A Multi-Modal Gaze Tracking Algorithm

Author(s):  
Zhenjie Hou ◽  
Xin Chao ◽  
Jiuzhen Liang ◽  
Tianjin Yang

A person’s emotional information, needs and cognitive processes can be described by eye movement states and concerns, so gaze tracking was first applied in the field of psychology. With the continuous development of information technology, the application range of gaze tracking has expanded from psychology to medical, military, commercial and many other fields. Aiming at the problem of high misjudgment rate and long time-consuming of traditional iris location methods, this paper proposes a gaze tracking method based on human eye geometric characteristics to improve the tracking accuracy in 2D environment. First, the human face is located by face location algorithm and the position of human eye is estimated roughly. Then the iris template is built by iris image, and the iris center location algorithm is used to locate the iris center position. Finally, the eyes corners and iris center points are extracted to locate the eye area accurately and obtain the binocular image. The binocular images are input into the feature extraction network as multi-modal information in parallel, and the convoluted feature channels are reconstructed using the weight redistribution module in the network. Then the reconstructed features are fused in the full connection layer. Finally, the output layer is used to classify the reconstructed features. Experiments were carried out on a self-built screen block dataset. For 12 classified data, the lowest recognition error rate is 5.34%.

2021 ◽  
Vol 4 (1) ◽  
pp. 121-128
Author(s):  
Fitri Isnaini ◽  
Wahyudi Prabowo

In the era of Information Systems, development changes, especially in the field of sales, have changed very rapidly. AdiWangi Trading Company is one of the companies engaged in the sale of staple goods. In providing services to customers and the general public, PD Adiwangi has not been able to fulfill information needs optimally. The process of data collection is still done manually, so it takes a long time to complete it. With the current process, customers often feel that they have been served a long time and for the company itself there are often differences between the items in the data recorded and the items stored in PD Adiwangi, so that why this research uses waterfall method. The design stages used include program planning, program design, database, and program development. Inventory Information System with manual record by inputting into excel and record incoming goods. Whereas, outcoming goods recorded rarely, employees are not taken for placement on shelves. It has become a habit until now so that inventory of goods also not observed. From the results of the study, it can be concluded that the program design made named Inventory program design at PD AdiWangi. It is expected to facilitate the process of data collection, as well as making reports quickly and accurately compared to systems manually.


2014 ◽  
Vol 631-632 ◽  
pp. 649-653 ◽  
Author(s):  
Fang Jia ◽  
Kui Liu ◽  
De Cheng Xu

To minimize the deficiency of the existing indoor location methods for mobile robots, the RSSI (received signal strength indication) model of WLAN is established. Then a combined location method for mobile robots based on DR (dead reckoning) and WLAN is proposed, which employs PMLA (probability matching location algorithm) and KF (Kalman filter) for information fusion. Simulation results reveal that the combined location approach works well in eliminating the cumulative error of DR and reducing the fluctuation of WLAN location. As a result, the proposed method is capable of enhancing the positioning accuracy of mobile robots to a certain extent, promising a low-cost and reliable location scheme for its development.


2020 ◽  
Author(s):  
Barbara Czecze ◽  
István Bondár

<p>The objective of this work was to relocate the entire seismicity of the Pannonian Basin with the Bayesloc algorithm, a Markov-Chain Monte Carlo inversion scheme using a Bayesian statistical framework.</p><p><span>In the Hungarian National Seismological Bulletin the magnitudes and event locations are determined with the iLoc location algorithm using the 3D global RSTT velocity model, and we used these locations as initial coordinates. In our work, we have used all of the instrumentally registered seismic events between 1996 and 2019 in the Pannonian Basin.</span></p><p><span>During data preprocessing we used graph theory to measure data connectivity. Similar to all multiple-event location methods, Bayesloc performs better when events are recorded on a common network. </span></p><p><span>We used</span> <span>several hundreds</span> <span>of ground truth events (quarry blasts, mine explosions, earthquakes)</span> <span>to tie down</span> <span>the seismicity pattern to known ground truth locations by giving them tighter prior distributions.</span></p><p><span>Based on the day-time peak on the origin-hour distribution of the bulletin earthquakes we assume that there are anthropogenic events labeled as earthquakes in the catalog, therefore we created a „Suspected</span> <span>explosions (SX)” group to set prior constrains.</span></p><p><span>The results show that the events around the mines are dramatically better clustered. The prior constraints contributed remarkably to the outcome of the relocation. We show that the results present an improved view of the seismicity of the region.</span></p>


2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Hao Qin

Aiming at the problems of poor image tracking effect, low precision, and long time in the process of image tracking of volleyball player’s arm hitting, a volleyball player's arm hitting image tracking method based on D-P algorithm is proposed. This paper analyzes the basic concept, basic principle, and basic equation of D-P algorithm and collects the arm stroke trajectory image of volleyball players under the three-dimensional visual model. Using wavelet multiscale decomposition method, the arm stroke trajectory of volleyball players is filtered, and the edge contour feature points of the arm stroke image of volleyball players are extracted. Using the gray histogram feature extraction method, the gray information of volleyball player's arm hitting trajectory image is enhanced. Combined with pixel adaptive enhancement technology, the key action feature points of volleyball player's arm hitting image trajectory are located. Based on D-P algorithm, the volleyball player's arm hitting image trajectory is adjusted and modified to realize the correct tracking of volleyball player's arm hitting image trajectory. The experimental results show that the trajectory tracking effect of volleyball player's arm hitting image is better, which can effectively improve the tracking accuracy and shorten the tracking time.


