Title :
Vehicle segmentation and classification using deformable templates
Author :
Jolly, Marie-Pierre Dubuisson ; Lakshmanan, Sridhar ; Jain, Anil K.
Author_Institution :
Siemens Corp. Res. Inc., Princeton, NJ, USA
fDate :
3/1/1996 12:00:00 AM
Abstract :
This paper proposes a segmentation algorithm using deformable template models to segment a vehicle of interest both from the stationary complex background and other moving vehicles in an image sequence. We define a polygonal template to characterize a general model of a vehicle and derive a prior probability density function to constrain the template to be deformed within a set of allowed shapes. We propose a likelihood probability density function which combines motion information and edge directionality to ensure that the deformable template is contained within the moving areas in the image and its boundary coincides with strong edges with the same orientation in the image. The segmentation problem is reduced to a minimization problem and solved by the Metropolis algorithm. The system was successfully tested on 405 image sequences containing multiple moving vehicles on a highway
Keywords :
Bayes methods; computer vision; edge detection; image classification; image segmentation; image sequences; motion estimation; probability; road traffic; road vehicles; simulated annealing; traffic control; Bayesian inference; Metropolis algorithm; deformable template models; edge directionality; image classification; image sequence; minimization; motion information; polygonal template; probability density function; simulated annealing; travel time estimation; vehicle image segmentation; Bayesian methods; Cameras; Deformable models; Image segmentation; Image sequences; Intelligent transportation systems; Licenses; Probability density function; Road vehicles; Shape;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on