Home > articles, blog post, news > Target Tracking and Prediction

Target Tracking and Prediction

July 29, 2012


complex locomotion system – “…The vision and sensor fusion techniques described in the previous chapters provide a measurement of target locations for each image frame. In its raw form, this information is of limited use for camera control because it is imprecise due to measurement noise; it may include false-positive detections of people; and it provides no association between new measurements and previous target locations. This makes it difficult to develop smooth camera control motions from the raw measurements. In addition, the data is in polar coordinates which complicates the task of associating the data with other sensors or devices in the room that may not share the same coordinate system. For these reasons, target measurements are converted to a global Cartesian coordinate system, associated with previously tracked targets, and used to update a filter/state estimator for each target track…Since the face is attached to the rest of the human body, its dynamics are directly related to those of the body. Head movements may be thought of as zero-mean random fluctuations with respect to the body position, so the same state model used for tracking the entire body has also been used for tracking head position. A human being has a complex locomotion system, which poses serious challenges in modeling. Rather than analyzing properties of the human gait, one may assume a drastically simplified model of the target as a mass under the influence of two forces: average leg force and friction. Leg force is used to push the body into motion, and friction comes from the inefficiency of the human body maintaining this motion. Intra-stride dynamics and rotation of the body, assuming that the body may move in any direction, are constrained only by leg force and inertia…” (Target Tracking)

the barn owl – “…Neurobiology research provides evidence that a cellular spatial representation is useful for fusing multimodal sensor information. The neural audio-visual processing mechanisms used by the barn owl, for example, have been extensively mapped by biologists. As explained by Knudsen, auditory and visual information in the barn owl (and many other animals) converges at the optic tectum, where a receptive field of spatially distributed neurons responds to stimuli on the basis of the direction to corresponding sources. This structure can easily associate acoustic events with corresponding visual targets due to the proximity of vision and sound signals in the neural array. Knudsen, du Lac, and Esterly [3] describe this neural topography as a “computational map” that provides a direct representation for spatial information. A cellular map efficates fusion of multiple sensor modalities, and can efficiently cross-reference target sensation to appropriate motor actions for directional perception and pursuit behaviors…” (Multimedia Sensor Fusion for Intelligent Camera Control and Human-Computer Interaction)

genetic algorithm (GA) for data association – “…In this paper, we investigate an approach based on multiple models to track maneuvering and nonmaneuvering targets, which overcome the above problems by using a genetic algorithm (GA) for data association. The choice for using multiple models is dictated by the fact that using a single model does not permit the tracking of maneuvering and nonmaneuvering targets simultaneously. GA is widely used to solve complex optimization problems in spite of the fact that there is no guarantee of obtaining the optimal solution. But, it does provide a set of potential solutions in the process of finding the best solution…In the literature, GA has been used for multitarget tracking. In [23],[24] , GA is used for data association with MHT algorithm. As discussed earlier, MHT algorithm is computationally expensive and it is difficult to use the same in a real-time tracking application, GA has been used to generate fuzzy rules to track a target. Similarly, GA algorithm has been used for off-line fuzzy system optimization, and the latter is used to update model probability for tracking targets using IMM algorithm…GA is used to analyze Doppler effects of a sound for motion analysis of a moving object. GA along with neural network has been used for tracking…the neural energy function is optimized for solving the data association problem. A multiple model-based tracking method has been proposed…track multiple targets using the Hopfield network for data association. The method proposed provides superior performance, but the drawback with the neural net-based approach is that it requires a large number of iterations and the selection of coefficients is by trial and error. In our proposed method in this paper, we do not use neural energy function…” (Genetic Algorithm-based Data Association and Multiple Filter Bank-based Target Tracking in Infrared Image Sequences)

A radar tracker is a component of a radar system, or an associated command and control (C2) system, that associates consecutive radar observations of the same target into tracks. It is particularly useful when the radar system is reporting data from several different targets or when it is necessary to combine the data from several different radars or other sensors (Wikepedia).

RELATED READING:
Multimedia Sensor Fusion for Intelligent Camera Control and Human-Computer Interaction
Multiple-target tracking with radar applications
Design and Analysis of Modern Tracking Systems
Genetic Algorithm-based Data Association and Multiple Filter Bank-based Target Tracking in Infrared Image Sequences
Stealth Navigation for Intercepting an Invader
List of mind control symptoms, whether the related technology is scientifically proven and if there is military interest or funding of the related technology

About these ads
Follow

Get every new post delivered to your Inbox.

Join 565 other followers

%d bloggers like this: