In this paper, we present a new approach for tracking targets in forward-looking infrared (FLIR) imagery taken from an airborne, moving platform. Our tracking approach uses the target intensity and the Gabor response distributions and computes a likelihood measure between the candidate and the model distributions by evaluating the Mean Shift Vector. When the Mean Shift Vector based tracker fail...

We describe a system for tracking multiple people with multiple cameras based on fusion of multiple cues. Face trackers are used to self-calibrate our system. Epipolar geometry and landmarks are employed to disambiguate the tracking problem. The correlation of visual information between different cameras is learnt using Support Vector Regression and Hierarchical Principal Component Analysis to ...

This paper investigates three different Kalman filter implementation options to estimate signal tracking errors in a GPS receiver with particular emphasis given to the carrier phase. The three options are outlined in terms of the system and measurement models. Initial assessment of the different options is performed in scalar-tracking mode with strong signals to assess their relative carrier ph...

Today, smart mobiles play an important role in our daily life. Most of these devices are equipped with a navigation function based on GNSS positioning. However, these devices may not work accurately in urban environments due to severe multipath interference and non-line of sight (NLOS) reception caused by nearby buildings. A promising approach for reducing the effect of multipath interference a...

Nonlinear tracking control of unmanned underwater vehicles (UUVs) in 6 degrees of freedom (DOF) is discussed. The 4-parameter unit quaternion is used in a singularity-free representation of attitude. Several control laws based on a generalized Lyapunov function for the attitude dynamics are derived, including feedback from the vector quaternion, the Euler rotation vector and the Rodrigues param...

Feature tracking algorithms for instationary vector fields are usually based on a correspondence analysis of the features at different time steps. This paper introduces a method for feature tracking which is based on the integration of stream lines of a certain vector field called feature flow field. We analyze for which features the method of feature flow fields can be applied, we show how eve...

The paper selected for implementation was Support Vector Tracking by Shai Avidan. The paper introduces a simple but novel idea of replacing the standard optical flow algorithm equation with equations that use the SVM to calculate the derivatives. The standard way of calculating optical flow is by solving the following matrix: A 11 A 12 u b 1 =-(1) A 21 A 22 v b 2 where (using Lucas Kanade optic...

This paper presents a learning based approach to tracking articulated human body motion from a single camera. In order to address the problem of pose ambiguity, a one-to-many mapping from image features to state space is learned using a set of relevance vector machines, extended to handle multivariate outputs. The image features are Hausdorff matching scores obtained by matching different shape...

This paper presents a novel learning feed-forward controller design approach for accurate robotics trajectory tracking. Based on the joint nonlinear dynamics characteristics, a model-free learning algorithm based on Support Vector Machine (SVM) is implemented for friction model identification. The experimental results verified that SVM based learning feed-forward controller is a good approach f...

Grid and block-based motion vector estimation techniques are proposed for motion tracking in video sequences. The grid technique is referred to the hexagon-diamond pattern. While, block-based technique is referred to 16 × 16 pixels of blocks in a single frame in video sequences. The hexagon and diamond pattern is applied onto the 16 × 16 pixels blocks in a single frame for motion tracking purpo...