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 dist… Show more
“…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.…”
Abstract-We present a computationally inexpensive RGBD-SLAM solution taylored to the application on autonomous MAVs, which enables our MAV to fly in an unknown environment and create a map of its surroundings completely autonomously, with all computations running on its onboard computer. We achieve this by implementing efficient methods for both tracking its current location with respect to a heavily processed previously seen RGBD image (keyframe) and efficient relative registration of a set of keyframes using bundle adjustment with depth constraints as a front-end for pose graph optimization. We prove the accuracy and efficiency of our system based on a public benchmark dataset and demonstrate that the proposed method enables our quadrotor to fly autonomously.
“…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.…”
Abstract-We present a computationally inexpensive RGBD-SLAM solution taylored to the application on autonomous MAVs, which enables our MAV to fly in an unknown environment and create a map of its surroundings completely autonomously, with all computations running on its onboard computer. We achieve this by implementing efficient methods for both tracking its current location with respect to a heavily processed previously seen RGBD image (keyframe) and efficient relative registration of a set of keyframes using bundle adjustment with depth constraints as a front-end for pose graph optimization. We prove the accuracy and efficiency of our system based on a public benchmark dataset and demonstrate that the proposed method enables our quadrotor to fly autonomously.
“…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.…”
Section: Related Workmentioning
confidence: 99%
“…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.…”
Section: Processing Of Forward-facing Camerasmentioning
We present a quadrotor Micro Aerial Vehicle (MAV) equipped with four cameras, which are arranged in two stereo configurations. The MAV is able to perform stereo matching for each camera pair on-board and in real-time, using an efficient sparse stereo method. In case of the camera pair that is facing forward, the stereo matching results are used for a reduced stereo SLAM system. The other camera pair, which is facing downwards, is used for ground plane detection and tracking. Hence, we are able to obtain a full 6DoF pose estimate from each camera pair, which we fuse with inertial measurements in an extended Kalman filter. Special care is taken to compensate various drift errors. In an evaluation we show that using two instead of one camera pair significantly increases the pose estimation accuracy and robustness.
“…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.…”
Section: Related Workmentioning
confidence: 99%
“…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.…”
Section: Processing Of Forward-facing Camerasmentioning
Abstract-We present a quadrotor Micro Aerial Vehicle (MAV) capable of autonomous indoor navigation. The MAV is equipped with four cameras arranged in two stereo configurations. One camera pair is facing forward and serves as input for a reduced stereo SLAM system. The other camera pair is facing downwards and is used for ground plane detection and tracking. All processing, including sparse stereo matching, is run on-board in real-time and at high processing rates. We demonstrate the capabilities of this MAV design in several flight experiments. Our MAV is able to recover from pose estimation errors and can cope with processing failures for one camera pair. We show that by using two camera pairs instead of one, we are able to significantly increase navigation accuracy and robustness.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.