Towards space-time semantics in two frames

Authors:
Karla Brkić;Axel Pinz;Zoran Kalafatić;Siniša Šegvić
Affiliations:
Faculty of Electrical Engineering and Computing, University of Zagreb, Croatia;Graz University of Technology, Austria;Faculty of Electrical Engineering and Computing, University of Zagreb, Croatia;Faculty of Electrical Engineering and Computing, University of Zagreb, Croatia
Venue:
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part III
Year:
2012

Citing 12
Cited 0

Dynamic Textures

International Journal of Computer Vision
Space-time Interest Points

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Motion Segmentation Using Occlusions

IEEE Transactions on Pattern Analysis and Machine Intelligence
On Space-Time Interest Points

International Journal of Computer Vision
Efficient Visual Event Detection Using Volumetric Features

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Local detection of occlusion boundaries in video

Image and Vision Computing
Histogram-based description of local space-time appearance

SCIA'11 Proceedings of the 17th Scandinavian conference on Image analysis
Interesting Interest Points

International Journal of Computer Vision
Detecting spatiotemporal structure boundaries: beyond motion discontinuities

ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part II
Learning hierarchical invariant spatio-temporal features for action recognition with independent subspace analysis

CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Spacetime Texture Representation and Recognition Based on a Spatiotemporal Orientation Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
An efficient fully unsupervised video object segmentation scheme using an adaptive neural-network classifier architecture

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a novel, low-level scheme to analyze spatial and temporal change within a local support region. Assuming available region correspondences between two adjacent frames, we divide each region into a regular grid of patches. Depending on the change of an image function inside the patch over time, each patch is assigned weights for the following four labels: "C" for a constant patch, "O" when new information originates from outside the support region, "I" for "inner" changes, and "N" for information from neighboring patches. Our method goes beyond optical flow, as it provides an additional semantic level of understanding the changes in space-time. We demonstrate how our novel "COIN" scheme can be used to categorize local space-time events in image pairs, including locally planar support regions, 3D discontinuities, and virtual vs. real crossings of 3D structures.