Estimation and Tracking: Principles, Techniques, and Software [Reviews and Abstracts]

Bar‐Shalom, Yaakov; Li, Xiaorong

doi:10.1109/map.1996.491294

Cited by 555 publications

(986 citation statements)

References 0 publications

Supporting

Mentioning

969

Contrasting

Unclassified

Order By: Relevance

“…Alauddin Al-Omary is with Information Technology, University of Bahrain (UOB), Al-Sukhir, Kingdom of Bahrain (e-mail: aalomary@uob.edu.bh) been extensively studied for several decades [1], [2].…”

Section: Related Workmentioning

confidence: 99%

Design and Implementation of Object Seeking Robot

Al-Omary¹

2012

IJCEE

View full text Add to dashboard Cite

Abstract-Thispaper presents the design and implementation of an object seeking robot. The robot controller is first implemented using an FPGA for fast prototyping. All parts of the design have been simulated and implemented using Xilinx tools. The system controller is then implemented using PIC16F84A single chip microcontroller to achieve low power consumption, and quick movement, which is a basic requirement in environments where quick response is needed in continuously changing dynamic situations. The robot sensors are part of an object tracking program to determine the location of certain objects and act as actuators for the control system, which operates two DC motors. The speed and direction of the movements are based on the received information from the sensors. The robot was tested and found to meet the specification for reliable operation.

show abstract

Section: Related Workmentioning

confidence: 99%

Design and Implementation of Object Seeking Robot

Al-Omary¹

2012

IJCEE

View full text Add to dashboard Cite

show abstract

“…The dynamics of each tracked object are modeled by means of a linear dynamical system which is tracked using the Kalman filter [15,16]. The state vector x(t) at time t is given as x(t) = (c x (t), c y (t), u x (t), u y (t)) T where c x (t), c y (t) are the horizontal and vertical coordinates of the tracked object's centroid, and u x (t), u y (t) are the corresponding components of the tracked object's speed.…”

Section: Tracking Blob Position and Speedmentioning

confidence: 99%

Propagation of Pixel Hypotheses for Multiple Objects Tracking

Baltzakis

Argyros

2009

Advances in Visual Computing

View full text Add to dashboard Cite

Abstract. In this paper we propose a new approach for tracking multiple objects in image sequences. The proposed approach differs from existing ones in important aspects of the representation of the location and the shape of tracked objects and of the uncertainty associated with them. The location and the speed of each object is modeled as a discrete time, linear dynamical system which is tracked using Kalman filtering. Information about the spatial distribution of the pixels of each tracked object is passed on from frame to frame by propagating a set of pixel hypotheses, uniformly sampled from the original object's projection to the target frame using the object's current dynamics, as estimated by the Kalman filter. The density of the propagated pixel hypotheses provides a novel metric that is used to associate image pixels with existing object tracks by taking into account both the shape of each object and the uncertainty associated with its track. The proposed tracking approach has been developed to support face and hand tracking for human-robot interaction. Nevertheless, it is readily applicable to a much broader class of multiple objects tracking problems.

show abstract

“…For instance, adaptive vector quantization (Gray, 1984) algorithms may be used if parameter values vary slowly. More sophisticated tracking algorithms (Bar-Shalom and Li, 1993;Blackman, 1986) arc needed to update tracks for parameters that exhibit rapid linear or nonlinear variations. In this section, on-line clustering of Brg and PA parameters is implemented by combining nearest-neighbor matching with linear Kalman filtering.…”

Section: Pattern Clusteringmentioning

confidence: 99%

“…The three basic functions -data association, track maintenance, and filtering and prediction -are now examined. Then, the match can be taken to be a probability, and written: (5) where M is the number of dimensions in the Where space, and x 11 and A 11 are, respectively, the Kalman filtering (Bar-Shalom and Li, 1993;Blackman, 1986) is employed to predict the next position Xiz, and covariance matrix A 11 of each track h. Recall from Section 3 that the usual clustering is bypassed when b corresponds to a PDW that has been assigned a previouslyestablished track through TOA deinterleaving. In this case, b retains its track, and does not perform data association, nor track maintenance.…”

Section: Pattern Clusteringmentioning

confidence: 99%

“…In a particular realization of the recognition system, fuzzy ARTMAP (Carpenter et a!., 199la, 1992) is considered for neural network classification of pulses from their type-specific parameters, whereas nearest-neighbor matching with a bank of Kalman filters (Bar-Shalom and Li, 1993;Blackman, 1986) is considered for separation of pulses from their environmentspecific parameters. The features of the system include: (1) By virtue of the fast-learning capabilities of ARTMAP neural networks (Carpenter eta!., 199la, 199lb, 1992), new information from familiar or unfamiliar radar type classes can be learned incrementally without retraining on the whole data set.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation