• The Journal of Korean Institute of Information Technology
• /
• v.16 no.12
• /
• pp.75-83
• /
• 2018

Recently, autonomous vehicles have been actively studied. Pedestrian detection and recognition technology is important in autonomous vehicles. Pedestrian detection using CNN(Convolutional Neural Netwrok), which is mainly used recently, generally shows good performance, but there is a performance degradation depending on the environment of the image. In this paper, we propose a pedestrian detection system applying long-term memory structure of hippocampal neural network based on CNN network with LGP-FL (Local Gradient Pattern-Feature Layer) added. First, change the input image to a size of $227{\times}227$. Then, the feature is extracted through a total of 5 layers of convolution layer. In the process, LGP-FL adds the LGP feature pattern and stores the high-frequency pattern in the long-term memory. In the detection process, it is possible to detect the pedestrian more accurately by detecting using the LGP feature pattern information robust to brightness and color change. A comparison of the existing methods and the proposed method confirmed the increase of detection rate of about 1~4%.

• Journal of Korean Society of Transportation
• /
• v.26 no.1
• /
• pp.137-144
• /
• 2008

It is important to know pedestrian volume to carry out pedestrian safety analysis and pedestrian friendly design. However, it is too difficult to come across research work related to pedestrian volume analysis in the field of transport, due to lack of interests on pedestrian movement. Most transport research has been focused on vehicles and highways rather than pedestrian. On the other hand, in the field of urban studies, there comes an effective tool to estimate pedestrian volumes using Space Syntax theory. This theory twins out to be effective and economic because it only requires network information, which is easy to acquire from maps and field survey. However, this method is different in the way representing networks from the way that is common in the field of transport. To make up for this point, this paper develops a novel measure for estimating pedestrian volume using Dial's algorithm, and applies the model in the two test networks; Insadong and Soongryemoon networks. The application results reveals that developed measure is an effective tool to explain pedestrian volume; a correlation coefficient between the measure and pedestrian volume is 0.713 in Insadong and 0.492 in Soongryemoon, and the goodness of fit($R^2$) of regression models are 0.893 in Insadong and 0.671 in Soongryemoon. This estimation method is significantly less complicated to estimate the effect of a pedestrian network change than Space Syntax theory, which requires special softwares not readily available.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.1
• /
• pp.31-41
• /
• 2018

This study aims to analyze region-based pedestrian evacuation behaviors and information offering effect using Social Force Model, which is micro simulation. All pedestrians were assumed to move to shelters through pedestrian roads according to guidance information at emergency situations, and the pedestrians were classified into adults and the handicapped. According to the results of the road network analysis and simulation analysis, the shelters to which pedestrians can move within the shortest time from each zone were selected as optimum shelters. From this study, the analysis showed that the information provision effects are informative even though total evacuation time increases due to the increase of pedestrian conflict. This study can be used as baseline data for urban area's pedestrian disaster prevention plans.

• IEIE Transactions on Smart Processing and Computing
• /
• v.5 no.4
• /
• pp.256-266
• /
• 2016

Concurrently detected and annotated abnormal events can have a significant impact on surveillance systems. By considering the specific domain of pedestrian trajectories, this paper presents two main contributions. First, as introduced in much of the work on trajectory-based anomaly detection in the literature, only information about pedestrian paths, such as direction and speed, is considered. Differing from previous work, this paper proposes a framework that deals with additional types of trajectory-based anomalies. These abnormal events take places when a person enters prohibited areas. Those restricted regions are constructed by an online learning algorithm that uses surrounding information, including detected pedestrians and background scenes. Second, a simple data-boosting technique is introduced to overcome a lack of training data; such a problem particularly challenges all previous work, owing to the significantly low frequency of abnormal events. This technique only requires normal trajectories and fundamental information about scenes to increase the amount of training data for both normal and abnormal trajectories. With the increased amount of training data, the conventional abnormal trajectory classifier is able to achieve better prediction accuracy without falling into the over-fitting problem caused by complex learning models. Finally, the proposed framework (which annotates tracks that enter prohibited areas) and a conventional abnormal trajectory detector (using the data-boosting technique) are integrated to form a united detector. Such a detector deals with different types of anomalous trajectories in a hierarchical order. The experimental results show that all proposed detectors can effectively detect anomalous trajectories in the test phase.

• Journal of Broadcast Engineering
• /
• v.21 no.4
• /
• pp.493-505
• /
• 2016

Among modern computer vision and video surveillance systems, the pedestrian counting system is a one of important systems in terms of security, scheduling and advertising. In the field of, pedestrian counting remains a variety of challenges such as changes in illumination, partial occlusion, overlap and people detection. During pedestrian counting process, the biggest problem is occlusion effect in crowded environment. Occlusion and overlap must be resolved for accurate people counting. In this paper, we propose a novel pedestrian counting system which improves existing pedestrian tracking method. Unlike existing pedestrian tracking method, proposed method shows that average filter tracking method can improve tracking performance. Also proposed method improves tracking performance through frame compensation and outlier removal. At the same time, we keep various information of tracking objects. The proposed method improves counting accuracy and reduces error rate about S6 dataset and S7 dataset. Also our system provides real time detection at the rate of 80 fps.

