This paper presents a novel approach to categorize multi-view vehicles in complex background using only two dimension characteristic vectors instead of high dimension vectors. Vehicles have large variability of models and the view-point makes the appearance change dramatically. Significant characteristics should be chosen as the evidence to categorize. In this paper, we categorize the vehicles into two categories – cars and lorries. Line detection method is used and calculating the average line length and the number of parallel lines as the two characteristics. A linear classifier is trained using 30 different view cars and lorries as the training set and an 10 additional different cars and lorries as the testing set.
Vehicles Categorization in Complex Background
Advanced Materials Research ; 998-999 ; 708-711
2014-07-30
4 pages
Article (Journal)
Electronic Resource
English
CATEGORIZATION OF VEHICLES IN THE SURROUNDINGS OF A MOTOR VEHICLE
European Patent Office | 2019
|Categorization of vehicles in the surroundings of a motor vehicle
European Patent Office | 2022
|