Object detection using a cascade of 3d models

Authors:
Hon-Keat Pong;Tat-Jen Cham
Affiliations:
School of Computer Engineering, Nanyang Technological University, Singapore;School of Computer Engineering, Nanyang Technological University, Singapore
Venue:
ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part II
Year:
2006

Citing 8
Cited 1

Elements of information theory

Elements of information theory
Surface simplification using quadric error metrics

Proceedings of the 24th annual conference on Computer graphics and interactive techniques
3D Pose Estimation by Directly Matching Polyhedral Models to Gray Value Gradients

International Journal of Computer Vision
Model-Based Localisation and Recognition of Road Vehicles

International Journal of Computer Vision
A survey of free-form object representation and recognition techniques

Computer Vision and Image Understanding
Unsupervised Learning of Models for Recognition

ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part I
Mutual Information Based Evaluation of 3D Building Models

ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 3 - Volume 3
Alignment by maximization of mutual information

Alignment by maximization of mutual information

Alignment of 3d models to images using region-based mutual information and neighborhood extended gaussian images

ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present an alignment framework for object detection using a hierarchy of 3D polygonal models. One difficulty with alignment methods is that the high-dimensional transformation space makes finding potential candidate states a time-consuming task. This is an important consideration in our approach, as an exhaustive search is applied on a densely-sampled state space in order to avoid local minima and to extract all possible candidates. In our framework, a level-of-detail (LOD) 3D geometric model hierarchy is generated for the target object. Each of this model acts as a classifier to determine which of the discrete states are potential candidates. The classification is done through the estimation of pixel and edge-based mutual information between the 3D model and the image, where the classification speed significantly depends on the LOD and resolution of the image. By combining these models of various LOD into a cascade, we show that search time can be reduced significantly while accuracy is maintained.