The computation of optical flow
ACM Computing Surveys (CSUR)
A General Motion Model and Spatio-Temporal Filters forComputing Optical Flow
International Journal of Computer Vision
Reliable and Efficient Computation of Optical Flow
International Journal of Computer Vision
SAC '94 Proceedings of the 1994 ACM symposium on Applied computing
Real-Time Tracking of Moving Persons by Exploiting Spatio-Temporal Image Slices
IEEE Transactions on Pattern Analysis and Machine Intelligence
On the Fourier Properties of Discontinuous Motion
Journal of Mathematical Imaging and Vision
Spatial-feature parametric clustering applied to motion-based segmentation in camouflage
Computer Vision and Image Understanding
Subpixel estimation of normal displacements along contours using MRF-models
ICIP '95 Proceedings of the 1995 International Conference on Image Processing (Vol.2)-Volume 2 - Volume 2
Machine Vision and Applications
High-speed target tracking by fuzzy hostility-induced segmentation of optical flow field
Applied Soft Computing
An adaptive motion segmentation for automated video surveillance
EURASIP Journal on Advances in Signal Processing
Robust temporal activity templates using higher order statistics
IEEE Transactions on Image Processing
Block-matching-based motion field generation utilizing directional edge displacement
Computers and Electrical Engineering
TGSF/TLoG filter with optical flow technique for large motion detection
Machine Graphics & Vision International Journal
| Hi-index | 0.14 |
A method for the detection of motion in image sequences is presented. In this method, the intensity history at each pixel is convolved with the second derivative in time of a temporal Gaussian smoothing function. The zero crossings in a single frame of the resulting function indicate the positions of moving edges. Intensity changes in time due to illumination effects do not produce zero crossings; thus, they are not interpreted as motion by the present method. It is also shown that the spatial and temporal derivatives of this function can be used to compute the component of the optical flow that is normal to the zero-crossing contours. This computation is also insensitive to nonconvective temporal and spatial variations in the image intensity that are caused by illumination effects.