• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.8
• /
• pp.848-855
• /
• 2008

In this paper, we describe correspondence among multiple images taken by multiple cameras. The correspondence among multiple views is an interesting problem which often appears in the application like visual surveillance or gesture recognition system. We use the principal axis and the ground plane homography to estimate foot of human. The principal axis belongs to the subtracted silhouette-based region of human using subtraction of the predetermined multiple background models with current image which includes moving person. For the calculation of the ground plane homography, we use landmarks on the ground plane in 3D space. Thus the ground plane homography means the relation of two common points in different views. In the normal human being, the foot of human has an exactly same position in the 3D space and we represent it to the intersection in this paper. The intersection occurs when the principal axis in an image crosses to the transformed ground plane from other image. However the positions of the intersection are different depend on camera views. Therefore we construct the correspondence that means the relationship between the intersection in current image and the transformed intersection from other image by homography. Those correspondences should confirm within a short distance measuring in the top viewed plane. Thus, we track a person by these corresponding points on the ground plane. Experimental result shows the accuracy of the proposed algorithm has almost 90% of detecting person for tracking based on correspondence of intersections.

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1381-1386
• /
• 2019

As traffic congestion in cities becomes more serious, intelligent traffic control is actively being researched. Reinforcement learning is the most actively used algorithm for traffic signal control, and recently Deep reinforcement learning has attracted attention of researchers. Extended versions of deep reinforcement learning have been emerged as deep reinforcement learning algorithm showed high performance in various fields. However, most of the existing traffic signal control were studied in a single intersection environment, and there is a limitation that the method at a single intersection does not consider the traffic conditions of the entire city. In this paper, we propose a cooperative traffic control at multi-intersection environment. The traffic signal control algorithm is based on a combination of extended versions of deep reinforcement learning and we considers traffic conditions of adjacent intersections. In the experiment, we compare the proposed algorithm with the existing deep reinforcement learning algorithm, and further demonstrate the high performance of our model with and without cooperative method.

• Spatial Information Research
• /
• v.15 no.2
• /
• pp.169-180
• /
• 2007

Applicability of Land-based MMS(Mobile Mapping System) having been increased gradually as digitalization of administrative operation and construction of integrated systems of the government and provincial government are growing up. As these requirements, the case can be occurred that the facilities should be surveyed rapidly in the specific area. At this case, the real time field processing method is more necessary than the post processing method and data processing speed should be an essential element as important as accuracy. In this study, the two space intersection methods used in photogrammetry were programmed and compared with each other to select more proper method for the three dimensional positioning in the field processing. Especially, at the analytic space intersection, the traditional close range terrestrial photogrammetry was modified and applied to that to adapt to MMS's characteristics that camera position and attitude are changed according to the vehicle movement. As a result, the difference of the accuracy between two methods is not significant but at the calculation time, the analytic space intersection is faster three times than the space intersection using collinearity condition.

• Journal of the Ergonomics Society of Korea
• /
• v.29 no.4
• /
• pp.611-617
• /
• 2010

To find out why elderly drivers have more frequent traffic accidents on intersection than any other one, this study was conducted to examine the characteristics of elderly drivers' driving behavior on intersection using a multifaceted driving behavior indicator. To do that, the driving behavior of both young adult drivers and elderly drivers were compared and analyzed, using a graphic driving simulator. As a result, compared with young adult drivers, elderly drivers showed a poor driving performance, and a high ratio of visual scanning time on the specific direction regardless of driving situation. Also, compared with young adult drivers, elderly drivers had a high overall level of arousal, and the phasic arousal activity on the specific stimulus was low. These results imply that through the intervention which induces the change in multifaceted indicators mentioned earlier, they could be helped to drive more safely on intersection.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.35 no.2
• /
• pp.427-436
• /
• 2015

This study analyzes the factors effecting on pedestrian crossing behavior in the unsignalized intersection. Pedestrian crossing behavior is the results of mental stress defined as a combination of environment perception, avoiding accidents, halting collision, and instant crossing decision. It is necessary to make walkable intersection in cities through relieving this stress influenced by personality, traffic condition, and roadway environment. The purpose of study is empirically to examine the crossing behavior such as crossing satisfaction, crossing trial frequency and waiting time based on various factors effecting on crossing intersection by video and questionnaire survey. The $x^2$-test is applied to analyze the characteristics of crossing trial frequency according to each factor. Also, the hazard rate model is established to find the factors effecting on waiting time for crossing. Finally, the direct and indirect effects on the pedestrian crossing satisfaction are presented as the results of LISREL.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.11
• /
• pp.507-520
• /
• 2017

