Flow Counting Using Realboosted Multi-sized Window Detectors
(2012) 3rd IEEE International Workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Streams (ARTEMIS 2012) In Lecture notes in computer science 7585. p.193-202- Abstract
- One classic approach to real-time object detection is to use adaboost to a train a set of look up tables of discrete features. By utilizing a discrete feature set, from features such as local binary patterns, efficient classifiers can be designed. However, these classifiers include interpolation operations while scaling the images over various scales. In this work, we propose the use of real valued weak classifiers which are designed on different scales in order to avoid costly interpolations. The use of real valued weak classifiers in combination with the proposed method avoiding interpolation leads to substantially faster detectors compared to baseline detectors. Furthermore, we investigate the speed and detection performance of such... (More)
- One classic approach to real-time object detection is to use adaboost to a train a set of look up tables of discrete features. By utilizing a discrete feature set, from features such as local binary patterns, efficient classifiers can be designed. However, these classifiers include interpolation operations while scaling the images over various scales. In this work, we propose the use of real valued weak classifiers which are designed on different scales in order to avoid costly interpolations. The use of real valued weak classifiers in combination with the proposed method avoiding interpolation leads to substantially faster detectors compared to baseline detectors. Furthermore, we investigate the speed and detection performance of such classifiers and their impact on tracking performance. Results indicate that the realboost framework combined with the proposed scaling framework achieves an 80% speed up over adaboost with bilinear interpolation. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/19103977-c682-46eb-836e-5169a56a62e9
- author
- Ardö, Håkan LU ; Nilsson, Mikael LU and Berthilsson, Rikard LU
- organization
- publishing date
- 2012
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- Computer Vision – ECCV 2012. Workshops and Demonstrations : Florence, Italy, October 7-13, 2012, Proceedings, Part III - Florence, Italy, October 7-13, 2012, Proceedings, Part III
- series title
- Lecture notes in computer science
- volume
- 7585
- pages
- 193 - 202
- publisher
- Springer
- conference name
- 3rd IEEE International Workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Streams (ARTEMIS 2012)
- conference location
- Florence, Italy
- conference dates
- 2012-10-13 - 2012-10-13
- external identifiers
-
- scopus:84867696956
- ISSN
- 0302-9743
- 1611-3349
- ISBN
- 978-3-642-33885-4
- 978-3-642-33884-7
- DOI
- 10.1007/978-3-642-33885-4_20
- language
- English
- LU publication?
- yes
- id
- 19103977-c682-46eb-836e-5169a56a62e9
- date added to LUP
- 2017-10-19 13:07:44
- date last changed
- 2024-01-14 07:55:56
@inproceedings{19103977-c682-46eb-836e-5169a56a62e9, abstract = {{One classic approach to real-time object detection is to use adaboost to a train a set of look up tables of discrete features. By utilizing a discrete feature set, from features such as local binary patterns, efficient classifiers can be designed. However, these classifiers include interpolation operations while scaling the images over various scales. In this work, we propose the use of real valued weak classifiers which are designed on different scales in order to avoid costly interpolations. The use of real valued weak classifiers in combination with the proposed method avoiding interpolation leads to substantially faster detectors compared to baseline detectors. Furthermore, we investigate the speed and detection performance of such classifiers and their impact on tracking performance. Results indicate that the realboost framework combined with the proposed scaling framework achieves an 80% speed up over adaboost with bilinear interpolation.}}, author = {{Ardö, Håkan and Nilsson, Mikael and Berthilsson, Rikard}}, booktitle = {{Computer Vision – ECCV 2012. Workshops and Demonstrations : Florence, Italy, October 7-13, 2012, Proceedings, Part III}}, isbn = {{978-3-642-33885-4}}, issn = {{0302-9743}}, language = {{eng}}, pages = {{193--202}}, publisher = {{Springer}}, series = {{Lecture notes in computer science}}, title = {{Flow Counting Using Realboosted Multi-sized Window Detectors}}, url = {{http://dx.doi.org/10.1007/978-3-642-33885-4_20}}, doi = {{10.1007/978-3-642-33885-4_20}}, volume = {{7585}}, year = {{2012}}, }