2014 · 10 citations · 18 references
ComputingAutonomous SystemsRobotics EngineeringComputer VisionSensor FusionSensorsDepth EstimationPoint Cloud ProcessingPose EstimationSensor Fusion For LocalizationSensor RegistrationTrack-to-track FusionExtrinsic CalibrationLidar SensorsLidar-based Relative NavigationMultimodal Sensor FusionPositionProximity Sensor FusionRegistration Error CorrectionTarget Localization
This paper describes a novel approach to estimating the position of target based on fusion of RGB-depth camera and 2D light detection and ranging (LiDAR) sensor measurements. In the proposed approach, the 3D and 2D position information of target measured by RGB-D camera and LiDAR sensor respectively are utilized to find location of target by incoporating visual tracker, depth information and vision-LiDAR low-level fusion algorithm (e.g., extrinsic calibration). Registration error correction of multiple measurements from both RGB-D camera and LiDAR sensors is executed in order to carry out data fuison. Then, results of local noisy position measuments are fused using track-to-track fusion algorithm. The experimental verification results are compared to position data from VICON motion capture and the results show that the performance of the proposed approach is better than each sensor's localization result in view of noise intensity.
18
Histograms of Oriented Gradients for Human Detection
Navneet Dalal, Bill Triggs · 2005 · 31.9K citations · Full text
Rapid object detection using a boosted cascade of simple features
Paul Viola, Michael Jones · 2005 · 18.2K citations
Multiple View Geometry in Computer Vision
Kybernetes · 2001 · 3.3K citations
Computer Vision Face Tracking For Use in a Perceptual User Interface
R. Bradski Gary · 1998 · 1.4K citations