Dynamic Object Tracking Research Articles

The Population-Based Optimization Algorithms for Role Modelling and Path Generation in Group Animation

Traditional animation by key frame techniques takes animators lots of time and vigour to model and simulate behaviours of crowds. For solving this problem, this paper presents a novel group animation generation approach based on population-based optimization algorithms. It is mainly divided into two parts. First, it puts forward a role modelling approach based on dynamic self-adaptive genetic algorithm and NURBS technology. Second, following the introduction to PSO (Particle Swarm Optimization) algorithm, a group path generative approach is presented. It simulates group behaviours, including cohesion and separation, dynamic object tracking and collision avoidance. Finally, a group of shark modelling and path generation images are exhibited as examples.

Bayesian Sensor Fusion Methods for Dynamic Object Tracking—A Comparative Study

In this paper we study the problem of Bayesian sensor fusion for dynamic object tracking. The prospects of utilizing measurements from several sensors to infer about a system state are manyfold and they range from increased estimate accuracy to more reliable and robust estimates. Sensor measurements may be combined, or fused, at a variety of levels; from the raw data level to a state vector level, or at the decision level. In this paper we mainly focus on the Bayesian fusion at the likelihood and state vector level. We analyze two groups of data fusion methods: centralized independent likelihood fusion, where the sensors report only its measurement to the fusion center, and hierarchical fusion, where each sensor runs its own local estimate which is then communicated to the fusion center along with the corresponding uncertainty. We compare the prospects of utilizing both approaches, and present explicit solutions in the forms of extended information filter, unscented information filter, and particle filter. Furthermore, we also propose a solution for fusion of arbitrary filters and test it on a hierarchical fusion example of two of the aforementioned filters. Hence, the main contributions of this paper are systematic comparative study of Bayesian fusion methods, and a method for hierarchical fusion of arbitrary filters. The fusion methods are tested on a synthetic data generated by multiple Monte Carlo runs for tracking of a dynamic object with several sensors of different accuracies by analyzing the quadratic Rényi entropy and root-mean-square error.

Study Infrared Radiation Characteristic on High-Speed Projectile

To improve the detection performance of dynamic object tracking system that cannot work normally at night, the infrared detection technology is put forward to design and study its detection tracking system. According to the characteristic that projectile can produce heat radiant energy when it flying, the surface projectile was divided into small unit area independently to calculate its infrared radiation energy, its heat radiation temperature equations were established, the method of four-order runge-kuta was applied to analyze and calculate temperature parameter. The relation between atmospheric attenuation and detection performance was analyzed in dynamic object tracking system. Through calculating and analyzing, the theory of infrared radiation technology meets the need of dynamic object tracking system.

An embedded multi-modal system for object localization and tracking

Reliable obstacle detection and localization is a key issue for driver assistance systems, particularly in urban environments. In this study a multi-modal perception approach is investigated, the objective being to enhance vehicle localization and dynamic object tracking in a world-centric map. A 3D ego-localization is achieved by merging information from a stereo vision system and data obtained from vehicle sensors. Mobile objects are detected using a multi-layer lidar that is also used to identify a constrained search space within the multiple target tracking process. Object localization and tracking is then performed in the fixed frame, which facilitates analysis and understanding of the scene. Experimental results using real world data are performed to evaluate the performance of the multi-modal system, and these are presented to show the effectiveness of the approach.

Dynamic Object Tracking (DOT) Microscopy To Image Endosomal Transport On Individual Microtubules In An Axon

Fluorescence imaging with single molecule resolution has been vital to many important discoveries in biology. The spatial resolution of fluorescence microscopy has a physical lower bound, the diffraction of light, which is approximately half of the wavelength and in the range of 200-300nm for visible light. Many biological objects of interest are on a length scale below this diffraction limit. Several high resolution techniques have been developed to break this diffraction limit. Here we describe a new high-resolution imaging technique called Dynamic Object Tracking (DOT) microscopy, in which dynamic trajectories of moving objects are used to reconstruct fluorescence images of cytoskeletal structures. DOT microscopy takes time-lapse measurements of fluorescence images of moving organelles, single molecules or particles in live cells. The trajectory taken by the particle over time marks out the microtubule or actin filament that it travels along. At each time frame, particle positions can be determined with high accuracy by PSF fitting to a 2D Gaussian function to get a resolution that breaks the diffraction limit. We have applied this technique to track retrograde transportation of endosomes containing single NGF molecules in the axons of neurons. A pseudo Total Internal Reflection Fluorescence (TIRF) microscope was constructed in house to take the measurements. Individual NGF molecules conjugated to single quantum dots were imaged and tracked in live cells. The sub-diffraction-limit DOT imaging of individual axonal microtubules was achieved and we are able to clearly depict more than five microtubules in a single axon.

