• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.6
• /
• pp.114-123
• /
• 2023

With the development of computer vision technology, video sensors such as CCTV are detecting incident. However, most of the current incident have been detected based on existing fixed imaging equipment. Accordingly, there has been a limit to the detection of incident in shaded areas where the image range of fixed equipment is not reached. With the recent development of edge-computing technology, real-time analysis of mobile image information has become possible. The purpose of this study is to evaluate the possibility of detecting expressway emergencies by introducing computer vision technology to dash cam. To this end, annotation data was constructed based on 4,388 dash cam still frame data collected by the Korea Expressway Corporation and analyzed using the YOLO algorithm. As a result of the analysis, the prediction accuracy of all objects was over 70%, and the precision of traffic accidents was about 85%. In addition, in the case of mAP(mean Average Precision), it was 0.769, and when looking at AP(Average Precision) for each object, traffic accidents were the highest at 0.904, and debris were the lowest at 0.629.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.1
• /
• pp.96-110
• /
• 2017

Most of vehicle detection studies using the existing general lens or wide-angle lens have a blind spot in the rear detection situation, the image is vulnerable to noise and a variety of external environments. In this paper, we propose a method that is detection in harsh external environment with noise, blind spots, etc. First, using a fish-eye lens will help minimize blind spots compared to the wide-angle lens. When angle of the lens is growing because nonlinear radial distortion also increase, calibration was used after initializing and optimizing the distortion constant in order to ensure accuracy. In addition, the original image was analyzed along with calibration to remove fog and calibrate brightness and thereby enable detection even when visibility is obstructed due to light and dark adaptations from foggy situations or sudden changes in illumination. Fog removal generally takes a considerably significant amount of time to calculate. Thus in order to reduce the calculation time, remove the fog used the major fog removal algorithm Dark Channel Prior. While Gamma Correction was used to calibrate brightness, a brightness and contrast evaluation was conducted on the image in order to determine the Gamma Value needed for correction. The evaluation used only a part instead of the entirety of the image in order to reduce the time allotted to calculation. When the brightness and contrast values were calculated, those values were used to decided Gamma value and to correct the entire image. The brightness correction and fog removal were processed in parallel, and the images were registered as a single image to minimize the calculation time needed for all the processes. Then the feature extraction method HOG was used to detect the vehicle in the corrected image. As a result, it took 0.064 seconds per frame to detect the vehicle using image correction as proposed herein, which showed a 7.5% improvement in detection rate compared to the existing vehicle detection method.

• Journal of KIISE:Computing Practices and Letters
• /
• v.9 no.4
• /
• pp.393-409
• /
• 2003

In this paper, we present a multi-task debugging environment for Qplus-T embedded-system such as internet information appliances. We will propose the structure and functions of a remote multi-task debugging environment supporting environment effective ross-development. And, we are going enhance the communication architecture between the host and target system to provide more efficient cross-development environment. The remote development toolset called Q+Esto consists to several independent support tools: an interactive shell, a remote debugger, a resource monitor, a target manager and a debug agent. Excepting a debug agent, all these support tools reside on the host systems. Using the remote multi-task debugger on the host, the developer can spawn and debug tasks on the target run-time system. It can also be attached to already-running tasks spawned from the application or from interactive shell. Application code can be viewed as C/C++ source, or as assembly-level code. It incorporates a variety of display windows for source, registers, local/global variables, stack frame, memory, event traces and so on. The target manager implements common functions that are shared by Q+Esto tools, e.g., the host-target communication, object file loading, and management of target-resident host tool´s memory pool and target system´s symbol-table, and so on. These functions are called OPEn C APIs and they greatly improve the extensibility of the Q+Esto Toolset. The Q+Esto target manager is responsible for communicating between host and target system. Also, there exist a counterpart on the target system communicating with the host target manager, which is called debug agent. Debug agent is a daemon task on real-time operating systems in the target system. It gets debugging requests from the host tools including debugger via target manager, interprets the requests, executes them and sends the results to the host.

