Salient Point Tracking for Key Frames Selection in Outdoor Image Sequences

摘要

Key frames are of great importance in applications where it is necessary to reduce information redundancy in the images, estimate a moving camera's pose efficiently, or make precise 3D reconstructions. Realtime key frame selection is commonly done by tracking many salient points until a certain percentage is no longer visible. The Fundamental-based tracker is an algorithm that maintains consistent correspondences through successive frames using the Fundamental matrix and the Epipolar geometry. We present an algorithm for tracking hundreds of salient points in sequences of monocular images of exterior urban and aquatic scenes. We extend the Fundamental- based tracker to discover points that are not extracted by the local feature detector because these points are below a threshold of detection. We employ the information of the scene geometry, the image appearance, and the apparent motion dynamics to find these points. This proposal allows maintaining many stable tracks for a longer time. We carry out an experimental evaluation on three very different image sequences captured by a single camera mounted on wheeled and underwater vehicles. Our algorithm shows a reliable tracking performance compared with the Pyramidal Lucas-Kanade tracker, at processing rates of 4 to 9 frames per second on a laptop.