A new feature detector and stereo matching method for accurate high-performance sparse stereo matching

Abstract

Abstract-Hardware platforms with limited processing power are often incapable of running dense stereo analysis algorithms at acceptable speed. Sparse algorithms provide an alternative but generally lack in accuracy. To overcome this predicament, we present an efficient sparse stereo analysis algorithm that applies a dense consistency check, leading to accurate matching results. We further improve matching accuracy by introducing a new feature detector based on FAST, which exhibits a less clustered feature distribution. The new feature detector leads to a superior performance of our stereo analysis algorithm. Performance evaluation shows that the proposed stereo matching system achieves processing rates above 200 frames per second on a commodity dual core CPU, and faster than video frame-rate processing on a lowperformance embedded platform. The stereo matching results prove to be superior to those obtained with ordinary sparse matching algorithms.

Efficient onbard RGBD-SLAM for autonomous MAVs

“…Since keyframe creation has to be fast, we apply a FAST corner detector on multiple pyramid levels. As also noticed in [15], FAST corners tend to flock to image regions with high contrast whereas there might be some regions with no FAST corners at all. We tackle this problem by detecting many FAST corners more than needed and assigning each to one of n × n grid cells within the image.…”

On-Board Dual-Stereo-Vision for the Navigation of an Autonomous MAV

“…Because sparse stereo matching is much faster than any dense algorithm, this MAV can maintain a high pose estimation rate of 30 Hz. This high performance can be credited to the efficiency of PTAM as well as to the efficiency of the used sparse stereo algorithm, which was previously published in [15]. Because this method appears to be much faster than all other existing approaches, it makes the most promising base for creating an MAV capable of simultaneously processing the imagery of two stereo cameras.…”

“…The two algorithms published in [15], for which an efficient open source implementation is available, are used for both of these tasks. Feature detection is, however, extended to include a scale space and an upper bound for the total number of features.…”

On-board dual-stereo-vision for autonomous quadrotor navigation

“…Because sparse stereo matching is much faster than any dense algorithm, this MAV can maintain a high pose estimation rate of 30 Hz. This high performance can be credited to the efficiency of PTAM as well as to the efficiency of the used sparse stereo algorithm, which was previously published in [17]. Because this method appears to be much faster than all other existing approaches, it makes the most promising base for creating an MAV capable of simultaneously processing the imagery of two stereo cameras.…”

“…The two algorithms published in [17], for which an efficient open source implementation is available, are used for both of these tasks. Feature detection is, however, extended to include a scale space and an upper bound for the total number of features.…”