• The KIPS Transactions:PartB
• /
• v.14B no.4
• /
• pp.311-320
• /
• 2007

This paper presents vision-based 3D facial expression animation technique and system which provide the robust 3D head pose estimation and real-time facial expression control. Many researches of 3D face animation have been done for the facial expression control itself rather than focusing on 3D head motion tracking. However, the head motion tracking is one of critical issues to be solved for developing realistic facial animation. In this research, we developed an integrated animation system that includes 3D head motion tracking and facial expression control at the same time. The proposed system consists of three major phases: face detection, 3D head motion tracking, and facial expression control. For face detection, with the non-parametric HT skin color model and template matching, we can detect the facial region efficiently from video frame. For 3D head motion tracking, we exploit the cylindrical head model that is projected to the initial head motion template. Given an initial reference template of the face image and the corresponding head motion, the cylindrical head model is created and the foil head motion is traced based on the optical flow method. For the facial expression cloning we utilize the feature-based method, The major facial feature points are detected by the geometry of information of the face with template matching and traced by optical flow. Since the locations of varying feature points are composed of head motion and facial expression information, the animation parameters which describe the variation of the facial features are acquired from geometrically transformed frontal head pose image. Finally, the facial expression cloning is done by two fitting process. The control points of the 3D model are varied applying the animation parameters to the face model, and the non-feature points around the control points are changed by use of Radial Basis Function(RBF). From the experiment, we can prove that the developed vision-based animation system can create realistic facial animation with robust head pose estimation and facial variation from input video image.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.14 no.1
• /
• pp.12-25
• /
• 2003

Objectives：As increasing number of new antidepressants have been being introduced in clinical practice, pharmacological understanding has been broadened. These changes mandate new information and theories to be incorporated into the treatment process of children with depressive disorders. In light of newly coming knowledge, this review intended to recapitulate the characteristics of new antidepressants and to consider the pivotal issues to develope guidelines for the treatment of depression in childhood and adolescence. Methods：Searching the Pub-Med online database for the articles with the key words of 'new', 'antidepressants' and 'children' ninety-seven headings of review articles were obtained. The author selected the articles of pertinent subjects in terms of either treatment guideline or psychopharmacology of new antidepressants. When required, articles about the clinical effectiveness of individual antidepressants were separatedly searched. In addition, the safety information of new antidepressants was acquired by browsing the official sites of the United States Food and Drugs Administration and Department of Health and Human Services. Results：1) For the clinical course, treatment phase, and treatment outcome, the reviews or treatment guidelines adopted the information from adult treatment guidelines. 2) Systematic and critical reviews unambiguously concluded that selective serotonin reuptake inhibitors(SSRIs) excelled tricyclic antidepressants( TCAs) for both efficacy and side effect profiles, and were recommend for the first-line choice for the treatment of children with depressive disorders. 3) New antidepressants generally lacked treatment experiences and randomized controlled clinical trials. 4) SSRIs and other new antidepressants, when used together, might result in pharmacokinetic and/or pharmacodynamic drug-to-drug interaction. 5) The difference of the clinical effectiveness of antidepressants between children and adults should be addressed from developmental aspects, which required further evidence. Conclusion：Treatment guidelines for the pharmacological treatment of childhood and adolescence depression could be constructed on the basis of clinical trial findings and practical experiences. Treatment guidelines are to best serve as the frame of reference for a clinician to make reasonable decisions for a particular therapeutic situation. In order to fulfill this role, guidelines should be updated as soon as new research data become available.

• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.135-155
• /
• 2018

The purpose of this study is to analyze the difference of interpretation level and intention to use message framing when autonomous vehicle, which is emerging as the product of 4th industrial revolution, is used as taxi, Interpretation level refers to the interpretation of a product or service, assuming that it will happen in the near future or in the distant future. Message framing refers to the formation of positive or negative expressions or messages at the extremes of benefits and losses. In other words, previous studies interpret the value of a product or service differently according to these two concepts. The purpose of this study is to investigate whether there are differences in intention to use when two concepts are applied when an autonomous vehicle is launched as a taxi. The results are summarized as follows: First, the message format explaining the gain and why should be used when using the autonomous taxi in the message framing configuration, and the loss and how when the autonomous taxi is not used. Messages were constructed and compared. The two message framing differed (t = 3.063), and the message type describing the benefits and reasons showed a higher intention to use. In addition, the results according to interpretation level are summarized as follows. There was a difference in intentions to use when assuming that it would occur in the near future and in the near future with respect to the gain and loss, Respectively. In summary, in order to increase the intention of using autonomous taxis, it is concluded that messages should be given to people assuming positive messages (Gain) and what can happen in the distant future. In addition, this study will be able to utilize the research method in studying intention to use new technology. However, this study has the following limitations. First, it assumes message framing and time without user experience of autonomous taxi. This will be different from the actual experience of using an autonomous taxi in the future. Second, self-driving cars should technical progress is continuing, but laws and institutions must be established in order to commercialize it and build the infrastructure to operate the autonomous car. Considering this fact, the results of this study can not reflect a more realistic aspect. However, there is a practical limit to search for users with sufficient experience in new technologies such as autonomous vehicles. In fact, although the autonomous car to take advantage of the public transportation by taxi is now ready for the road infrastructure, and technical and legal public may not be willing to choose to not have enough knowledge to use the Autonomous cab. Therefore, the main purpose of this study is that by assuming that autonomous cars will be commercialized by taxi you can do to take advantage of the autonomous car, it is necessary to frame the message, why can most effectively be used to find how to deliver. In addition, the research methodology should be improved and future research should be done as follows. First, most students responded in this study. It is also true that it is difficult to generalize the hypotheses to be tested in this study. Therefore, in future studies, it would be reasonable to investigate the population of various distribution considering the age, area, occupation, education level, etc. Where autonomous taxi can be used rather than those who can drive. Second, it is desirable to construct various message framing of the questionnaire, but it is necessary to learn various message framing in advance and to prevent errors in response to the next message framing. Therefore, it is desirable to measure the message framing with a certain amount of time when the questionnaire is designed.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.2 no.1 s.2
• /
• pp.25-40
• /
• 2003

The purpose of this thesis is development of detection algorithm for stop-line detector. Detail detection area is set in basing detection area($1.8{\times}4.0m$) and traffic information(volume, occupancy, nonoccupancy) is collected by passive infrared detector at designing detection area. The basis detection area($1.8{\times}4.0m$) is named existing PIR and detection area applied on development algorithm is named proposal PIR. The proposal PIR is collected data such volume, occupancy, nonoccupancy, speed and lane change, but this thesis is limited to evaluate for volume, occupancy and nonoccupancy The procedure and each step of being developed algorithm is described in the next (1) The detection area of proposal PIR is made up of 2 of $1.8{\times}0.6m$ size(the detection area is named 1 and 3) and 1 of $1.8{\times}1.78m$ size(the detection area is named 2) (2) The image detection area is set on monitor to analyze outdoor photographing data then video frame analysis has been done by analyzer. (3) The occupancy, nonoccupancy and speed data of vehicle have been collected with the detection area 1 and 3 and lane change has been collected with combination of detection area 1, 2 and 3 The MAD and MAPE have been utilized to being compared with volume, occupancy and nonoccupancy for the field application and evaluation of a algorithm As the result, the proposal PIR data have been identified superior to the existing PIR data and the effect has been improved its information(volume, occupancy and nonoccupancy)

• Asia pacific journal of information systems
• /
• v.18 no.4
• /
• pp.57-81
• /
• 2008

