Linking Computer Vision with Off-the-Shelf Accelerometry through Kinetic Energy for Precise Localization

In this paper we propose the integration of computer vision with accelerometry in order to provide a precise localization solution. In terms of accelerometry, our approach makes use of a single off-the-shelf accelerometer on the waist to precisely obtain the velocity of the user. This allows us to calculate the kinetic energy of the person being tracked, and link the accelerometry data with the computer vision part of the system, where we employ segmentation of local regions of motion in the motion history image to estimate movement, and we leverage the number of pixels within the movement silhouettes as a metric accounting for the kinetic energy and the distance to the camera for the person being tracked. The fusion of the data from both technologies with a Kalman filter delivers an accuracy in the localization solution of up to 0.5 meters.

[1]  Gérard Lachapelle,et al.  Indoor Positioning System Using Accelerometry and High Accuracy Heading Sensors , 2003 .

[2]  Wiebren Zijlstra,et al.  Assessment of spatio-temporal parameters during unconstrained walking , 2004, European Journal of Applied Physiology.

[3]  Koichi Hashimoto,et al.  Identifying a moving object with an accelerometer in a camera view , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[4]  Gaurav S. Sukhatme,et al.  Visual-inertial simultaneous localization, mapping and sensor-to-sensor self-calibration , 2009, 2009 IEEE International Symposium on Computational Intelligence in Robotics and Automation - (CIRA).

[5]  Ling Liu,et al.  Unified analytical models for Location Management costs and optimum design of location areas , 2009, 2009 5th International Conference on Collaborative Computing: Networking, Applications and Worksharing.

[6]  F. Seco,et al.  A comparison of Pedestrian Dead-Reckoning algorithms using a low-cost MEMS IMU , 2009, 2009 IEEE International Symposium on Intelligent Signal Processing.

[7]  Andreas Savvides,et al.  PEM-ID: Identifying people by gait-matching using cameras and wearable accelerometers , 2009, 2009 Third ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC).

[8]  Andrey E. Barabanov,et al.  Adaptive filtering of tracking camera data and onboard sensors for a small helicopter autopilot , 2009, 2009 IEEE Control Applications, (CCA) & Intelligent Control, (ISIC).

[9]  E. Martin.  Solving training issues in the application of the wavelet transform to precisely analyze human body acceleration signals , 2010, 2010 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[10]  László Havasi,et al.  A statistical method for object localization in multi-camera tracking , 2010, 2010 IEEE International Conference on Image Processing.

[11]  Ruzena Bajcsy,et al.  Precise indoor localization using smart phones , 2010, ACM Multimedia.

[12]  Andreas Savvides,et al.  Towards Cooperative Localization of Wearable Sensors using Accelerometers and Cameras , 2010, 2010 Proceedings IEEE INFOCOM.

[13]  Huijun Di,et al.  A Robust Approach for Person Localization in Multi-camera Environment , 2010, 2010 20th International Conference on Pattern Recognition.

[14]  Koichi Hashimoto,et al.  Accelerometer detection in a camera view based on feature point tracking , 2010, 2010 IEEE/SICE International Symposium on System Integration.

[15]  L. Gonzo,et al.  An integrated system for people fall-detection with data fusion capabilities based on 3D ToF camera and wireless accelerometer , 2010, 2010 IEEE Sensors.

[16]  E. Martin.  Real time patient's gait monitoring through wireless accelerometers with the wavelet transform , 2011, 2011 IEEE Topical Conference on Biomedical Wireless Technologies, Networks, and Sensing Systems.

[17]  Shang-Hong Lai,et al.  People Localization in a Camera Network Combining Background Subtraction and Scene-Aware Human Detection , 2011, MMM.

[18]  Matthew Turk,et al.  Multisensory embedded pose estimation , 2011, 2011 IEEE Workshop on Applications of Computer Vision (WACV).

[19]  E. Martin.  Novel method for stride length estimation with body area network accelerometers , 2011, 2011 IEEE Topical Conference on Biomedical Wireless Technologies, Networks, and Sensing Systems.

[20]  Ruzena Bajcsy,et al.  Determination of a Patient's Speed and Stride Length Minimizing Hardware Requirements , 2011, 2011 International Conference on Body Sensor Networks.