud sequence and a Euclidean space discrimination between the classified sequence and another sequence of a different class. The new model is able to classify and map the point clouds sequence inputs into a Euclidean space where the distances between the gesture sequences correspond to the gesture similarities. We present results on a point cloud dataset and the MSR Action 3D dataset showing the discrimination of new gesture categories with a high precision.