Automatic segmentation of dynamic objects from an image pair

Show simple item record

dc.contributor.author Malireddi, Sri Raghu
dc.contributor.author Raman, Shanmuganathan
dc.date.accessioned 2016-06-09T09:26:24Z
dc.date.available 2016-06-09T09:26:24Z
dc.date.issued 2016-04
dc.identifier.citation Malireddi, Sri Raghu and Raman, Shanmuganathan, "Automatic segmentation of dynamic objects from an image pair”, arXiv, Cornell University Library, DOI: arXiv:1604.04724, Apr. 2016. en_US
dc.identifier.other https://arxiv.org/abs/1604.04724
dc.identifier.uri https://repository.iitgn.ac.in/handle/123456789/2301
dc.description.abstract Automatic segmentation of objects from a single image is a challenging problem which generally requires training on large number of images. We consider the problem of automatically segmenting only the dynamic objects from a given pair of images of a scene captured from different positions. We exploit dense correspondences along with saliency measures in order to first localize the interest points on the dynamic objects from the two images. We propose a novel approach based on techniques from computational geometry in order to automatically segment the dynamic objects from both the images using a top-down segmentation strategy. We discuss how the proposed approach is unique in novelty compared to other state-of-the-art segmentation algorithms. We show that the proposed approach for segmentation is efficient in handling large motions and is able to achieve very good segmentation of the objects for different scenes. We analyse the results with respect to the manually marked ground truth segmentation masks created using our own dataset and provide key observations in order to improve the work in future. en_US
dc.description.statementofresponsibility by Sri Raghu Malireddi and Shanmuganathan Raman
dc.language.iso en_US en_US
dc.publisher Cornell University Library en_US
dc.title Automatic segmentation of dynamic objects from an image pair en_US
dc.type Preprint en_US


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search Digital Repository


Browse

My Account