A single-view based framework for robust estimation of heights and positions of moving people

In recent years, there has been increased interest in characterizing 3D information from video sequences for human tracking/identification. In this paper, we propose a single view-based framework for robust estimation of height and position. In the proposed work, 2D features of a target object are back-projected into the 3D scene where its coordinate system is given by a rectangular marker. Then the position and height are measured in the scene space. In addition, geometric error caused by inaccurate projective mapping is corrected by using geometric constraints provided by the marker. The accuracy and robustness are verified on the experimental results of several video sequences from outdoor environments.

[1]  Tieniu Tan,et al.  A survey on visual surveillance of object motion and behaviors , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[2]  Azriel Rosenfeld,et al.  Tracking Groups of People , 2000, Comput. Vis. Image Underst..

[3]  Sudeep Sarkar,et al.  Improved gait recognition by gait dynamics normalization , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Zhengyou Zhang,et al.  A Flexible New Technique for Camera Calibration , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Larry S. Davis,et al.  Multi-camera Tracking and Segmentation of Occluded People on Ground Plane Using Search-Guided Particle Filtering , 2006, ECCV.

[6]  László Havasi,et al.  Detection of Gait Characteristics for Scene Registration in Video Surveillance System , 2007, IEEE Transactions on Image Processing.

[7]  Tieniu Tan,et al.  Principal axis-based correspondence between multiple cameras for people tracking , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Larry S. Davis,et al.  View-invariant Estimation of Height and Stride for Gait Recognition , 2002, Biometric Authentication.

[9]  Marie-Odile Berger,et al.  Calibration errors in augmented reality: a practical study , 2005, Fourth IEEE and ACM International Symposium on Mixed and Augmented Reality (ISMAR'05).

[10]  O. Faugeras.  Three-dimensional computer vision: a geometric viewpoint , 1993 .

[11]  Ian D. Reid,et al.  Single View Metrology , 2000, International Journal of Computer Vision.

[12]  Mubarak Shah,et al.  Consistent Labeling of Tracked Objects in Multiple Cameras with Overlapping Fields of View , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Sing Bing Kang,et al.  Parameter-Free Radial Distortion Correction with Center of Distortion Estimation , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Antonio Criminisi,et al.  Accurate Visual Metrology from Single and Multiple Uncalibrated Images , 2001, Distinguished Dissertations.

[15]  Larry S. Davis,et al.  W4: Real-Time Surveillance of People and Their Activities , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Olivier Faugeras,et al.  Three-Dimensional Computer Vision , 1993 .

[17]  Mubarak Shah,et al.  A Multiview Approach to Tracking People in Crowded Scenes Using a Planar Homography Constraint , 2006, ECCV.

[18]  Larry S. Davis,et al.  Person identification using automatic height and stride estimation , 2002, Object recognition supported by user interaction for service robots.

[19]  Larry S. Davis,et al.  Non-parametric Model for Background Subtraction , 2000, ECCV.

[20]  Lily Lee,et al.  Monitoring Activities from Multiple Video Streams: Establishing a Common Coordinate Frame , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Antonio Criminisi,et al.  Creating Architectural Models from Images , 1999, Comput. Graph. Forum.