Show simple item record

dc.contributor.authorShimizu, Hiroaki
dc.contributor.authorPoggio, Tomaso
dc.date.accessioned2005-12-19T22:32:54Z
dc.date.available2005-12-19T22:32:54Z
dc.date.issued2003-08-27
dc.identifier.otherMIT-CSAIL-TR-2003-013
dc.identifier.otherAIM-2003-020
dc.identifier.otherCBCL-230
dc.identifier.urihttp://hdl.handle.net/1721.1/30397
dc.description.abstractThe capability of estimating the walking direction of people would be useful in many applications such as those involving autonomous cars and robots.We introduce an approach for estimating the walking direction of people from images, based on learning the correct classification of a still image by using SVMs. We find that the performance of the system can be improved by classifying each image of a walking sequence and combining the outputs of the classifier.Experiments were performed to evaluate our system and estimate the trade-off between number of images in walking sequences and performance.
dc.format.extent11 p.
dc.format.extent12026063 bytes
dc.format.extent489901 bytes
dc.format.mimetypeapplication/postscript
dc.format.mimetypeapplication/pdf
dc.language.isoen_US
dc.relation.ispartofseriesMassachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory
dc.subjectAI
dc.subjectpedestrian
dc.subjectwalking direction
dc.subjectclassification
dc.subjectSVM
dc.subjectrecognition
dc.subjecthuman motion
dc.titleDirection Estimation of Pedestrian from Images


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record