Human tracking using multiple views

Human tracking plays an important role in providing activity assistance and care for users in smart homes. This paper presents a method for detecting and tracking of a user in a smart home using multiple sensors. We consider one PTZ camera and multiple Kinects in order to offer continuity over the users movement. Thus, the user can be keep inside the frame for most of the time. In this way, we minimize the drawbacks of using only one type of sensor. For example, field of view provided by Kinect sensor is not wide enough to cover the entire room. Also, the PTZ camera is not able to detect and track a person in case of different situations, such as the person is sitting or it is under the camera. The system is proposed for the Ambient Intelligence Laboratory (AmI-Lab) at the University Politehnica of Bucharest, and the design is compatible with the software architecture developed for this laboratory, AmI-Platform. The training and evaluation is operated on custom dataset, extracted from the AmI-Lab test environment.

[1]  Paul A. Viola,et al.  Multiple-Instance Pruning For Learning Efficient Cascade Detectors , 2007, NIPS.

[2]  R. Dobrescu,et al.  Smart sensor network for continuous monitoring at home of elderly population with chronic diseases , 2012, 2012 20th Telecommunications Forum (TELFOR).

[3]  Shuicheng Yan,et al.  An HOG-LBP human detector with partial occlusion handling , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[4]  Adina Magda Florea,et al.  Multimodal Indoor Tracking of a Single Elder in an AAL Environment , 2013, ISAmI.

[5]  Pietro Perona,et al.  Integral Channel Features , 2009, BMVC.

[6]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[7]  Paul A. Viola,et al.  Robust Real-time Object Detection , 2001 .

[8]  Adina Magda Florea,et al.  Data Fusion in a Multi Agent System for Person Detection and Tracking in an Intelligent Room , 2014, IDC.

[9]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[10]  Pietro Perona,et al.  Pedestrian Detection: An Evaluation of the State of the Art , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.