“…There exists, however, at least one example for sparse stereo matching with a forwardfacing camera pair [14]. Here, the sparsely matched features are used for a modified version of the SLAM method presented in [17], which itself is an extension of PTAM that incorporates depth information.…”
Section: Related Workmentioning
confidence: 99%
“…For the forward-facing cameras we use a method that largely matches the processing pipeline described in [14]. We improved the performance of this method mainly through code level optimizations and by resolving one problem in the original PTAM code, which in case of small maps causes Bundle Adjustment to be executed too frequently.…”
Section: Processing Of Forward-facing Camerasmentioning
confidence: 99%
“…Those extensions will be explained later, when their necessity becomes apparent. For completeness, we provide a summary of the original method from [14] at this point.…”
Section: Processing Of Forward-facing Camerasmentioning
confidence: 99%
“…Feature detection is, however, extended to include a scale space and an upper bound for the total number of features. We set our bound to 800 features, which is less than the 1000 features used in [14]. An example for the performance of this stereo method during indoor flight of our MAV is given in Fig.…”
Section: Processing Of Forward-facing Camerasmentioning
confidence: 99%
“…Here, the IMU measurements are used for performing the Kalman prediction, while the Kalman correction is then executed with the estimated pose. Unlike in [14], we process the IMU measurements at a higher rate of 100 Hz.…”
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.
“…There exists, however, at least one example for sparse stereo matching with a forwardfacing camera pair [14]. Here, the sparsely matched features are used for a modified version of the SLAM method presented in [17], which itself is an extension of PTAM that incorporates depth information.…”
Section: Related Workmentioning
confidence: 99%
“…For the forward-facing cameras we use a method that largely matches the processing pipeline described in [14]. We improved the performance of this method mainly through code level optimizations and by resolving one problem in the original PTAM code, which in case of small maps causes Bundle Adjustment to be executed too frequently.…”
Section: Processing Of Forward-facing Camerasmentioning
confidence: 99%
“…Those extensions will be explained later, when their necessity becomes apparent. For completeness, we provide a summary of the original method from [14] at this point.…”
Section: Processing Of Forward-facing Camerasmentioning
confidence: 99%
“…Feature detection is, however, extended to include a scale space and an upper bound for the total number of features. We set our bound to 800 features, which is less than the 1000 features used in [14]. An example for the performance of this stereo method during indoor flight of our MAV is given in Fig.…”
Section: Processing Of Forward-facing Camerasmentioning
confidence: 99%
“…Here, the IMU measurements are used for performing the Kalman prediction, while the Kalman correction is then executed with the estimated pose. Unlike in [14], we process the IMU measurements at a higher rate of 100 Hz.…”
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.
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.