A Multibody Factorization Method for Independently Moving Objects
International Journal of Computer Vision
Mean Shift: A Robust Approach Toward Feature Space Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Multibody Structure and Motion: 3-D Reconstruction of Independently Moving Objects
ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part I
A multi-body factorization method for motion analysis
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
MonoSLAM: Real-Time Single Camera SLAM
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Model-Selection Framework for Multibody Structure-and-Motion of Image Sequences
International Journal of Computer Vision
Coupled Object Detection and Tracking from Static Cameras and Moving Vehicles
IEEE Transactions on Pattern Analysis and Machine Intelligence
Improving the Agility of Keyframe-Based SLAM
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part II
Parallel Tracking and Mapping for Small AR Workspaces
ISMAR '07 Proceedings of the 2007 6th IEEE and ACM International Symposium on Mixed and Augmented Reality
Online/Realtime Structure and Motion for General Camera Models
WACV '08 Proceedings of the 2008 IEEE Workshop on Applications of Computer Vision
Multibody Structure-from-Motion in Practice
IEEE Transactions on Pattern Analysis and Machine Intelligence
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part IV
Histogram-based description of local space-time appearance
SCIA'11 Proceedings of the 17th Scandinavian conference on Image analysis
| Hi-index | 0.00 |
We present a novel online method to model independent foreground motion by using solely traditional structure and motion (S+M) algorithms. On the one hand, the visible static scene can be reconstructed and on the other hand, the position and orientation (pose) of the observer (mobile camera) are estimated. Additionally, we use 3D-outlier analysis for foreground motion detection and tracking. First, we cluster the available 3D-information such that, with high probability, each cluster corresponds to a moving object. Next, we establish a purely geometrybased object representation that can be used to reliably estimate each object's pose. Finally, we extend the purely geometry-based object representation and add local descriptors to solve the loop closing problem for the underlying S+M algorithm. Experimental results on single and multi-object video data demonstrate the viability of this method. Major results include the computation of a stable representation of moving foreground objects, basic recognition possibilities due to descriptors, and motion trajectories that can be used for motion analysis of objects. Our novel multibody structure and motion (MSaM) approach runs online and can be used to control active surveillance systems in terms of dynamic scenes, observer pose, and observer-to-object pose estimation, or to enrich available information in existing appearance- and shape-based object categorization.