Detecting Moving Regions in CrowdCam Images

TL;DR

This paper presents a novel method for detecting moving regions in CrowdCam images by aggregating probabilistic match information across image pairs, effectively identifying dynamic scene parts without prior scene knowledge.

Contribution

The proposed approach introduces a probabilistic matching framework that leverages epipolar geometry constraints to detect dynamic regions in CrowdCam images without scene or camera prior.

Findings

Effective detection of dynamic regions demonstrated on challenging datasets

No prior scene or camera information required for the method

High-quality dynamic probability maps produced for each image

Abstract

We address the novel problem of detecting dynamic regions in CrowdCam images, a set of still images captured by a group of people. These regions capture the most interesting parts of the scene, and detecting them plays an important role in the analysis of visual data. Our method is based on the observation that matching static points must satisfy the epipolar geometry constraints, but computing exact matches is challenging. Instead, we compute the probability that a pixel has a match, not necessarily the correct one, along the corresponding epipolar line. The complement of this probability is not necessarily the probability of a dynamic point because of occlusions, noise, and matching errors. Therefore, information from all pairs of images is aggregated to obtain a high quality dynamic probability map, per image. Experiments on challenging datasets demonstrate the effectiveness of the algorithm on a broad range of settings; no prior knowledge about the scene, the camera characteristics or the camera locations is required.