大会名称 |
---|
2009年 情報科学技術フォーラム(FIT) |
大会コ-ド |
F |
開催年 |
2009 |
発行日 |
2009/8/20 |
セッション番号 |
5H |
セッション名 |
画像認識 |
講演日 |
2009/09/03 |
講演場所(会議室等) |
H会場(9号館2F 923教室) |
講演番号 |
H-003 |
タイトル |
Comparison of Several Shape Descriptors in Order to Perform Car Recognition from a Moving Camera |
著者名 |
Briois Sebastien, Ohya Jun, Xie Yingdi, |
キーワード |
shape descriptor, car recognition, contours extraction, shape description |
抄録 |
This paper focuses on car recognition from a moving camera. After implementing a robust method to define a region of interest for the car recognition algorithm, the main issue to overcome is the choice of a suitable shape descriptor. In the past decade, several methods have been proposed. Wang, Lee [99], Alajilan [07], Han, Yang [05] constitute the main contributions to shape descriptors. The objective of this article is to test these algorithms and to compare their robustness to describe contours of a car. We first present briefly these past research works and outline their application to vehicle shapes. In a second step we perform a comparison on robustness and time computation from the different shape descriptors methods and try to propose a specific method for our objective to detect cars from a moving camera. |
本文pdf |
PDF download (200.7KB) |