Abstract: Shadows add great amount of realism to a scene and
many algorithms exists to generate shadows. Recently, Shadow
volumes (SVs) have made great achievements to place a valuable
position in the gaming industries. Looking at this, we concentrate on
simple but valuable initial partial steps for further optimization in SV
generation, i.e.; model simplification and silhouette edge detection
and tracking. Shadow volumes (SVs) usually takes time in generating
boundary silhouettes of the object and if the object is complex then
the generation of edges become much harder and slower in process.
The challenge gets stiffer when real time shadow generation and
rendering is demanded. We investigated a way to use the real time
silhouette edge detection method, which takes the advantage of
spatial and temporal coherence, and exploit the level-of-details
(LOD) technique for reducing silhouette edges of the model to use
the simplified version of the model for shadow generation speeding
up the running time. These steps highly reduce the execution time of
shadow volume generations in real-time and are easily flexible to any
of the recently proposed SV techniques. Our main focus is to exploit
the LOD and silhouette edge detection technique, adopting them to
further enhance the shadow volume generations for real time
rendering.
Abstract: An important problem in speech research is the automatic extraction of information about the shape and dimensions of the vocal tract during real-time speech production. We have previously developed Southampton dynamic magnetic resonance imaging (SDMRI) as an approach to the solution of this problem.However, the SDMRI images are very noisy so that shape extraction is a major challenge. In this paper, we address the problem of tongue shape extraction, which poses difficulties because this is a highly deforming non-parametric shape. We show that combining active shape models with the dynamic Hough transform allows the tongue shape to be reliably tracked in the image sequence.
Abstract: Extended Kalman Filter (EKF) is probably the most
widely used estimation algorithm for nonlinear systems. However,
not only it has difficulties arising from linearization but also many
times it becomes numerically unstable because of computer round off
errors that occur in the process of its implementation. To overcome
linearization limitations, the unscented transformation (UT) was
developed as a method to propagate mean and covariance
information through nonlinear transformations. Kalman filter that
uses UT for calculation of the first two statistical moments is called
Unscented Kalman Filter (UKF). Square-root form of UKF (SRUKF)
developed by Rudolph van der Merwe and Eric Wan to
achieve numerical stability and guarantee positive semi-definiteness
of the Kalman filter covariances. This paper develops another
implementation of SR-UKF for sequential update measurement
equation, and also derives a new UD covariance factorization filter
for the implementation of UKF. This filter is equivalent to UKF but
is computationally more efficient.
Abstract: Region covariance (RC) descriptor is an effective
and efficient feature for visual tracking. Current RC-based tracking
algorithms use the whole RC matrix to track the target in video
directly. However, there exist some issues for these whole RCbased
algorithms. If some features are contaminated, the whole RC
will become unreliable, which results in lost object-tracking. In
addition, if some features are very discriminative to the
background, other features are still processed and thus reduce the
efficiency. In this paper a new robust tracking method is proposed,
in which the whole RC matrix is decomposed into several low rank
matrices. Those matrices are dynamically chosen and processed so
as to achieve a good tradeoff between discriminability and
complexity. Experimental results have shown that our method is
more robust to complex environment changes, especially either
when occlusion happens or when the background is similar to the
target compared to other RC-based methods.
Abstract: In this paper, an estimation accuracy of multiple moving
talker tracking using a microphone array is improved. The tracking
can be achieved by the adaptive method in which two algorithms are integrated, namely, the PAST (Projection Approximation Subspace
Tracking) algorithm and the IPLS (Interior Point Least Square) algorithm. When either talker begins to speak again after a silent
period, an appropriate feasible region for an evaluation function of
the IPLS algorithm might not be set. Then, the tracking fails due to the incorrect updating. Therefore, if an increment of the number of
active talkers is detected, the feasible region must be reset. Then, a low cost realization is required for the high speed tracking and a high
accuracy realization is desired for the precise tracking. In this paper,
the directions roughly estimated using the delayed-sum-array method
are used for the resetting. Several results of experiments performed in
an actual room environment show the effectiveness of the proposed method.
Abstract: The problem of manipulator control is a highly
complex problem of controlling a system which is multi-input, multioutput,
non-linear and time variant. In this paper some adaptive
fuzzy, and a new hybrid fuzzy control algorithm have been
comparatively evaluated through simulations, for manipulator
control. The adaptive fuzzy controllers consist of self-organizing,
self-tuning, and coarse/fine adaptive fuzzy schemes. These
controllers are tested for different trajectories and for varying
manipulator parameters through simulations. Various performance
indices like the RMS error, steady state error and maximum error are
used for comparison. It is observed that the self-organizing fuzzy
controller gives the best performance. The proposed hybrid fuzzy
plus integral error controller also performs remarkably well, given its
simple structure.
Abstract: This paper suggests a fast and stable Target Tracking
system in collaborative control of UAV and UGV. Wi-Fi communication range is limited in collaborative control of UAV and UGV. Thus, to secure a stable communications, UAV and UGV have
to be kept within a certain distance from each other. But existing
method which uses UAV Vertical Camera to follow the motion of
UGV is likely to lose a target with a sudden movement change.
