Abstract: The ability to recognize humans and their activities by computer vision is a very important task, with many potential application. Study of human motion analysis is related to several research areas of computer vision such as the motion capture, detection, tracking and segmentation of people. In this paper, we describe a segmentation method for extracting human body contour in modified HLS color space. To estimate a background, the modified HLS color space is proposed, and the background features are estimated by using the HLS color components. Here, the large amount of human dataset, which was collected from DV cameras, is pre-processed. The human body and its contour is successfully extracted from the image sequences.
Abstract: An important step in three-dimensional reconstruction
and computer vision is camera calibration, whose objective is to
estimate the intrinsic and extrinsic parameters of each camera. In this
paper, two linear methods based on the different planes are given. In
both methods, the general plane is used to replace the calibration
object with very good precision. In the first method, after controlling
the camera to undergo five times- translation movements and taking
pictures of the orthogonal planes, a set of linear constraints of the
camera intrinsic parameters is then derived by means of homography
matrix. The second method is to get all camera parameters by taking
only one picture of a given radius circle. experiments on simulated
data and real images,indicate that our method is reasonable and is a
good supplement to camera calibration.
Abstract: The objective of this paper, is to apply support vector machine (SVM) approach for the classification of cancerous and normal regions of prostate images. Three kinds of textural features are extracted and used for the analysis: parameters of the Gauss- Markov random field (GMRF), correlation function and relative entropy. Prostate images are acquired by the system consisting of a microscope, video camera and a digitizing board. Cross-validated classification over a database of 46 images is implemented to evaluate the performance. In SVM classification, sensitivity and specificity of 96.2% and 97.0% are achieved for the 32x32 pixel block sized data, respectively, with an overall accuracy of 96.6%. Classification performance is compared with artificial neural network and k-nearest neighbor classifiers. Experimental results demonstrate that the SVM approach gives the best performance.
Abstract: Manufacturing components of fiber-reinforced
thermoplastics requires three steps: heating the matrix, forming and
consolidation of the composite and terminal cooling the matrix. For
the heating process a pre-determined temperature distribution through
the layers and the thickness of the pre-consolidated sheets is
recommended to enable forming mechanism. Thus, a design for the
heating process for forming composites with thermoplastic matrices
is necessary. To obtain a constant temperature through thickness and
width of the sheet, the heating process was analyzed by the help of
the finite element method. The simulation models were validated by
experiments with resistance thermometers as well as with an infrared
camera. Based on the finite element simulation, heating methods for
infrared radiators have been developed. Using the numeric
simulation many iteration loops are required to determine the process
parameters. Hence, the initiation of a model for calculating relevant
process parameters started applying regression functions.
Abstract: The purpose of this study is to design a portable virtual
piano. By utilizing optical fiber gloves and the virtual piano software
designed by this study, the user can play the piano anywhere at any
time. This virtual piano consists of three major parts: finger tapping
identification, hand movement and positioning identification, and
MIDI software sound effect simulation. To play the virtual piano, the
user wears optical fiber gloves and simulates piano key tapping
motions. The finger bending information detected by the optical fiber
gloves can tell when piano key tapping motions are made. Images
captured by a video camera are analyzed, hand locations and moving
directions are positioned, and the corresponding scales are found. The
system integrates finger tapping identification with information about
hand placement in relation to corresponding piano key positions, and
generates MIDI piano sound effects based on this data. This
experiment shows that the proposed method achieves an accuracy rate
of 95% for determining when a piano key is tapped.
Abstract: One of the main issues in Computer Vision is to extract the movement of one or several points or objects of interest in an image or video sequence to conduct any kind of study or control process. Different techniques to solve this problem have been applied in numerous areas such as surveillance systems, analysis of traffic, motion capture, image compression, navigation systems and others, where the specific characteristics of each scenario determine the approximation to the problem. This paper puts forward a Computer Vision based algorithm to analyze fish trajectories in high turbulence conditions in artificial structures called vertical slot fishways, designed to allow the upstream migration of fish through obstructions in rivers. The suggested algorithm calculates the position of the fish at every instant starting from images recorded with a camera and using neural networks to execute fish detection on images. Different laboratory tests have been carried out in a full scale fishway model and with living fishes, allowing the reconstruction of the fish trajectory and the measurement of velocities and accelerations of the fish. These data can provide useful information to design more effective vertical slot fishways.
