Learned Models for Estimation of Rigid and ArticulatedHuman Motion from Stationary or Moving Camera
International Journal of Computer Vision
Object Oriented Motion-Segmentation for Video-Compression in theCNN-UM
Journal of VLSI Signal Processing Systems - Special issue on spatiotemporal signal processing with analog CNN visual microprocessors
Independent Motion Detection in 3D Scenes
IEEE Transactions on Pattern Analysis and Machine Intelligence
Extracting Structure from Optical Flow Using the Fast Error Search Technique
International Journal of Computer Vision
A framework for heading-guided recognition of human activity
Computer Vision and Image Understanding
Independent motion detection directly from compressed surveillance video
IWVS '03 First ACM SIGMM international workshop on Video surveillance
Joint optical flow estimation, segmentation, and 3D interpretation with level sets
Computer Vision and Image Understanding
IEEE Transactions on Pattern Analysis and Machine Intelligence
Towards direct recovery of shape and motion parameters from image sequences
Computer Vision and Image Understanding
Moving object segmentation by background subtraction and temporal analysis
Image and Vision Computing
A supervised approach in background modelling for visual surveillance
AVBPA'03 Proceedings of the 4th international conference on Audio- and video-based biometric person authentication
Determining spatial motion directly from normal flow field: a comprehensive treatment
ACCV'10 Proceedings of the 2010 international conference on Computer vision - Volume Part I
Hi-index | 0.00 |
The dimensionality of visual motion analysis can be reduced by analyzing projections of flow vector fields. In contrast to motion vector fields, these projections exhibit simple geometric properties which are invariant to the scene structure and depend only on the camera motion. Using these properties, structure and motion can be either completely or partially decoupled. We estimate motion parameters from projections of flow fields by using robust techniques, implemented in a recursive observer model. The model is applicable to general camera motion and to large field of view and requires no point correspondence. We demonstrate our projection method on the problem of detecting independently moving objects from a moving camera. Using the projection approach, the problem can be reduced to a one-dimensional optimization process which involves robust line-fitting and outlier detection. Instantaneousdetection measurements are integrated temporally using tracking and spatially applying grouping of coherently moving points.