Learn More
—This paper describes the vision-based control of a small autonomous aircraft following a road. The computer vision system detects natural features of the scene and tracks the roadway in order to determine relative yaw and lateral displacement between the aircraft and the road. Using only the vision measurements and onboard inertial sensors, a control(More)
The present study describes the distribution and structural features of calretinin-immunoreactive neurons and fiber plexuses in the cerebral cortex of a lacertid lizard, at the light and electron microscopic levels, and also examines the colocalization of calretinin with parvalbumin and gamma-aminobutyric acid (GABA) in certain cortical regions.(More)
The morphology, distribution, and ultrastructural features of calbindin-D28k-immunoreactive neurons and fibers in the cortical regions of the lizard Psammodromus algirus, considered homologues to the mammalian hippocampal formation, were analyzed by using the peroxidase anti-peroxidase technique at the light and electron microscopic level. On the basis of(More)
Common visual servoing methods use image features to define a signal error in the feedback loops of robot motion controllers. This paper suggests a new visual servo control scheme that uses an on-line trajectory generator as an intermediate layer between image processing algorithms and robot motion controllers. The motion generation algorithm is capable of(More)
We consider some Bernoulli free boundary type problems for a general class of quasilinear elliptic (pseudomonotone) operators involving measures depending on unknown solutions. We treat those problems by applying the Ambrosetti-Rabinowitz minimax theorem to a sequence of approximate nonsingular problems and passing to the limit by some a priori estimates.(More)
—A vision-based system for detecting and classifying moving obstacles in a cluttered environment using a single camera mounted on a small unmanned aerial vehicle is presented. Feature correspondences between successive image frames are found using the SIFT algorithm, and a model of the background motion is generated by Random Sample Consensus (RANSAC). The(More)
A framework for 3D target reconstruction and relative pose estimation through fusion of vision and sparse-pattern range data (e.g. line-scanning LIDAR) is presented. The algorithm augments previous work in monocular vision-only SLAM/SfM to incorporate range data into the overall solution. The aim of this work is to enable a more dense reconstruction with(More)
Description: The primary motivation for this project lies in enabling unmanned aerial vehicles (UAVs) BLOCKIN BLOCKIN to BLOCKIN BLOCKIN detect BLOCKIN BLOCKIN and BLOCKIN BLOCKIN avoid BLOCKIN BLOCKIN other BLOCKIN BLOCKIN aircraft BLOCKIN BLOCKIN without BLOCKIN BLOCKIN the BLOCKIN BLOCKIN aid BLOCKIN BLOCKIN of BLOCKIN BLOCKIN expensive BLOCKIN BLOCKIN(More)
This milestones report details progress toward 3D target reconstruction through fusion of vision and LIDAR data. The utility of using both vision and LIDAR for on-orbit target reconstruction is first presented. The technical approach, including a new camera-LIDAR Structure from Motion (SfM) framework, is next presented, though this technical framework is(More)