论文标题
直观人机相互作用的骨骼数据的手势识别
Gesture Recognition from Skeleton Data for Intuitive Human-Machine Interaction
论文作者
论文摘要
人的手势识别在工业应用中扮演了资本作用，例如人机相互作用。我们提出了一种基于一组手工制作的功能的动态手势进行分割和分类的方法，这些方法是根据Kinect传感器提供的骨架数据得出的。手势检测的模块依赖于执行框架二进制分类的前馈神经网络。手势识别方法应用了一个滑动窗口，该窗口从空间和时间维度中提取信息。然后，我们将各个持续时间的窗户结合在一起，以获得多个时间表的方法和额外的性能增长。在最近的复发神经网络对时间序列域的成功成功的鼓励下，我们还提出了一种基于双向长期短期记忆细胞同时进行手势分割和分类的方法，该方法显示出在长时间尺度上学习时间关系的能力。我们评估了针对Chalearn发表的数据集上的所有不同方法，以查看2014年的People Challenge。最有效的方法达到了JACCARD指数为0.75，这几乎表明与最先进的技术相结合的表现几乎可以搭配。最后，公认的手势用于与协作机器人互动。
Human gesture recognition has assumed a capital role in industrial applications, such as Human-Machine Interaction. We propose an approach for segmentation and classification of dynamic gestures based on a set of handcrafted features, which are drawn from the skeleton data provided by the Kinect sensor. The module for gesture detection relies on a feedforward neural network which performs framewise binary classification. The method for gesture recognition applies a sliding window, which extracts information from both the spatial and temporal dimensions. Then we combine windows of varying durations to get a multi-temporal scale approach and an additional gain in performance. Encouraged by the recent success of Recurrent Neural Networks for time series domains, we also propose a method for simultaneous gesture segmentation and classification based on the bidirectional Long Short-Term Memory cells, which have shown ability for learning the temporal relationships on long temporal scales. We evaluate all the different approaches on the dataset published for the ChaLearn Looking at People Challenge 2014. The most effective method achieves a Jaccard index of 0.75, which suggests a performance almost on pair with that presented by the state-of-the-art techniques. At the end, the recognized gestures are used to interact with a collaborative robot.
