• Journal of Information Processing Systems
• /
• v.19 no.5
• /
• pp.663-672
• /
• 2023

Most vehicle detection methods have poor vehicle feature extraction performance at night, and their robustness is reduced; hence, this study proposes a night vehicle detection method based on style transfer image enhancement. First, a style transfer model is constructed using cycle generative adversarial networks (cycleGANs). The daytime data in the BDD100K dataset were converted into nighttime data to form a style dataset. The dataset was then divided using its labels. Finally, based on a YOLOv5s network, a nighttime vehicle image is detected for the reliable recognition of vehicle information in a complex environment. The experimental results of the proposed method based on the BDD100K dataset show that the transferred night vehicle images are clear and meet the requirements. The precision, recall, mAP@.5, and mAP@.5:.95 reached 0.696, 0.292, 0.761, and 0.454, respectively.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.18 no.36
• /
• pp.49-59
• /
• 1995

The vehicle navigation system is developed for helping driver to retrieve driving information more easily and fastly. Navigation System informs driver many pieces of driving information - roadway structure and system, on-line traffic condition, the position of vehicle, route guidance, destination and other information service. As the style of information is diverse and the amount of information is large, driver may have mental and visual overload. The display of information can disturb the driver's attention and this can cause accidents. This state is caused by the defect of human-machine interactions. When the navigation system is designed, human factors - cognitive, judgment, operating - must be considered. The display style must be designed simply and easily, not to be obstacle of human -machine interface. In this study, outside-in view display style and inside-out view display style are compared each other. Two factors are measured. One is cognitive factor-time of cognition on information that is displayed by screen display, cognition error rate. The other is image of screen display - subject's feeling about several styles of display, degree of subject's preference. The prototype of roadway is four kinds - Cross, T-cross, Y-cross and O-cross. Roadway display for test is taken from paper maps. Traffic condition display style, vehicle position display style and route guidance display style are taken from current display style. Traffic condition display style is symbol. Vehicle position display style and route guidance display style are described as color and symbol. The test on screen display is implemented doing given tasks. Then the test is analyzed statistically, The result of test analysis gives the guideline to the designer for the map display of the vehicle navigation system.

• Proceedings of the ESK Conference
• /
• 1995.10a
• /
• pp.208-213
• /
• 1995

The vehicle navigation system is developed for helping driver to retrieve driving information more easily and lastly. Navigation System informs driver many pieces of driving information - roadway structure and system, on-line traffic condition, the position of vehicle, route guidance, destination and other infor- mation service. As the style of information is diverse and the amount of information is large, driver may have mental and visual overload. The display of information can disturb the driver's attention and this can cause accidents. This state is caused by the defect of human-machine interactions. When the navigation system is designed, human factors - cognitive, judgment, operating -must be considered. The display style must be designed simply and easily, not to be obstacle of human - machine interface. In this study, outside- in view display style and inside-out view display style are compared each other. Tow factors are measured. One is cognitive factor-time of cognition on information that is displayed by screen display, cognition error rate. The other is image of screen display - subject's feeling about several styles of display, degree of subject's preference. The prototype of roadway is four kinds -Cross, T-cross and O-cross. Roadway display for test is taken from paper maps. Traffic condition display style, vehicle position display style and route guidance display style are taken from current display style. Traffic condition display style is symbol. vehicle position display style and route guidance display style are described as color and symbol. The test on screen display is implemented doing given tasks. Then the test is analyzed statistically. The result of test analysis gives the guideline to the designer for the map display of the vehicle navigation system.

• Proceedings of the Korea Society of Design Studies Conference
• /
• 2001.05a
• /
• pp.142-143
• /
• 2001

• Archives of design research
• /
• v.14 no.4
• /
• pp.35-45
• /
• 2001

The origin of Minivan styled RV dates all the way back to the year 1959 when Volkswagen introduced the Microbus in Germany. But the new category of "Minivan" was made, and first used by Chrysler. This was when Chrysler revealed a new vehicle in 1982 named "Minivan". Minivan was successful in gathering the public attention with it′s multi-purpose characteristic. Ever since, many models were introduced in this category by various auto-makers around the world, which made the Minivan segment very competitive. Various Minivans were also introduced by the Korean auto-makers and these models have been finding their place rapidly in the market owing to their unique characteristics. But the reason for the growth of the Minivan category in Korea was quite different from that of other nations. Through out this thesis, the possibilities of a Minivan that can full fill the needs of a new life style of a family in the basis of various documentary records will be discussed. Ways of making roads, where bigger sized Minivans are continuously increasing, more efficient will also be considered. The main topic of this thesis will be about Minivan styled RV(Recreational vehicle) in relation to the change of Korean life style.

• Proceedings of the Korea Society of Design Studies Conference
• /
• 2005.05a
• /
• pp.24-25
• /
• 2005

• Proceedings of the KSR Conference
• /
• 2008.06a
• /
• pp.1195-1200
• /
• 2008

The railway bridge design specification used in our country at present, is reflected results that take into account link between vehicle and roadbed according to decision of TGV vehicle style in 1994, and executes design verification. Hereafter, the particular loading condition and the design speed of the high-speed EMU that is recognized to the next generation of high speed railway, are plain difference with TGV vehicle style decided in 1994. The effect that these load and design speed get in roadbed, especially superstructure, displays difference with the existent high speed railway. The goal of this study is to choose the suitable bridge type, and to reduce the construction cost for the next generation of railway, i.e., the high-speed EMU.

• Proceedings of the KSR Conference
• /
• 2004.10a
• /
• pp.228-233
• /
• 2004

A derailment coefficient of railway vehicle is as one of important element that estimate running safety. Derailment coefficient is ratio of lateral load/vertical load happens in contact point between wheel and rail. Lateral load increases, dangerous of derailment can rise. There are ground and vehicle to measurement method of these derailment coefficient. Method of ground is simple, but when vehicles passes data of a point, there is shortcoming that acquire locally. Curved surface style wheel shape that use so far among vehicle method in this research wishes to be not but describe about static load test of wheel-set for derailment coefficient measurement that have plane plate shape that manufacture separate way and correction result etc. to test.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.22 no.3
• /
• pp.157-165
• /
• 2014

To develop a compact vehicle for women, the most important areas are 'behavioral characteristics, life style and driving posture'. Static AM95%ile manikin is used for package guideline. Since women's characteristics and sitting position are different from men, however, the guideline cannot satisfy women drivers. Therefore, the goal of this study is to make the database with dynamic women's driving posture and behavioral characteristics at compact vehicle. Research process will be made as follows. Firstly, through the online/offline survey and statistic analysis, lifestyle and behavioral characteristics (discomfort elements) of women are extracted. Secondly, the author performs scenario test to acquire the discomfort value of driving situation and life style. 3D models of women's manikin and driving posture were created by CATIA HUMAN. The 3D models are used for the purpose of analyzing women's driving posture. Finally, with the ANOVA result and comparison between real driving posture and package guidelines, the author is able to suggest the main issue for women drivers.

• Journal of Internet Computing and Services
• /
• v.6 no.3
• /
• pp.147-158
• /
• 2005

Day after day the information of vehicle under the complex traffic environments is greatly required not only for traffic flow but also for vehicle disclosure of traffic violation, Vehicle information can be obtained from a recognition of vehicle license plate, This paper proposes a new vehicle plate recognition mechanism that uses moving style vehicle-loaded camera, The method is a real-time processing system using multi-step image processing and recognition process that recognizes general vehicles and special purpose vehicles, The experimental results of real environmental image and recognition using the proposed method are shown.