Eventually, UGV has disadvantages that it could only move at a low
speed and not make any sudden change of direction in order to keep
track of the target. Therefore, we suggest utilizing AR Drone UAV front camera to track fast-moving and Omnidirectional Mecanum
Wheel UGV.
Abstract: In this paper, we introduce a novel algorithm for object tracking in video sequence. In order to represent the object to be tracked, we propose a spatial color histogram model which encodes both the color distribution and spatial information. The object tracking from frame to frame is accomplished via center voting and back projection method. The center voting method has every pixel in the new frame to cast a vote on whereabouts the object center is. The back projection method segments the object from the background. The segmented foreground provides information on object size and orientation, omitting the need to estimate them separately. We do not put any assumption on camera motion; the proposed algorithm works equally well for object tracking in both static and moving camera videos.
Abstract: Real-time object tracking is a problem which involves extraction of critical information from complex and uncertain imagedata. In this paper, we present a comprehensive methodology to design an artificial neural network (ANN) for a real-time object tracking application. The object, which is tracked for the purpose of demonstration, is a specific airplane. However, the proposed ANN can be trained to track any other object of interest. The ANN has been simulated and tested on the training and testing datasets, as well as on a real-time streaming video. The tracking error is analyzed with post-regression analysis tool, which finds the correlation among the calculated coordinates and the correct coordinates of the object in the image. The encouraging results from the computer simulation and analysis show that the proposed ANN architecture is a good candidate solution to a real-time object tracking problem.
Abstract: Detection and tracking of the lip contour is an important
issue in speechreading. While there are solutions for lip tracking
once a good contour initialization in the first frame is available,
the problem of finding such a good initialization is not yet solved
automatically, but done manually. We have developed a new tracking
solution for lip contour detection using only few landmarks (15
to 25) and applying the well known Active Shape Models (ASM).
The proposed method is a new LMS-like adaptive scheme based on
an Auto regressive (AR) model that has been fit on the landmark
variations in successive video frames. Moreover, we propose an extra
motion compensation model to address more general cases in lip
tracking. Computer simulations demonstrate a fair match between
the true and the estimated spatial pixels. Significant improvements
related to the well known LMS approach has been obtained via a
defined Frobenius norm index.
Abstract: In this paper we consider the problem of change
detection and non stationary signals tracking. Using parametric
estimation of signals based on least square lattice adaptive filters we
consider for change detection statistical parametric methods using
likelihood ratio and hypothesis tests. In order to track signals
dynamics, we introduce a compensation procedure in the adaptive
estimation. This will improve the adaptive estimation performances
and fasten it-s convergence after changes detection.
Abstract: Time delay in bilateral teleoperation system was
introduced as a sufficient reason to make the system unstable or
certainly degrade the system performance. In this paper, simulations
and experimental results of implementing p-like control scheme,
under different ranges of variable time delay, will be presented to
verify a certain criteria, which guarantee the system stability and
position tracking. The system consists of two Phantom premium 1.5A
devices. One of them acts as a master and the other acts as a slave.
The study includes deriving the Phantom kinematic and dynamic
model, establishing the link between the two Phantoms over
Simulink in Matlab, and verifying the stability criteria with
simulations and real experiments.
Abstract: This paper presents recent work on the improvement
of the robotics vision based control strategy for underwater pipeline
tracking system. The study focuses on developing image processing
algorithms and a fuzzy inference system for the analysis of the
terrain. The main goal is to implement the supervisory fuzzy learning
control technique to reduce the errors on navigation decision due to
the pipeline occlusion problem. The system developed is capable of
interpreting underwater images containing occluded pipeline, seabed
and other unwanted noise. The algorithm proposed in previous work
does not explore the cooperation between fuzzy controllers,
knowledge and learnt data to improve the outputs for underwater
pipeline tracking. Computer simulations and prototype simulations
demonstrate the effectiveness of this approach. The system accuracy
level has also been discussed.
Abstract: This paper compares the heuristic Global Search
Techniques; Genetic Algorithm, Particle Swarm Optimization,
Simulated Annealing, Generalized Pattern Search, genetic algorithm
hybridized with Nelder–Mead and Generalized pattern search
technique for tuning of fuzzy PID controller for Puma 560. Since the
actual control is in joint space ,inverse kinematics is used to generate
various joint angles correspoding to desired cartesian space
trajectory. Efficient dynamics and kinematics are modeled on Matlab
which takes very less simulation time. Performances of all the tuning
methods with and without disturbance are compared in terms of ITSE
in joint space and ISE in cartesian space for spiral trajectory tracking.
Genetic Algorithm hybridized with Generalized Pattern Search is
showing best performance.
Abstract: The Continuously Adaptive Mean-Shift (CamShift)
algorithm, incorporating scene depth information is combined with
the l1-minimization sparse representation based method to form a
hybrid kernel and state space-based tracking algorithm. We take
advantage of the increased efficiency of the former with the
robustness to occlusion property of the latter. A simple interchange
scheme transfers control between algorithms based upon drift and
occlusion likelihood. It is quantified by the projection of target
candidates onto a depth map of the 2D scene obtained with a low cost
stereo vision webcam. Results are improved tracking in terms of drift
over each algorithm individually, in a challenging practical outdoor
multiple occlusion test case.
