Abstract
This work proposes to learn visual encodings of attention patterns\nthat enables sequential attention for object detection in real world\nenvironments. The system embeds a saccadic decision procedure in\na cascaded process where visual evidence is probed at informative\nimage locations. It is based on the extraction of information theoretic\nsaliency by determining informative local image descriptors that\nprovide selected foci of interest. The local information in terms\nof code book vector responses and the geometric information in the\nshift of attention contribute to recognition states of a Markov decision\nprocess. A Q-learner performs then performs search on useful actions\ntowards salient locations, developing a strategy of action sequences\ndirected in state space towards the optimization of information maximization.\nThe method is evaluated in outdoor object recognition and demonstrates\nefficient performance.
Original language | English |
---|---|
Title of host publication | Image Analysis |
Subtitle of host publication | 14th Scandinavian Conference, SCIA 2005, Joensuu, Finland, June 19-22, 2005. Proceedings |
Editors | Heikki Kalviainen, Jussi Parkkinen, Arto Kaarna |
Publisher | Springer |
Pages | 639-648 |
Number of pages | 10 |
ISBN (Electronic) | 978-3-540-31566-7 |
ISBN (Print) | 978-3-540-26320-3 |
DOIs | |
Publication status | Published - 2005 |
Event | 14th Scandinavian Conference on Image Analysis, SCIA 2005 - Joensuu, Finland Duration: 19 Jun 2005 → 22 Jun 2005 Conference number: 14 |
Publication series
Name | Lecture Notes in Computer Science |
---|---|
Publisher | Springer |
Volume | 3540 |
ISSN (Print) | 0302-9743 |
ISSN (Electronic) | 1611-3349 |
Conference
Conference | 14th Scandinavian Conference on Image Analysis, SCIA 2005 |
---|---|
Abbreviated title | SCIA |
Country | Finland |
City | Joensuu |
Period | 19/06/05 → 22/06/05 |