*Result*: Vision-aided navigation for GPS-denied environments using landmark feature identification
Embry-Riddle Aeronautical University. Department of Aerospace Engineering.
"Daytona Beach, Florida, December 2014."
Includes bibliographical references (leaves 106-115).
Motivation ; Literature review ; Scope of work ; Technical objectives -- Detection and tracking algorithms. CAMshift algorithm. Mean shift theory - Mass center calculation - Histogram back - projection - Effect of scaling and orientation features in CAMshift algorithm ; Adaptable (advanced) compressive (ADCOM) tracking algorithm. Background subtraction based tracker - Particle filter based L1 tracker - Fundamental types of online tracking algorithms - Need for a stable, robust and efficient algorithm - Random projection - Sparse measurement matrix representation - ADCOM tracking algorithm. Haar - like features , Dimensionality reduction (lossless compression) , Naïve Bayes classifier ; Secondary algorithms to support data - dependent and data - independent algorithms. Template matching - Pattern recognition - Color detection - Edge detection - Corner detection - Kanade - Lucas - Tomasi tracker (KLT) -- Image processing implementation. Implementation and analysis of CAMshift algorithm ; Implementation and analysis of ADCOM algorithm -- Navigation filters. Kalman filter ; Extended Kalman filter. Experimental EKF for vision - aided navigation -- pt. V. Extended Kalman filter (EKF) implementation. Position and velocity estimates using a 4 - state EKF (with accelerometer data) ; Position and velocity estimates using a 4 - state EKF (without accelerometer data) ; 4 - state extended Kalman filter with additive white Gaussian noise ; Extended Kalman filter for tracking multiple landmarks / targets ; 6 - state extended Kalman filter -- pt. VI. Conclusion and future recommendations. Future recommendations.
1014343457
*Further Information*
*This thesis investigate the development of vision-aided navigation algorithms that utilize processed images from a monocular camera as an alternative to GPS. The vision-aided navigation approach explored in this thesis entails defining a set of inertial landmarks, the locations of which are known within the environment, and employing image processing algorithms to detect these landmarks in image frames collected from an onboard monocular camera. These vision-based landmark measurements effectively serve as surrogate GPS measurements that can be incorporated into a navigation filter. Several image processing algorithms were considered for landmark detection and this thesis focuses in particular on two approaches: the continuous adaptive mean shift (CAMSHIFT) algorithm and the adaptable compressive (ADCOM) tracking algorithm. These algorithms are discussed in detail and applied for the detection and tracking of landmarks in monocular camera images. Navigation filters are then designed that employ sensor fusion of accelerometer and rate gyro data from an inertial measurement unit (IMU) with vision-based measurements of the centroids of one or more landmarks in the scene. These filters are tested in simulated navigation scenarios subject to varying levels of sensor and measurement noise and varying number of landmarks. Finally, conclusions and recommendations are provided regarding the implementation of this vision-aided navigation approach for autonomous vehicle navigation systems.*