Abstract: H.264/AVC offers a considerably higher improvement
in coding efficiency compared to other compression standards such
as MPEG-2, but computational complexity is increased significantly.
In this paper, we propose selective mode decision schemes for fast
intra prediction mode selection. The objective is to reduce the
computational complexity of the H.264/AVC encoder without
significant rate-distortion performance degradation. In our proposed
schemes, the intra prediction complexity is reduced by limiting the
luma and chroma prediction modes using the directional information
of the 16×16 prediction mode. Experimental results are presented to
show that the proposed schemes reduce the complexity by up to 78%
maintaining the similar PSNR quality with about 1.46% bit rate
increase in average.
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 paper presents a system for tracking the movement of laparoscopic instruments which is based on an orthogonal system of webcams and video image processing. The movements are captured with two webcams placed orthogonally inside of the physical trainer. On the image, the instruments were detected by using color markers placed on the distal tip of each instrument. The 3D position of the tip of the instrument within the work space was obtained by linear triangulation method. Preliminary results showed linearity and repeatability in the motion tracking with a resolution of 0.616 mm in each axis; the accuracy of the system showed a 3D instrument positioning error of 1.009 ± 0.101 mm. This tool is a portable and low-cost alternative to traditional tracking devices and a trustable method for the objective evaluation of the surgeon’s surgical skills.
Abstract: This paper describes a prototype aircraft that can fly
slowly, safely and transmit wireless video for tasks like reconnaissance,
surveillance and target acquisition. The aircraft is designed to
fly in closed quarters like forests, buildings, caves and tunnels which
are often spacious but GPS reception is poor. Envisioned is that a
small, safe and slow flying vehicle can assist in performing dull,
dangerous and dirty tasks like disaster mitigation, search-and-rescue
and structural damage assessment.
Abstract: This paper describes new computer vision algorithms
that have been developed to track moving objects as part of a
long-term study into the design of (semi-)autonomous vehicles. We
present the results of a study to exploit variable kernels for tracking in
video sequences. The basis of our work is the mean shift
object-tracking algorithm; for a moving target, it is usual to define a
rectangular target window in an initial frame, and then process the data
within that window to separate the tracked object from the background
by the mean shift segmentation algorithm. Rather than use the
standard, Epanechnikov kernel, we have used a kernel weighted by the
Chamfer distance transform to improve the accuracy of target
representation and localization, minimising the distance between the
two distributions in RGB color space using the Bhattacharyya
coefficient. Experimental results show the improved tracking
capability and versatility of the algorithm in comparison with results
using the standard kernel. These algorithms are incorporated as part of
a robot test-bed architecture which has been used to demonstrate their
effectiveness.
Abstract: Video Mosaicing is the stitching of selected frames of
a video by estimating the camera motion between the frames and
thereby registering successive frames of the video to arrive at the
mosaic. Different techniques have been proposed in the literature for
video mosaicing. Despite of the large number of papers dealing with
techniques to generate mosaic, only a few authors have investigated
conditions under which these techniques generate good estimate of
motion parameters. In this paper, these techniques are studied under
different videos, and the reasons for failures are found. We propose
algorithms with incorporation of outlier removal algorithms for better
estimation of motion parameters.
Abstract: In this paper we illuminate a frequency domain based
classification method for video scenes. Videos from certain topical
areas often contain activities with repeating movements. Sports
videos, home improvement videos, or videos showing mechanical
motion are some example areas. Assessing main and side frequencies
of each repeating movement gives rise to the motion type. We
obtain the frequency domain by transforming spatio-temporal motion
trajectories. Further on we explain how to compute frequency features
for video clips and how to use them for classifying. The focus of
the experimental phase is on transforms utilized for our system.
By comparing various transforms, experiments show the optimal
transform for a motion frequency based approach.