Abstract: This article presents the results using a parametric approach and a Wavelet Transform in analysing signals emitting from the sperm whale. The extraction of intrinsic characteristics of these unique signals emitted by marine mammals is still at present a difficult exercise for various reasons: firstly, it concerns non-stationary signals, and secondly, these signals are obstructed by interfering background noise. In this article, we compare the advantages and disadvantages of both methods: Auto Regressive models and Wavelet Transform. These approaches serve as an alternative to the commonly used estimators which are based on the Fourier Transform for which the hypotheses necessary for its application are in certain cases, not sufficiently proven. These modern approaches provide effective results particularly for the periodic tracking of the signal's characteristics and notably when the signal-to-noise ratio negatively effects signal tracking. Our objectives are twofold. Our first goal is to identify the animal through its acoustic signature. This includes recognition of the marine mammal species and ultimately of the individual animal (within the species). The second is much more ambitious and directly involves the intervention of cetologists to study the sounds emitted by marine mammals in an effort to characterize their behaviour. We are working on an approach based on the recordings of marine mammal signals and the findings from this data result from the Wavelet Transform. This article will explore the reasons for using this approach. In addition, thanks to the use of new processors, these algorithms once heavy in calculation time can be integrated in a real-time system.
Abstract: In this paper we present a new method for over-height
vehicle detection in low headroom streets and highways using digital
video possessing. The accuracy and the lower price comparing to
present detectors like laser radars and the capability of providing
extra information like speed and height measurement make this
method more reliable and efficient. In this algorithm the features are
selected and tracked using KLT algorithm. A blob extraction
algorithm is also applied using background estimation and
subtraction. Then the world coordinates of features that are inside the
blobs are estimated using a noble calibration method. As, the heights
of the features are calculated, we apply a threshold to select overheight
features and eliminate others. The over-height features are
segmented using some association criteria and grouped using an
undirected graph. Then they are tracked through sequential frames.
The obtained groups refer to over-height vehicles in a scene.
Abstract: Target tracking and localization are important applications
in wireless sensor networks. In these applications, sensor nodes
collectively monitor and track the movement of a target. They have
limited energy supplied by batteries, so energy efficiency is essential
for sensor networks. Most existing target tracking protocols need to
wake up sensors periodically to perform tracking. Some unnecessary
energy waste is thus introduced. In this paper, an energy efficient
protocol for target localization is proposed. In order to preserve
energy, the protocol fixes the number of sensors for target tracking,
but it retains the quality of target localization in an acceptable
level. By selecting a set of sensors for target localization, the other
sensors can sleep rather than periodically wake up to track the target.
Simulation results show that the proposed protocol saves a significant
amount of energy and also prolongs the network lifetime.
Abstract: The paper proposes a way of parallel processing of
SURF and Optical Flow for moving object recognition and tracking.
The object recognition and tracking is one of the most important task
in computer vision, however disadvantage are many operations cause
processing speed slower so that it can-t do real-time object recognition
and tracking. The proposed method uses a typical way of feature
extraction SURF and moving object Optical Flow for reduce
disadvantage and real-time moving object recognition and tracking,
and parallel processing techniques for speed improvement. First
analyse that an image from DB and acquired through the camera using
SURF for compared to the same object recognition then set ROI
(Region of Interest) for tracking movement of feature points using
Optical Flow. Secondly, using Multi-Thread is for improved
processing speed and recognition by parallel processing. Finally,
performance is evaluated and verified efficiency of algorithm
throughout the experiment.
Abstract: This paper presents an algorithm for the recognition
and tracking of moving objects, 1/10 scale model car is used to verify
performance of the algorithm. Presented algorithm for the recognition
and tracking of moving objects in the paper is as follows. SURF
algorithm is merged with Lucas-Kanade algorithm. SURF algorithm
has strong performance on contrast, size, rotation changes and it
recognizes objects but it is slow due to many computational
complexities. Processing speed of Lucas-Kanade algorithm is fast but
the recognition of objects is impossible. Its optical flow compares the
previous and current frames so that can track the movement of a pixel.
The fusion algorithm is created in order to solve problems which
occurred using the Kalman Filter to estimate the position and the
accumulated error compensation algorithm was implemented. Kalman
filter is used to create presented algorithm to complement problems
that is occurred when fusion two algorithms. Kalman filter is used to
estimate next location, compensate for the accumulated error. The
resolution of the camera (Vision Sensor) is fixed to be 640x480. To
verify the performance of the fusion algorithm, test is compared to
SURF algorithm under three situations, driving straight, curve, and
recognizing cars behind the obstacles. Situation similar to the actual is
possible using a model vehicle. Proposed fusion algorithm showed
superior performance and accuracy than the existing object
recognition and tracking algorithms. We will improve the performance
of the algorithm, so that you can experiment with the images of the
actual road environment.