Abstract: The aim of this study was to develop a dynamic cardiac phantom for quality control in myocardial scintigraphy. The dynamic heart phantom constructed only contained the left ventricle, made of elastic material (latex), comprising two cavities: one internal and one external. The data showed a non-significant variation in the values of left ventricular ejection fraction (LVEF) obtained by varying the heart rate. It was also possible to evaluate the ejection fraction (LVEF) through different arrays of image acquisition and to perform an intercomparison of LVEF by two different scintillation cameras. The results of the quality control tests were satisfactory, showing that they can be used as parameters in future assessments. The new dynamic heart phantom was demonstrated to be effective for use in LVEF measurements. Therefore, the new heart simulator is useful for the quality control of scintigraphic cameras.
Abstract: This paper addresses the problem of recognizing and
interpreting the behavior of human workers in industrial
environments for the purpose of integrating humans in software
controlled manufacturing environments. In this work we propose a
generic concept in order to derive solutions for task-related manual
production applications. Thus, we are able to use a versatile concept
providing flexible components and being less restricted to a specific
problem or application. We instantiate our concept in a spot welding
scenario in which the behavior of a human worker is interpreted
when performing a welding task with a hand welding gun. We
acquire signals from inertial sensors, video cameras and triggers and
recognize atomic actions by using pose data from a marker based
video tracking system and movement data from inertial sensors.
Recognized atomic actions are analyzed on a higher evaluation level
by a finite state machine.
Abstract: With advances in computer vision, non-contact gaze tracking systems are heading towards being much easier to operate and more comfortable for use, the technique proposed in this paper is specially designed for achieving these goals. For the convenience in operation, the proposal aims at the system with simple configuration which is composed of a fixed wide angle camera and dual infrared illuminators. Then in order to enhance the usability of the system based on single camera, a self-adjusting method which is called Real-time gaze Tracking Algorithm with head movement Compensation (RTAC) is developed for estimating the gaze direction under natural head movement and simplifying the calibration procedure at the same time. According to the actual evaluations, the average accuracy of about 1° is achieved over a field of 20×15×15 cm3.
Abstract: A new hybrid method to realise high-precision
distortion determination for optical ultra-precision 3D measurement
systems based on stereo cameras using active light projection is
introduced. It consists of two phases: the basic distortion
determination and the refinement. The refinement phase of the
procedure uses a plane surface and projected fringe patterns as
calibration tools to determine simultaneously the distortion of both
cameras within an iterative procedure. The new technique may be
performed in the state of the device “ready for measurement" which
avoids errors by a later adjustment. A considerable reduction of
distortion errors is achieved and leads to considerable improvements
of the accuracy of 3D measurements, especially in the precise
measurement of smooth surfaces.
Abstract: In the last years numerous applications of Human-
Computer Interaction have exploited the capabilities of Time-of-
Flight cameras for achieving more and more comfortable and precise
interactions. In particular, gesture recognition is one of the most active
fields. This work presents a new method for interacting with a virtual
object in a 3D space. Our approach is based on the fusion of depth
data, supplied by a ToF camera, with color information, supplied
by a HD webcam. The hand detection procedure does not require
any learning phase and is able to concurrently manage gestures of
two hands. The system is robust to the presence in the scene of
other objects or people, thanks to the use of the Kalman filter for
maintaining the tracking of the hands.
Abstract: Skyline extraction in mountainous images can be used
for navigation of vehicles or UAV(unmanned air vehicles), but it is
very hard to extract skyline shape because of clutters like clouds, sea
lines and field borders in images. We developed the edge-based
skyline extraction algorithm using a proposed multistage edge filtering
(MEF) technique. In this method, characteristics of clutters in the
image are first defined and then the lines classified as clutters are
eliminated by stages using the proposed MEF technique. After this
processing, we select the last line using skyline measures among the
remained lines. This proposed algorithm is robust under severe
environments with clutters and has even good performance for
infrared sensor images with a low resolution. We tested this proposed
algorithm for images obtained in the field by an infrared camera and
confirmed that the proposed algorithm produced a better performance
and faster processing time than conventional algorithms.