Knowledge is an essential strategic weapon for sustaining competitive advantage and is the key determinant for organizational growth. When knowledge is shared and disseminated throughout the organization, it increases an organization's value by providing the ability to respond to new and unusual situations. The growing importance of knowledge as a critical resource has forced executives to pay attention to their organizational knowledge. Organizations are increasingly undertaking knowledge management initiatives and making significant investments. Knowledge sourcing is considered as the first important step in effective knowledge management. Most firms continue to make an effort to realize the benefits of knowledge management by using various knowledge sources effectively. Appropriate knowledge sourcing strategies enable organizations to create, acquire, and access knowledge in a timely manner by reducing search and transfer costs, which result in better firm performance. In response, the knowledge management literature has devoted substantial attention to the analysis of knowledge sourcing strategies. Many studies have categorized knowledge sourcing strategies into intemal- and external-oriented. Internal-oriented sourcing strategy attempts to increase firm performance by integrating knowledge within the boundary of the firm. On the contrary, external-oriented strategy attempts to bring knowledge in from outside sources via either acquisition or imitation, and then to transfer that knowledge across to the organization. However, the extant literature on knowledge sourcing strategies focuses primarily on large organizations. Although many studies have clearly highlighted major differences between large and small firms and the need to adopt different strategies for different firm sizes, scant attention has been given to analyzing how knowledge sourcing strategies affect firm performance in small firms and what are the differences between small and large firms in the patterns of knowledge sourcing strategies adoption. This study attempts to advance the current literature by examining the impact of knowledge sourcing strategies on small firm performance from a holistic perspective. By drawing on knowledge based theory from organization science and complementarity theory from the economics literature, this paper is motivated by the following questions: (1) what are the adoption patterns of different knowledge sourcing strategies in small firms (i,e., what sourcing strategies should be adopted and which sourcing strategies work well together in small firms)?; and (2) what are the performance implications of these adoption patterns? In order to answer the questions, this study developed three hypotheses. First hypothesis based on knowledge based theory is that internal-oriented knowledge sourcing is positively associated with small firm performance. Second hypothesis developed on the basis of knowledge based theory is that external-oriented knowledge sourcing is positively associated with small firm performance. The third one based on complementarity theory is that pursuing both internal- and external-oriented knowledge sourcing simultaneously is negatively or less positively associated with small firm performance. As a sampling frame, 700 firms were identified from the Annual Corporation Report in Korea. Survey questionnaires were mailed to owners or executives who were most erudite about the firm s knowledge sourcing strategies and performance. A total of 188 companies replied, yielding a response rate of 26.8%. Due to incomplete data, 12 responses were eliminated, leaving 176 responses for the final analysis. Since all independent variables were measured using continuous variables, supermodularity function was used to test the hypotheses based on the cross partial derivative of payoff function. The results indicated no significant impact of internal-oriented sourcing strategies while positive impact of external-oriented sourcing strategy on small firm performance. This intriguing result could be explained on the basis of various resource and capital constraints of small firms. Small firms typically have restricted financial and human resources. They do not have enough assets to always develop knowledge internally. Another possible explanation is competency traps or core rigidities. Building up a knowledge base based on internal knowledge creates core competences, but at the same time, excessive internal focused knowledge exploration leads to behaviors blind to other knowledge. Interestingly, this study found that Internal- and external-oriented knowledge sourcing strategies had a substitutive relationship, which was inconsistent with previous studies that suggested complementary relationship between them. This result might be explained using organizational identification theory. Internal organizational members may perceive external knowledge as a threat, and tend to ignore knowledge from external sources because they prefer to maintain their own knowledge, legitimacy, and homogeneous attitudes. Therefore, integrating knowledge from internal and external sources might not be effective, resulting in failure of improvements of firm performance. Another possible explanation is small firms resource and capital constraints and lack of management expertise and absorptive capacity. Although the integration of different knowledge sources is critical, high levels of knowledge sourcing in many areas are quite expensive and so are often unrealistic for small enterprises. This study provides several implications for research as well as practice. First this study extends the existing knowledge by examining the substitutability (and complementarity) of knowledge sourcing strategies. Most prior studies have tended to investigate the independent effects of these strategies on performance without considering their combined impacts. Furthermore, this study tests complementarity based on the productivity approach that has been considered as a definitive test method for complementarity. Second, this study sheds new light on knowledge management research by identifying the relationship between knowledge sourcing strategies and small firm performance. Most current literature has insisted complementary relationship between knowledge sourcing strategies on the basis of data from large firms. Contrary to the conventional wisdom, this study identifies substitutive relationship between knowledge sourcing strategies using data from small firms. Third, implications for practice highlight that managers of small firms should focus on knowledge sourcing from external-oriented strategies. Moreover, adoption of both sourcing strategies simultaneousiy impedes small firm performance.

