A Keygraph Classification Framework for Real-Time Object Detection

Details A Keygraph Classification Framework for Real-Time Object Detection A Keygraph Classification Framework for Real-Time Object Detection

2009-01-30

arxiv.org/abs/0901.4953v1

Computer Science

Computer Vision and Pattern Recognition

9 pages, 23 figures

Scientific paper

In this paper, we propose a new approach for keypoint-based object detection. Traditional keypoint-based methods consist in classifying individual points and using pose estimation to discard misclassifications. Since a single point carries no relational features, such methods inherently restrict the usage of structural information to the pose estimation phase. Therefore, the classifier considers purely appearance-based feature vectors, thus requiring computationally expensive feature extraction or complex probabilistic modelling to achieve satisfactory robustness. In contrast, our approach consists in classifying graphs of keypoints, which incorporates structural information during the classification phase and allows the extraction of simpler feature vectors that are naturally robust. In the present work, 3-vertices graphs have been considered, though the methodology is general and larger order graphs may be adopted. Successful experimental results obtained for real-time object detection in video sequences are reported.

Affiliated with

Also associated with

No associations

Rating

A Keygraph Classification Framework for Real-Time Object Detection does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with A Keygraph Classification Framework for Real-Time Object Detection, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A Keygraph Classification Framework for Real-Time Object Detection will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-425391