A MULTI-CAMERA VIEW DIRECTION PLANNING STRATEGY FOR MOBILE ROBOTS

A multi-camera view direction planning strategy for mobile robots is discussed. Two concurrent tasks for efficient and safe locomotion in dynamic environments are considered: self-localization and dynamic object tracking. The approach is to assign different tasks to different cameras, such that for each task an individual optimal view direction is selected based on information gain maximization. Thereby, the individual task performance is improved significantly. The performance of the proposed strategy is evaluated in simulations considering a humanoid robot navigation scenario and compared with two conventional multi-camera view direction planning strategies.

Real-Time Three-Dimensional Occupancy Grid Modeling for the Detection and Tracking of Construction Resources

Awareness of the construction environment can be improved by automatic three-dimensional (3D) sensing and modeling of job sites in real time. Commercially available 3D modeling approaches based on range scanning techniques are capable of modeling static objects only, and thus cannot model dynamic objects in real time in an environment comprised of moving humans, equipment, and materials. Emerging prototype video range cameras offer an alternative by facilitating affordable, wide field of view, dynamic object tracking at frame rates better than 1 Hz (real time). This paper describes a methodology to model, detect, and track the position of static and moving objects in real time, based on data obtained from video range cameras. Experiments with this technology have produced results that indicate that video rate 3D data acquisition and analysis of construction environments can support effective modeling, detection, and tracking of project resources. This approach to job site awareness has inherent value and broad application. In combination with effective management practices and other sensing techniques, this technology has the potential to significantly improve safety on construction job sites.

TViews: An Extensible Architecture for Multiuser Digital Media Tables

The TViews table is a media interaction platform designed for shared living spaces within the home environment. This platform consists of three parts: a dynamic object tracking and identification system that works with an extensible set of tagged objects on the table's surface, a planar display that is integrated into the table's surface, and a set of application programming interfaces (APIs) that tie these elements together. TViews is an extensible method and acoustic-based sensing framework for creating digital media tables that overcome many limitations of single-purpose systems. The system provides a means for real-time multiobject tracking on the tabletop and for the management of large numbers of objects and applications across multiple platform instances

Time-resolved analysis and visualization of dynamic processes in living cells.

Recent development of in vivo microscopy techniques, including green fluorescent proteins, has allowed the visualization of a wide range of dynamic processes in living cells. For quantitative and visual interpretation of such processes, new concepts for time-resolved image analysis and continuous time-space visualization are required. Here, we describe a versatile and fully automated approach consisting of four techniques, namely highly sensitive object detection, fuzzy logic-based dynamic object tracking, computer graphical visualization, and measurement in time-space. Systematic model simulations were performed to evaluate the reliability of the automated object detection and tracking method. To demonstrate potential applications, the method was applied to the analysis of secretory membrane traffic and the functional dynamics of nuclear compartments enriched in pre-mRNA splicing factors.

A Neural Controller based Binocular Vision System for Object Tracking

In this paper, we present a learning control approach to the problem of visual tracking using an active binocular vision system. The simulated vision system used here is composed of two cameras which have freedom of pan and are mounted on a plate that can tilt. A self organizing map is trained to learn the mapping between visual feedback as received from the simulated CCD cameras and the incremental values in the orientation angles of the vision system to fixate continuously on a mobile target. A direct implication of this is that the object should be centered at the vergence point of the cameras. This is accomplished by ensuring minimum disparity of the target vector from the center of the images of both the cameras. The learning algorithm is presented and the simulation study shows an average focussing error of 0.15 pixels after 1200 iterations for a small, defined joint angle space of the vision system. Thus, a significant contribution of this work is the application of a self organizing map in dynamic object tracking.