Research on the acquisition of human behavior data based on Kinect

In the field of computer vision, identifying interesting objects from complex environments by depth data becomes a hot topic in the field of computer vision. In the research of human behavior recognition, it is an important branch in the field of action recognition to obtain the data of human behavior through depth data, and then to do the corresponding detection and recognition. This paper studies the acquisition technology of human behavior data based on Kinect, analyzes the technical parameters and measurement principle of the new generation of Kinect v2(Kinect for Windows v2 sensor), and designs a human behavior data acquisition system based on Kinect v2. Through experiments, it is proved that the method presented in this paper for the acquisition of human body behavior data is practical and feasible.

[1]  Pat O'Connor,et al.  7.6 A 512×424 CMOS 3D Time-of-Flight image sensor with multi-frequency photo-demodulation up to 130MHz and 2GS/s ADC , 2014, 2014 IEEE International Solid-State Circuits Conference Digest of Technical Papers (ISSCC).

[2]  Jake K. Aggarwal,et al.  View invariant human action recognition using histograms of 3D joints , 2012, 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[3]  Xueping Liu,et al.  Real-time action detection and temporal segmentation in continuous video , 2017 .

[4]  Nasser Kehtarnavaz,et al.  A survey of depth and inertial sensor fusion for human action recognition , 2015, Multimedia Tools and Applications.

[5]  John Sell,et al.  The Xbox One System on a Chip and Kinect Sensor , 2014, IEEE Micro.

[6]  Juan Carlos López,et al.  Kinect and Episodic Reasoning for Human Action Recognition , 2016, DCAI.

[7]  Cai Zi-xing.  Method of 3D visualization using laser radar on board of mobile robot , 2004 .

[8]  Juan Song,et al.  An Online Continuous Human Action Recognition Algorithm Based on the Kinect Sensor , 2016, Sensors.

[9]  Xuzhi Wang,et al.  Human action recognition based on Kinect and PSO-SVM by representing 3D skeletons as points in lie group , 2016, 2016 International Conference on Audio, Language and Image Processing (ICALIP).

[10]  Petros Daras,et al.  Real-Time Skeleton-Tracking-Based Human Action Recognition Using Kinect Data , 2014, MMM.

[11]  Kurt Konolige,et al.  Projected texture stereo , 2010, 2010 IEEE International Conference on Robotics and Automation.

[12]  Yibo Li,et al.  Research on the acquisition of human body behavior data based on binocular stereo vision , 2017, 2017 29th Chinese Control And Decision Conference (CCDC).