Efficient Interaction Recognition through Positive Action Representation

By Tao Hu, Xinyan Zhu, Wei Guo, Kehua Su. 2013

38 citations recorded by the source corpus.

This paper proposes a novel approach to decompose two-person interaction into a Positive Action and a Negative Action for more efficient behavior recognition. A Positive Action plays the decisive role in a two-person exchange. Thus, interaction recognition can be simplified to Positive Action-based recognition, focusing on an action representation of just one person. Recently, a new depth sensor has become widely available, the Microsoft Kinect camera, which provides RGB-D data with 3D spatial information for quantitative analysis. However, there are few publicly accessible test datasets using this camera, to assess two-person interaction recognition approaches. Therefore, we created a new dataset with six types of complex human interactions (i.e., named K3HI), including kicking, pointing, punching, pushing, exchanging an object, and shaking hands. Three types of features were extracted for each Positive Action: joint, plane, and velocity features. We used continuous Hidden Markov Models (HMMs) to evaluate the Positive Action-based interaction recognition method and the traditional two-person interaction recognition approach with our test dataset. Experimental results showed that the proposed recognition technique is more accurate than the traditional method, shortens the sample training time, and therefore achieves comprehensive superiority.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering, Human-Computer Interaction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Vasileios Argyriou
2. Victoria Bloom
3. Dimitrios Makris
4. Hong Cheng
5. Guo Ye
6. Yanli Ji
7. Wanqing Li
8. Pichao Wang

In Control and Systems Engineering

1. Dimitrios Makris
2. Vasileios Argyriou
3. Victoria Bloom
4. Hong Cheng
5. Wanqing Li
6. Michael Firman
7. Pichao Wang
8. Yonghong Hou

In Human-Computer Interaction

1. Dimitrios Makris
2. Hong Cheng
3. Vasileios Argyriou
4. Victoria Bloom
5. Guo Ye
6. Yanli Ji

Citations in the corpus

• G3Di: A Gaming Interaction Dataset with a Real Time Detection and Evaluation Framework (2014, background): “representation for human motion [3] [7] [10] [19] [20] so we focus on pose based approaches.”
• Interactive body part contrast mining for human interaction recognition (2014, background): “The papers [9] and [12] show us that it is much efficient to extract the essential features for action recognition.”