Three-dimensional computer vision: a geometric viewpoint
Three-dimensional computer vision: a geometric viewpoint
The Active Recovery of 3D Motion Trajectories and Their Use in Prediction
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Flexible New Technique for Camera Calibration
IEEE Transactions on Pattern Analysis and Machine Intelligence
Event Detection and Analysis from Video Streams
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Multi-view Method for Gait Recognition Using Static Body Parameters
AVBPA '01 Proceedings of the Third International Conference on Audio- and Video-Based Biometric Person Authentication
A Four-step Camera Calibration Procedure with Implicit Image Correction
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Event Detection by Eigenvector Decomposition Using Object and Frame Features
CVPRW '04 Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 7 - Volume 07
3D Reconstruction by Fitting Low-Rank Matrices with Missing Data
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Multi-View Geometry for General Camera Models
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Hi-index | 0.00 |
Current computer vision algorithms can process video sequences and perform key low-level functions, such as motion detection, motion tracking, and object classification. This motivates activity detection (e.g. recognizing people's behavior and intent), which is becoming increasingly important. However, they all have severe performance limitations when used over an extended range of applications. They suffer from high false detection rates and missing detection rates, or loss of track due to partial occlusions, etc. Also, activity detection is limited to 2D image domain and is confined to qualitative activities (such as a car entering a region of interest). Adding 3D information will increase the performance of all computer vision algorithms and the activity detection system. In this paper, we propose a unique approach which creates a 3D site model via sensor fusion of laser range finder and a single camera, which then can convert the symbolic features (pixel based) of each object to physical features (e.g. feet or yards). We present experimental results to demonstrate our 3D site model.