Reduced Search Space for Rapid Bicycle Detection
Author
Summary, in English
particular, the application addressed is from video recorded in a live environment. The future aim from the
results in this paper is to investigate a full year of video data. Hence, processing speed is of great concern.
The proposed solution involves the use of an object detector and a search space reduction method based on
prior knowledge regarding the application at hand. The method using prior knowledge utilizes random sample
consensus, and additional statistical analysis on detection outputs, in order to define a reduced search space. It
is experimentally shown that, in the application addressed, it is possible to reduce the full search space by 62%
with the proposed methodology. This approach, which employs a full detector in combination with the design
of a simple and fast model that can capture prior knowledge for a specific application, leads to a reduced search
space and thereby a significantly improved processing speed.
Department/s
- Mathematics (Faculty of Engineering)
- Transport and Roads
- Mathematical Imaging Group
Publishing year
2013
Language
English
Publication/Series
[Host publication title missing]
Document type
Conference paper
Publisher
SciTePress
Topic
- Computer Vision and Robotics (Autonomous Systems)
- Mathematics
Keywords
- Bicycle Detection
- Search Space
- RANSAC
- SMQT
- split up SNoW
Conference name
2nd International Conference on Pattern Recognition Applications and Methods (ICPRAM 2013)
Conference date
2013-02-15 - 2013-02-18
Conference place
Barcelona, Spain
Status
Published
Research group
- Mathematical Imaging Group