• Proceedings of the Korean Institute of Interior Design Conference
• /
• 2001.05a
• /
• pp.157-162
• /
• 2001

This Research analyzed with itinerary tracking : two of each other shopping sites were selected as research point. Analyzing the result, pedestrian path choice is affected by direction of escalator, visual information of the object, plain form of passage, presence and absence of companion and proportion of spatial knowledge from experience. The factors affecting pedestrian path choice are divided into two groups which are the effects from the environment, and personal characteristics.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.11
• /
• pp.181-186
• /
• 2014

The paper proposes a new method of segmentation-based feature extraction to improve performance in pedestrian upper-body detection. General pedestrian detectors that use local features are often plagued by false positives due to the locality. Color information of multi parts of the upper body is utilized in figure-ground segmentation scheme to extract an salient, "global" shape feature capable of reducing the false positives. The performance of the multi-part color segmentation-based feature is evaluated by changing color spaces and the parameters of color histogram. The experimental result from an upper-body dataset shows that the proposed feature is effective in reducing the false positives of local feature-based detectors.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.863-870
• /
• 2022

Unsatisfactory urban walking environment stresses urban residents, and may cause mental illness and chronic diseases by reducing walking activities. Therefore, establishing a high-quality walking environment that can promote walking activities in urban residents has emerged as an important issue. The walking environment consists of various components, such as trees, stairs, streetlights, benches, signs, fences, and facilities, and it is essential to understand which components and their settings act as satisfiers or dissatisfiers for pedestrians, to create a better quality walking environment. Therefore, this study investigated pedestrian satisfaction and dissatisfaction as a function of various environmental components through a survey using walking environment images. The results revealed that most of the walking environment components except the braille block and treezone exhibited significant correlations with pedestrian satisfaction. Particularly, safety-related component (e.g., adjacent roads, parked cars, traffic cushions, and car separation), and landscape-related components (e.g., trees and green), as well as the material settings of landscape facilities (e.g., wooden fences, benches, stairs, and walkway surfaces) correlated with pedestrian satisfaction. The results of this study can contribute to the extraction of useful features to evaluate pedestrian satisfaction as a function of the walking environment. The research outcome is expected to assist in the effective arrangement of walking environment components and their settings, which will ultimately contribute to significantly satisfactory walking environment and encourage walking activities.

• Journal of Korean Society of Transportation
• /
• v.32 no.6
• /
• pp.638-650
• /
• 2014

The objective of this study is to identify the causes of pedestrian volume path to the destination by investigating the influential levels of regional and planning features in the central area of Seoul. Regional characteristics can be classified from the result of the analysis and through the spatial characteristics of pedestrian volume. For global scale analysis, Ordinary Least Squares (OLS) regression is used for the degree of influence of each characteristics to pedestrian volume. For the local scale, Geographically Weighted Regression (GWR) is used to identify regional influential factors with consideration for spatial differences. The results of OLS indicate that boroughs with transportation facilities, commercial business districts, universities, and planning features with education research facilities and planning facilities have a positive effect on pedestrian volume path to the destination. Correspondingly, transportation hubs and congested areas, commercial and business centers, and university towns and research facilities in the Seoul central area can be identified through the results of GWR. The results of this study can provide information with relevance to existing plans and policies about the importance of regional characteristics and spatial heterogeneity effects on pedestrian volume, as well as significance in the establishment of regional development plans.

• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.34 no.11
• /
• pp.85-94
• /
• 2018

This study aims to investigate how easy pedestrians get around within/through the "Apartment Complexes (AC), " a common style of high-rise multi-family housing in Korea. Over the past six decades, the AC has been the most conventional way to provide standardized housing efficiently to address the problems of the shortage of housing and the substandard housing, due to the explosion of urban population with the rapid industrialization. The AC is a huge chunk of homeogenous multi-family housing, mostly condos with decent infrastructure, including parks, pedestrian passages, schools, ect. Both in the new town development and urban renewal programs have utilized the advantages of the AC. Since the design principals of AC tend to adopt the "protective design" to prevent cars and pedestrians coming outside from passing it, it has been criticised for dissecting the continuity of socioeconomic context in neighborhoods. The neo-traditional planning urbanists, including Jane Jacobs, emphasize that smaller blocks and grid road newtworks are the key in improving social, cultural, and economic vitality of the neighborhoods, because these design concepts allow more pedestrians and different types of people to be mixed in a neighborhood. In this study, we first adopted objective measures for pedestrian accessibility and pedestrian efficiency. These measures were used to calculate the lengths of shortest paths from residential buildings to the edges of AC. We tested the difference in shortest paths between the current pedestrian networks of AC and hypothetical grid networks on the AC, and the relative difference is considered as the pedestrian efficiency, using the network analysis function of Geographic Information Systems (GIS) and Python programming. We found from the randomly selected 30 ACs that the existing non-grid road networks in ACs are worse than the hypothesized grid networks, in terms of pedestrian efficiency. In average, pedestrians in AC with the conventional road networks have to walk than 25%, 26%, and 27% longer than the networks of $125{\times}45m$, $100{\times}45m$, and $75{\times}45m$, respectively. With the t-test analysis, we found the pedestrian efficiency of AC with the conventional network is lower than grid-networks. Many new urbanists stress, easiness of walking is one of the most import elements for community building and social bonds. With the findings from the objective measures of pedestrian accessibility and efficiency, the AC would have limitations to attract people outside into the AC itself, which would increase dis-connectivity with adjacent areas.