Abstract: Using the animations video of teaching materials is an
effective learning method. However, we thought that more effective learning method is to produce the teaching video by learners
themselves. The learners who act as the producer must learn and understand well to produce and present video of teaching materials to
others. The purpose of this study is to propose the project based learning (PBL) technique by co-producing video of IT (information
technology) teaching materials. We used the T2V player to produce
the video based on TVML a TV program description language. By
proposed method, we have assigned the learners to produce the
animations video for “National Examination for Information
Processing Technicians (IPA examination)" in Japan, in order to get
them learns various knowledge and skill on IT field. Experimental
result showed that learning effect has occurred at the video production
process that useful for IT personnel resources development.
Abstract: Motion estimation is a key problem in video
processing and computer vision. Optical flow motion estimation can
achieve high estimation accuracy when motion vector is small.
Three-step search algorithm can handle large motion vector but not
very accurate. A joint algorithm was proposed in this paper to
achieve high estimation accuracy disregarding whether the motion
vector is small or large, and keep the computation cost much lower
than full search.
Abstract: Vision based tracking problem is solved through a
combination of optical flow, MACH filter and log r-θ mapping.
Optical flow is used for detecting regions of movement in video
frames acquired under variable lighting conditions. The region of
movement is segmented and then searched for the target. A template
is used for target recognition on the segmented regions for detecting
the region of interest. The template is trained offline on a sequence of
target images that are created using the MACH filter and log r-θ
mapping. The template is applied on areas of movement in
successive frames and strong correlation is seen for in-class targets.
Correlation peaks above a certain threshold indicate the presence of
target and the target is tracked over successive frames.
Abstract: Electro-optical devices are increasingly used for
military sea-, land- and air applications to detect, recognize and track
objects. Typically, these devices produce video information that is
presented to an operator. However, with increasing availability of
electro-optical devices the data volume is becoming very large,
creating a rising need for automated analysis. In a military setting,
this typically involves detecting and recognizing objects at a large
distance, i.e. when they are difficult to distinguish from background
and noise. One may consider combining multiple images from a
video stream into a single enhanced image that provides more
information for the operator. In this paper we investigate a simple
algorithm to enhance simulated images from a military context and
investigate how the enhancement is affected by various types of
disturbance.
Abstract: Video sensor networks operate on stringent requirements
of latency. Packets have a deadline within which they have
to be delivered. Violation of the deadline causes a packet to be
treated as lost and the loss of packets ultimately affects the quality
of the application. Network latency is typically a function of many
interacting components. In this paper, we propose ways of reducing
the forwarding latency of a packet at intermediate nodes. The
forwarding latency is caused by a combination of processing delay
and queueing delay. The former is incurred in order to determine the
next hop in dynamic routing. We show that unless link failures in a
very specific and unlikely pattern, a vast majority of these lookups
are redundant. To counter this we propose source routing as the
routing strategy. However, source routing suffers from issues related
to scalability and being impervious to network dynamics. We propose
solutions to counter these and show that source routing is definitely
a viable option in practical sized video networks. We also propose a
fast and fair packet scheduling algorithm that reduces queueing delay
at the nodes. We support our claims through extensive simulation on
realistic topologies with practical traffic loads and failure patterns.
Abstract: Wireless LAN (WLAN) access in public hotspot areas
becomes popular in the recent years. Since more and more multimedia
information is available in the Internet, there is an increasing demand
for accessing multimedia information through WLAN hotspots.
Currently, the bandwidth offered by an IEEE 802.11 WLAN cannot
afford many simultaneous real-time video accesses. A possible way to
increase the offered bandwidth in a hotspot is the use of multiple access
points (APs). However, a mobile station is usually connected to the
WLAN AP with the strongest received signal strength indicator (RSSI).
The total consumed bandwidth cannot be fairly allocated among those
APs. In this paper, we will propose an effective load-balancing scheme
via the support of the IAPP and SNMP in APs. The proposed scheme is
an open solution and doesn-t need any changes in both wireless stations
and APs. This makes load balancing possible in WLAN hotspots,
where a variety of heterogeneous mobile devices are employed.
