Automatic Segmentation of Dynamic Objects from an Image Pair
This work addresses the challenge of segmenting moving objects in scenes for applications like robotics or surveillance, but it appears incremental as it builds on existing segmentation methods with a novel geometric twist.
The paper tackles the problem of automatically segmenting dynamic objects from a pair of images captured from different positions, using dense correspondences and saliency measures to localize interest points and a computational geometry-based approach for segmentation, achieving very good segmentation results as analyzed against manually marked ground truth.
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.