Video Analysis

Research

Person Re-Identification

Long-duration tracking of individuals across large sites is a challenge. Trucks of individuals from disjoint fields of view need to be linked, despite the sa...

Activity Recognition

Providing a semantic interpretation of the actions and interactions between the actors in a scene enables behavior analysis for automated decision-making. Th...

Video Tracking

Video tracking is the process of localizing an object in video at every time instant. It is a challenging problem especially when there are multiple objects ...

Dynamic Textures

One of the most important elements of modern Computer Vision is the concept of image texture, or simply texture. Depending on the task at hand (e.g. image-ba...

Resources

HAUS Dataset

Repository of the Human Activities Under Surveillance video dataset.

Posts

Video Understanding

9 minute read

Video understanding is concerned with the parsing of the image data flow for the semantic understanding of the objects in the scene, but also their actions a...

Human Interactions

2 minute read

Recognizing human interactions from video is an important step forward towards the long-term goal of performing scene understanding fully automatically. Rece...

Transfer Learning from Multiple Sources

2 minute read

Transfer learning allows leveraging the knowledge of source domains, available a priori, to help training a classifier for a target domain, where the availab...

Video Surveillance

7 minute read

Increasingly, large networks of surveillance cameras are employed to monitor public and private facilities. This continuous collection of imagery has the pot...

Aerial Video Analysis

8 minute read

In aerial video moving objects of interest are typically very small, and being able to detect them is key to enable tracking. There are detection methods tha...

People Detection

3 minute read

People detection and tracking in video are fundamental Computer Vision capabilities that still constitute a research challenge. Important difficulties are du...

Dynamic Texture Segmentation

2 minute read

Segmenting the image plane of video sequences is often one of the first steps towards the analysis of video. A lot of effort has been spent on developing ima...

Dynamic Texture Recognition

2 minute read

Recognition of objects based on their images is one of the central problems in modern Computer Vision. Objects can be characterized by their geometric, photo...

Publications

AVSS
A model change detection approach to dynamic scene modeling Kim, S. J., Doretto, G., Rittscher, J., Tu, P., Krahnstoever, N., and Pollefeys, M. In IEEE International Conference on Advanced Video and Signal Based Surveillance, 2009. Oral abstract bibTeX pdf
In this work we propose a dynamic scene model to provide information about the presence of salient motion in the scene, and that could be used for focusing the attention of a pan/tilt/zoom camera, or for background modeling purposes. Rather than proposing a set of saliency detectors, we define what we mean by salient motion, and propose a precise model for it. Detecting salient motion becomes equivalent to detecting a model change. We derive optimal online procedures to solve this problem, which enable a very fast implementation. Promising results show that our model can effectively detect salient motion even in severely cluttered scenes, and while a camera is panning and tilting.
```
@inproceedings{kimDRTKP09avss,
  abbr = {AVSS},
  author = {Kim, S. J. and Doretto, G. and Rittscher, J. and Tu, P. and Krahnstoever, N. and Pollefeys, M.},
  title = {A model change detection approach to dynamic scene modeling},
  booktitle = {IEEE International Conference on Advanced Video and Signal Based
  	Surveillance},
  year = {2009},
  pages = {490--495},
  month = sep,
  bib2html_pubtype = {Conferences},
  bib2html_rescat = {Video Analysis, Dynamic Textures, Visual Motion Detection},
  file = {kimDRTKP09avss.pdf:doretto\\conference\\kimDRTKP09avss.pdf:PDF},
  keywords = {dynamic scene modeling, video analysis, PTZ camera, focus-ofattention, background
  	modeling, sequential generalized likelihood ratio, model change detection,
  	linear dynamical systems, dynamic textures},
  owner = {doretto},
  timestamp = {2009.09.28},
  wwwnote = {Oral}
}
```
Event recognition with fragmented object tracks Chan, M., Hoogs, A., Sun, Z., Schmiederer, J., Bhotika, R., and Doretto, G. Technical Report 2006GRC038, GE Global research, 2006. Visualization and Computer Vision Laboratory abstract bibTeX
Complete and accurate video tracking is very difficult to achieve in practice due to occlusions, traffic, shadows and appearance changes. In this paper, we study the feasibility of event recognition when object tracks are fragmented at various levels. By changing the lock score threshold controlling track termination, different levels of track fragmentation are generated. In addition, the data contains lengthy occlusions of objects involved in the events. The effect on event recognition is revealed by examining the event model match score as a function of lock score threshold. Using a Dynamic Bayes network to model events, it is shown that event recognition improves with greater track fragmentation, assuming fragmented tracks for the same object are linked together. This is counter-intuitive, as it implies that event recognition works better as tracking degrades. The experiments also show that the model is capable of handling long tracking gaps. The study is conducted on busy scenes of airplane servicing activities, with occlusions lasting hundreds of frames, object appearance changes and significant clutter traffic.
```
@techreport{chanHSSBD06tr,
  author = {Chan, M. and Hoogs, A. and Sun, Z. and Schmiederer, J. and Bhotika, R. and Doretto, G.},
  title = {Event recognition with fragmented object tracks},
  institution = {GE Global research},
  year = {2006},
  number = {2006GRC038},
  address = {Niskayuna, NY, USA},
  month = jan,
  note = {Visualization and Computer Vision Laboratory},
  bib2html_pubtype = {Tech Reports},
  bib2html_rescat = {Video Analysis, Event Recognition},
  file = {chanHSSBD06tr.pdf:doretto\\report\\chanHSSBD06tr.pdf:PDF;chanHSSBD06tr.pdf:doretto\\report\\chanHSSBD06tr.pdf:PDF},
  keywords = {Video Analysis, event recognition, semantics, dynamic bayesian
  	network, video analysis},
  owner = {doretto},
  timestamp = {2006.11.29}
}
```