Abstract: In this paper application of artificial intelligence for
baby and children caring is studied. Then a new idea for injury
prevention and safety announcement is presented by using digital
image processing. The paper presents the structure of the proposed
system. The system determines the possibility of the dangers for
children and babies in yards, gardens and swimming pools or etc. In
the presented idea, multi camera System is used and receiver videos
are processed to find the hazardous areas then the entrance of
children and babies in the determined hazardous areas are analyzed.
In this condition the system does the programmed action capture,
produce alarm or tone or send message.
Abstract: This paper presents a review on vision aided systems
and proposes an approach for visual rehabilitation using stereo vision
technology. The proposed system utilizes stereo vision, image
processing methodology and a sonification procedure to support
blind navigation. The developed system includes a wearable
computer, stereo cameras as vision sensor and stereo earphones, all
moulded in a helmet. The image of the scene infront of visually
handicapped is captured by the vision sensors. The captured images
are processed to enhance the important features in the scene in front,
for navigation assistance. The image processing is designed as model
of human vision by identifying the obstacles and their depth
information. The processed image is mapped on to musical stereo
sound for the blind-s understanding of the scene infront. The
developed method has been tested in the indoor and outdoor
environments and the proposed image processing methodology is
found to be effective for object identification.
Abstract: In this work a dual laser triangulation system is presented for fast building of 2.5D textured models of objects within a production line. This scanner is designed to produce data suitable for 3D completeness inspection algorithms. For this purpose two laser projectors have been used in order to considerably reduce the problem of occlusions in the camera movement direction. Results of reconstruction of electronic boards are presented, together with a comparison with a commercial system.
Abstract: A camera in the building site is exposed to different
weather conditions. Differences between images of the same scene
captured with the same camera arise also due to temperature variations.
The influence of temperature changes on camera parameters
were modelled and integrated into existing analytical camera model.
Modified camera model enables quantitatively assessing the influence
of temperature variations.
Abstract: Agriculture products are being more demanding in
market today. To increase its productivity, automation to produce
these products will be very helpful. The purpose of this work is to
measure and determine the ripeness and quality of watermelon. The
textures on watermelon skin will be captured using digital camera.
These images will be filtered using image processing technique. All
these information gathered will be trained using ANN to determine
the watermelon ripeness accuracy. Initial results showed that the best
model has produced percentage accuracy of 86.51%, when measured
at 32 hidden units with a balanced percentage rate of training dataset.
Abstract: Real-time hand tracking is a challenging task in many
computer vision applications such as gesture recognition. This paper
proposes a robust method for hand tracking in a complex environment
using Mean-shift analysis and Kalman filter in conjunction with 3D
depth map. The depth information solve the overlapping problem
between hands and face, which is obtained by passive stereo measuring
based on cross correlation and the known calibration data of
the cameras. Mean-shift analysis uses the gradient of Bhattacharyya
coefficient as a similarity function to derive the candidate of the hand
that is most similar to a given hand target model. And then, Kalman
filter is used to estimate the position of the hand target. The results
of hand tracking, tested on various video sequences, are robust to
changes in shape as well as partial occlusion.
Abstract: It is important to give input information without other device in AR system. One solution is using hand for augmented reality application. Many researchers have proposed different solutions for hand interface in augmented reality. Analyze Histogram and connecting factor is can be example for that. Various Direction searching is one of robust way to recognition hand but it takes too much calculating time. And background should be distinguished with skin color. This paper proposes a hand tracking method to control the 3D object in augmented reality using depth device and skin color. Also in this work discussed relationship between several markers, which is based on relationship between camera and marker. One marker used for displaying virtual object and three markers for detecting hand gesture and manipulating the virtual object.
Abstract: Existing image-based virtual reality applications
allow users to view image-based 3D virtual environment in a more
interactive manner. User could “walkthrough"; looks left, right, up
and down and even zoom into objects in these virtual worlds of
images. However what the user sees during a “zoom in" is just a
close-up view of the same image which was taken from a distant.
Thus, this does not give the user an accurate view of the object from
the actual distance. In this paper, a simple technique for zooming in
an object in a virtual scene is presented. The technique is based on
the 'hotspot' concept in existing application. Instead of navigation
between two different locations, the hotspots are used to focus into
an object in the scene. For each object, several hotspots are created.
A different picture is taken for each hotspot. Each consecutive
hotspot created will take the user closer to the object. This will
provide the user with a correct of view of the object based on his
proximity to the object. Implementation issues and the relevance of
this technique in potential application areas are highlighted.