The set-based similar sequence matching method measures similarity not for an individual data item but for a set grouping multiple data items. In the method, the similarity of two sets is represented as the size of intersection between them. However, there is a critical performances issue for the method in twofold: 1) calculating intersection size is a time consuming process, and 2) the number of set pairs that should be calculated the intersection size is quite large. In this paper, we propose an index-based search method for improving performance of set-based similar sequence matching in order to solve these performance issues. Our method consists of two parts. In the first part, we convert the set similarity problem into the intersection size comparison problem, and then, provide an index structure that accelerates the intersection size calculation. Second, we propose an efficient set-based similar sequence matching method which exploits the proposed index structure. Through experiments, we show that the proposed method reduces the execution time by 30 to 50 times then the existing methods. We also show that the proposed method has scalability since the performance gap becomes larger as the number of data sequences increases.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.32 no.4
• /
• pp.107-112
• /
• 2009

The purpose of this study was to examine elderly drivers' driving performances at the intersections, suggested by Bao and Boyle(2009), according to visual information processing skills. Visual information processing skills of elderly drivers were measured by using the visual working memory task, developed by Min et al.(2006). Seven elderly drivers were divided into two groups(good/poor) depending on the level of visual information processing skills and eleven younger drivers were a contrast group. This study examined the differences of driving performance(i.e., intersection passing times, approach velocities, speed variation and handling variations) among three groups. The results showed that elderly drivers having the poor visual information processing skills passed more slowly through the intersection than the contrast group, and passing times between elderly drivers having the good visual information processing skills and the contrast group was not significantly different. It is suggested that elderly drivers having the poor visual information processing skills use more times when they pass through the intersection, because they don't process a lot of hazardous and latent hazardous factors quickly.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.9
• /
• pp.4472-4477
• /
• 2013

This paper describes the color features of smoke in each standard color model in order to present the most suitable color model for somke detection in video surveillance system. Histogram intersection technique is used to analyze the difference characteristics between color of smoke and color of non smoke. The considered standard color models are RGB, YCbCr, CIE-Lab, HSV, and if the calculated histogram intersection value is large for the considered color model, then the smoke spilt characteristics are not good in that color model. If the calculated histogram intersection value is small, then the smoke spilt characteristics are good in that color model. The analyzed result shows that the RGB and HSV color models are the most suitable for color model based smoke detection by performing respectively 0.14 and 0.156 for histogram intersection value.

• Journal of Korean Society of Transportation
• /
• v.26 no.4
• /
• pp.41-49
• /
• 2008

Signalized intersection analysis using lane groups often generalizes distinct characteristics of individual lanes. An individual lane level analysis procedure is proposed. The method can assess individual lane LOS without additional data collection efforts. Analysis results of the proposed method were compared with the current HCM analysis results and outputs of aaSIDRA, which can calculate intersection performance lane-by-lane. The results showed individual lane analysis mostly produces similar results with HCM and aaSIDRA. However, lane analysis results for permitted left lanes showed some differences with aaSIRDRA due to the different method of assessing saturation flow rate of the permitted left turn movement. It is expected that the proposed method could complement the weaknesses of current HCM signalized intersection analysis.

• Journal of the Korean Institute of Gas
• /
• v.2 no.1
• /
• pp.74-82
• /
• 1998

The grain boundary etching method as a technique for assessing degradation of structural materials used at elevated temperature has received much attention since it is simple, inexpensive and easy to apply to real plant components. In this study, the technique is applied to some aged petroleum and chemical plant components such as reactors and drums. As a degradation parameter, intersection number ratio ($N_i/N_o$), is employed. The intersection number ratio ($N_i/N_o$) is defined as the ratio of intersection number ($N_i$) obtained from 5-minute picric acid etched surface to the number ($N_o$) obtained from Nital etched surface. In order to study degradation level, several relationships were measured such as the correlation between shift in ductile brittle transition temperature, $({\Delta}DBTT)_{sp}$ and intersection number ratio, ($N_i/N_o$) and the correlation between the measured ($N_i/N_o$) values and Larson-Miller Parameter values.