A novel probabilistic perception algorithm is presented as a real-time joint solution to data association, object tracking, and object classification for an autonomous ground vehicle in all-weather conditions. The presented algorithm extends a Rao-Blackwellized Particle Filter originally built with a particle filter for data association and a Kalman filter for multi-object tracking (Miller et a...

We develop an interactive likelihood (ILH) for sequential Monte Carlo (SMC) methods for image-based multiple target tracking applications. The purpose of the ILH is to improve tracking accuracy by reducing the need for data association. In addition, we integrate a recently developed deep neural network for pedestrian detection along with the ILH with a multi-Bernoulli filter. We evaluate the pe...

In high dynamic situations, the GPS carrier tracking loop requires a wide bandwidth to track a carrier signal because the Doppler frequency changes more rapidly with time. However, a wide bandwidth allows noises within the bandwidth of the tracking loop to pass through the loop filter. As these noises are used in the numerical controlled oscillator (NCO), the carrier tracking loop of a GPS rece...

In the study of dynamic gesture recognition, gesture tracking must be performed reliably in real-time for sufficiently long periods when there is too much background interference. To deal with these problems effectively, an improved particle filter algorithm is proposed in order to track the moving hand quickly and accurately. Firstly, the algorithm improves the traditional hand model and prese...

This paper studies the problem of tracking a mobile device in mixed line-of-sight (LOS) and non-line-of-sight (NLOS) conditions. NLOS error is assumed to be Gaussian with unknown mean and variance. An adaptive Rao-Blackwellized particle filter (RBPF) is proposed for mobile tracking in such scenarios. An extended Kalman filter is used to approximately estimate the mobile state, and the particle ...

In the study, a real time pedestrian tracking algortithm is presented using thermal infrared imagery. It makes use of the characteristics of pedestrian body regions in infrared images, which is based on a particle filter framework. The method constructs the regions of interest's (ROI) histogram representation in an intensity-distance projection space model, so as to hurdle the disadvantage of i...

In some estimation or identification techniques, a forgetting factor has been used to improve the tracking performance for time-varying systems. However, the value of has been typically determined empirically, without any evidence of optimality. In our previous work, this open problem is solved using the framework of H optimization. The resultant H filter enables the forgetting factor to be opt...

Human tracking is the process of locating moving objects (human) over time using camera. It has wide number of applications like security and surveillance, traffic control, video editing, medical imaging etc. It can be a time consuming process due to the large amount of data contained in video. The objective of human tracking is to associate target objects in consecutive video frames. To initia...