Abstract: Understanding road features such as lanes, the color
of lanes, and sidewalks in a live video captured from a moving
vehicle is essential to build video-based navigation systems. In this
paper, we present a novel idea to understand the road features using
support vector machines. Various feature vectors including color
components of road markings and the difference between two
regions, i.e., chosen AOIs, and so on are fed into SVM, deciding
colors of lanes and sidewalks robustly. Experimental results are
provided to show the robustness of the proposed idea.
Abstract: Detecting object in video sequence is a challenging
mission for identifying, tracking moving objects. Background
removal considered as a basic step in detected moving objects tasks.
Dual static cameras placed in front and rear moving platform
gathered information which is used to detect objects. Background
change regarding with speed and direction moving platform, so
moving objects distinguished become complicated. In this paper, we
propose framework allows detection moving object with variety of
speed and direction dynamically. Object detection technique built on
two levels the first level apply background removal and edge
detection to generate moving areas. The second level apply Moving
Areas Filter (MAF) then calculate Correlation Score (CS) for
adjusted moving area. Merging moving areas with closer CS and
marked as moving object. Experiment result is prepared on real scene
acquired by dual static cameras without overlap in sense. Results
showing accuracy in detecting objects compared with optical flow
and Mixture Module Gaussian (MMG), Accurate ratio produced to
measure accurate detection moving object.
Abstract: This paper makes a contribution to the on-going
debate on conceptualization and lexicalization of cutting and
breaking (C&B) verbs by discussing data from Telugu, a language of
India belonging to the Dravidian family. Five Telugu native speakers-
verbalizations of agentive actions depicted in 43 short video-clips
were analyzed. It was noted that verbalization of C&B events in
Telugu requires formal units such as simple lexical verbs, explicator
compound verbs, and other complex verb forms. The properties of
the objects involved, the kind of instruments used, and the manner of
action had differential influence on the lexicalization patterns.
Further, it was noted that all the complex verb forms encode 'result'
and 'cause' sub-events in that order. Due to the polysemy associated
with some of the verb forms, our data does not support the
straightforward bipartition of this semantic domain.
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: Vision-based intelligent vehicle applications often require large amounts of memory to handle video streaming and image processing, which in turn increases complexity of hardware and software. This paper presents an FPGA implement of a vision-based blind spot warning system. Using video frames, the information of the blind spot area turns into one-dimensional information. Analysis of the estimated entropy of image allows the detection of an object in time. This idea has been implemented in the XtremeDSP video starter kit. The blind spot warning system uses only 13% of its logic resources and 95k bits block memory, and its frame rate is over 30 frames per sec (fps).
Abstract: A virtual collaborative classroom was created at East Carolina University, using videoconference technology via regular internet to bring students from 18 different countries, 2 at a time, to the ECU classroom in real time to learn about each other-s culture. Students from two countries are partnered one on one, they meet for 4-5 weeks, and submit a joint paper. Then the same process is repeated for two other countries. Lectures and student discussions are managed with pre-determined topics and questions. Classes are conducted in English and reading assignments are placed on the website. Administratively all partners are independent, students pay fees and get credits at their home institution. Familiarity with technology, knowledge in cultural understanding and attitude change were assessed, only attitude changes are reported in this paper. After taking this course, all students stated their comfort level in working with, and their desire to interact with, culturally different others grew stronger and their xenophobia and isolationist attitudes decreased.
Abstract: In real-time networks a large number of application programs are relying on video data and heterogeneous data transmission techniques. The aim of this research is presenting a method for end-to-end vouch quality service in surface applicationlayer for sending video data in comparison form in wireless heterogeneous networks. This method tries to improve the video sending over the wireless heterogeneous networks with used techniques in surface layer, link and application. The offered method is showing a considerable improvement in quality observing by user. In addition to this, other specifications such as shortage of data load that had require to resending and limited the relation period length to require time for second data sending, help to be used the offered method in the wireless devices that have a limited energy. The presented method and the achieved improvement is simulated and presented in the NS-2 software.