• Journal of KIISE:Computing Practices and Letters
• /
• v.8 no.4
• /
• pp.479-488
• /
• 2002

In recent years the amount of digital video used has risen dramatically to keep pace with the increasing use of the Internet and consequently an automated method is needed for indexing digital video databases. Textual information, both superimposed and embedded scene texts, appearing in a digital video can be a crucial clue for helping the video indexing. In this paper, a new method is presented to extract both superimposed and embedded scene texts in a freeze-frame of news video. The algorithm is summarized in the following three steps. For the first step, a color image is converted into a gray-level image and applies contrast stretching to enhance the contrast of the input image. Then, a modified local adaptive thresholding is applied to the contrast-stretched image. The second step is divided into three processes: eliminating text-like components by applying erosion, dilation, and (OpenClose+CloseOpen)/2 morphological operations, maintaining text components using (OpenClose+CloseOpen)/2 operation with a new Geo-correction method, and subtracting two result images for eliminating false-positive components further. In the third filtering step, the characteristics of each component such as the ratio of the number of pixels in each candidate component to the number of its boundary pixels and the ratio of the minor to the major axis of each bounding box are used. Acceptable results have been obtained using the proposed method on 300 news images with a recognition rate of 93.6%. Also, my method indicates a good performance on all the various kinds of images by adjusting the size of the structuring element.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.8
• /
• pp.145-159
• /
• 2021

is a contemporary experimental film that forms ambiguity in the narrative and the psychological motivation of the characters, destroys linear temporality, and reminds of manipulation possibilities in digital images through varied techniques, and it carries implication by the fact that the transformation process of human subjects and self-awareness are connected to social trauma and makes way to infer by comparing it to the historical contexts of other nations or societies. centers on the space outside the screen, absent space, and the intrinsic meaning within the space and the frame and shares the information in the visible space and the space outside the screen and arouses an active perceptual process so that the audience can deduce the information that is not presented. The film visualized the historical meaning without describing the background of the times in detail and aimed to express the conflicts and worries between the god, a transcendental existence, with humans, which are marginal beings, within the conflicting structure among humans. Moreover, attempted to resolve the sadness of loss and absence through the spatial aesthetics and the film presented the progression of the situation through the contrast of the characters and also the comparison between light and darkness. This study intends to make an attempt of interpreting the realm involving personal (characters) stories and the social and historical backgrounds together with the religious sphere and discuss the visualization of the semantic context. In addition, this study analyzed the sequence of the scenes in , which reconstructs identity and historical cases and religious values to observe the meaning and characteristics and closely analyze the general meaning pursued by the film. discussed the issues of trauma that individuals, regions, and nations confront as a representation and interpretation of the trauma connoted in the film, and consideration can be provided about the implication concerning the situation and context in South Korea. Furthermore, the film placidly discusses the growth and agony in humans and the society without expressing it excessively, so it will be a valuable research result to inspire the trend of creating films that incorporate new imaging technology and original visualization techniques.