Author(s):  
Harijanto Pangestu

At certain moments, especially on national holiday transportation users greatly increase. The manual ticket booking system of inter-city buses is not very effective and efficient as indicated that it takes long time to book tickets and find information about ticket availability for a specific purpose on a certain day. Besides, inaccuracies often happen on synchronizing ticket availability with seat availability. Due to those problems, it needs to be made a model of ticketing information system of inter-city buses. The initial phase focused on booking tickets at a branch office. The next stage of development is integrating the  information system of all branch offices to the central office. The purpose of this paper is to create a model of the system design if inter-city bus ticket reservation in inter-provincial branches can provide convenience for the branch to book tickets booked by customers. The methodology used in this research is a preliminary study by library research, followed by analysis on running systems through survey findings, then identification of information needs. From the results of this study it is found that a more specific design and implementation are expected to be made so as to provide more benefits to its users. The results of this study can be further developed and integrated with the central office.


2019 ◽  
Vol 9 (1) ◽  
pp. 1
Author(s):  
Alfi Rusdianti ◽  
Fitri Arofiati

Intensive care unit (ICU) is in principle not designed to accept the presence of a patient's visitor or family for a long time. One of the effects that arises is an increase in the patient's family anxiety. In general, nurses do not consider the patient's family as part of his holistic care. So, it takes the role of nurses to identify the patient's family needs, in order to realize holistic care. This review aims to identify the family needs of patients treated in the intensive care unit. Literature is obtained from the Ebsco database, ProQuest and Science Direct, using keywords: family needs, nursing strategy and intensive care unit. From 7 literature sources obtained about what is needed by the patient's family. This review produced 5 themes, namely family needs for information, closeness, support, involvement, and knowing the care received by patients. This review only focuses on the patient's family needs in general. The family is part of the patient. Identified family needs, namely information needs, closeness, support, involvement and knowledge of care received by patients. The participation of health workers is needed in identifying and encouraging the fulfillment of family needs. Keyword: family needs, nursing strategies, intensive care unit


2022 ◽  
Vol 11 (1) ◽  
Author(s):  
Eléonore Roussel ◽  
Christophe Szwaj ◽  
Clément Evain ◽  
Bernd Steffen ◽  
Christopher Gerth ◽  
...  

AbstractRecording electric field evolution in single-shot with THz bandwidth is needed in science including spectroscopy, plasmas, biology, chemistry, Free-Electron Lasers, accelerators, and material inspection. However, the potential application range depends on the possibility to achieve sub-picosecond resolution over a long time window, which is a largely open problem for single-shot techniques. To solve this problem, we present a new conceptual approach for the so-called spectral decoding technique, where a chirped laser pulse interacts with a THz signal in a Pockels crystal, and is analyzed using a grating optical spectrum analyzer. By borrowing mathematical concepts from photonic time stretch theory and radio-frequency communication, we deduce a novel dual-output electro-optic sampling system, for which the input THz signal can be numerically retrieved—with unprecedented resolution—using the so-called phase diversity technique. We show numerically and experimentally that this approach enables the recording of THz waveforms in single-shot over much longer durations and/or higher bandwidth than previous spectral decoding techniques. We present and test the proposed DEOS (Diversity Electro-Optic Sampling) design for recording 1.5 THz bandwidth THz pulses, over 20 ps duration, in single-shot. Then we demonstrate the potential of DEOS in accelerator physics by recording, in two successive shots, the shape of 200 fs RMS relativistic electron bunches at European X-FEL, over 10 ps recording windows. The designs presented here can be used directly for accelerator diagnostics, characterization of THz sources, and single-shot Time-Domain Spectroscopy.


2019 ◽  
Author(s):  
Irmawati Carolina ◽  
Akim Manaor Hara Pardede ◽  
Adi Supriyatna

Quota calculation for teaching lecturers to become routine activities carried out every month which is used as a reference for payment of honorarium teaching lecturers and management decision making. Calculation of teaching credits that are done manually requires quite a long time due to the increasing number of lecturers. In addition, mistakes and errors often occur in the credit calculation process and cause complaints from lecturers who teach in each semester. The purpose of this study is to build an application that can calculate the number of credits to teach lecturers quickly and accurately. Designing an application certainly requires a method that is specific to help during the process. Based on the developmental needs of the method, one of the important elements in the development of information needs. The method used in the design of this application is Extreme Programming which is a method that has four stages in its implementation, namely planning, designing, coding and testing. Through these four stages, it is expected that the results will be maximized and can be more helpful in the process needed. The results of this study in the form of a quota mapping application teaching lecturers that can provide convenience and accuracy in calculating the number of credits teaching lecturers quickly and accurately, able to reduce errors in the calculation process and can minimize complaints from lecturers related to teaching fees obtained


2018 ◽  
Vol 4 (2) ◽  
pp. 159-168
Author(s):  
Aris Aris ◽  
Tiya Puspita Firdaus ◽  
Neha Nurseha

Data processing system of Higher Education Raharja needs the best and integrated to facilitate decision making and create good service standard. Especially if the data is related to Control and Quality. Data and information easily accessible to support the performance of each section. As in theEngineering section, In data processing Engineering section still can not provide the best service to meet the strategic information needs required to support reporting on the management of Higher Education Raharja. It takes a long time to generate information data items as required, this happens because it has not been integrated with the management and information processing can not be effective and efficient, With the design method using UML, as well as making the application program using PHP programming language website based .So can help in reporting data goods engineering section for management that can improve the performance of engineering section for Higher Education Raharja so as to provide good and faster service.


Sign in / Sign up

Export Citation Format

Share Document