Surveillance video indexing and retrieval |
This is a summary of my Phd work. Read my Phd thesis to have
detailed information. The goal of my Phd work is to propose a general approach for
surveillance video indexing and retrieval. Based on the hypothesis
that videos are preprocessed by an external video analysis module,
this approach is composed of two phases:indexing phase and retrieval phase.
![](images/architecture8.JPG)
Fig 1. Architecture of the proposed approach
Indexing phase:
In order to profit from the output of various video analysis modules, a
general data model consisting of two main concepts objects and events,
is proposed.
Firstly, two new key blob detection methods in the object representation task choose for each detected object a set of key blobs associated with a weight. (cf. Fig 2)
![](images/person100.jpg)
Fig 2. Representative blobs for a detected and tracked person
Retrieval phase:
The retrieval phase starts with a user query and is composed of 4
tasks. In the formulation task, user expresses his query in a new
rich query language. This query is then analyzed by the syntax parsing task. A new matching method based on EMD (Earth Movers Distance) in the matching task aims at
retrieving effectively relevant results [2]. Two proposed methods in the
relevance feedback task allow to interact with the user in order to
improve retrieved results[3].
|
Keywords : indexing, retrieval, matching, relevance feedback |
Download: the implementation of EMD, mobile object matching in C++ are avaible. Please send me an email. |
Main publications |
[1] Thi-Lan Le, Alain Boucher, Monique Thonnat, Francois Brémond, Surveillance video indexing and retrieval using object features and semantic events, International Journal of Pattern Recognition and Artificial Intelligence (IJPRAI), Special issue on Visual Analysis and Understanding for Surveillance Applications, Vol. 23, num. 7, 2009.
[pdf] |
[2] Thi-Lan Le, Monique Thonnat, Alain Boucher, Francois Brémond, Appearance based retrieval for tracked objects in surveillance videos, ACM International Conference on Image and Video Retrieval (CIVR), July 8-10, 2009, Santorini, Greece.
|
[3] Thi-Lan Le, Relevance feedback for surveillance video retrieval at object level, The 2nd FTRA International Workshop on Multimedia and Semantic Technologies (MUST), 2011, Greece
|
|