• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.3
• /
• pp.389-395
• /
• 2022

Because of improvement of deep learning techniques, deep learning using computer vision such as classification, detection and segmentation has also been used widely at many fields. Expecially, automatic driving is one of the major fields that applies computer vision systems. Also there are a lot of works and researches to combine multiple tasks in a single network. In this study, we propose the network that predicts the individual depth of pedestrians and vehicles. Proposed model is constructed based on YOLOv3 for object detection and Monodepth for depth estimation, and it process object detection and depth estimation consequently using encoder and decoder based on hard parameter sharing. We also used attention module to improve the accuracy of both object detection and depth estimation. Depth is predicted with monocular image, and is trained using self-supervised training method.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.31 no.6_1
• /
• pp.483-491
• /
• 2013

By a development of car navigation systems and mobile or positioning technology, it increases interest in location based services, especially pedestrian navigation systems. Updating of digital maps is important because digital maps are mass data and required to short updating cycle. In this paper, we proposed change detection for different network data-sets based on areal feature matching. Prior to change detection, we defined type of updating between different network data-sets. Next, we transformed road lines into areal features(block) that are surrounded by them and calculated a shape similarity between blocks in different data-sets. Blocks that a shape similarity is more than 0.6 are selected candidate block pairs. Secondly, we detected changed-block pairs by bipartite graph clustering or properties of a concave polygon according to types of updating, and calculated Fr$\acute{e}$chet distance between segments within the block or forming it. At this time, road segments of KAIS map that Fr$\acute{e}$chet distance is more than 50 are extracted as updating road features. As a result of accuracy evaluation, a value of detection rate appears high at 0.965. We could thus identify that a proposed method is able to apply to change detection between different network data-sets.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.6
• /
• pp.87-96
• /
• 2022

The traffic vulnerable, including elderly pedestrians, have a relatively low walking speed and slow cognitive response time due to reduced physical ability. Although a smart crossing system has been developed and operated to improve problem, it is difficult to operate a signal that reflects the appropriate walking speed for each pedestrian. In this study, a neural network model and a multiple regression model-based traversing speed estimation model were developed using image information collected in an area with a high percentage of traffic vulnerability. to support the provision of optimal walking signals according to real-time traffic weakness. actual traffic data collected from the urban traffic network of Paju-si, Gyeonggi-do were used. The performance of the model was evaluated through seven selected indicators, including correlation coefficient and mean absolute error. The multiple linear regression model had a correlation coefficient of 0.652 and 0.182; the neural network model had a correlation coefficient of 0.823 and 0.105. The neural network model showed higher predictive power.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.14 no.2
• /
• pp.128-133
• /
• 2021

Currently, autonomous vehicle markets are commercializing a third-level autonomous vehicle, but there is a possibility that an accident may occur even during fully autonomous driving due to stability issues. In fact, autonomous vehicles have recorded 81 accidents. This is because, unlike level 3, autonomous vehicles after level 4 have to judge and respond to emergency situations by themselves. Therefore, this paper proposes a vehicle crisis detection system(VCDS) that collects and stores information outside the vehicle through CNN, and uses the stored information and vehicle sensor data to output the crisis situation of the vehicle as a number between 0 and 1. The VCDS consists of two modules. The vehicle external situation collection module collects surrounding vehicle and pedestrian data using a CNN-based neural network model. The vehicle crisis situation determination module detects a crisis situation in the vehicle by using the output of the vehicle external situation collection module and the vehicle internal sensor data. As a result of the experiment, the average operation time of VESCM was 55ms, R-CNN was 74ms, and CNN was 101ms. In particular, R-CNN shows similar computation time to VESCM when the number of pedestrians is small, but it takes more computation time than VESCM as the number of pedestrians increases. On average, VESCM had 25.68% faster computation time than R-CNN and 45.54% faster than CNN, and the accuracy of all three models did not decrease below 80% and showed high accuracy.

• Journal of Korean Society for Geospatial Information Science
• /
• v.20 no.4
• /
• pp.37-44
• /
• 2012

There are approximately 25,724 shelters to which people can be quickly evacuated for safety in case of emergency across the nation, and Seoul has about 3,870 shelters. Those nationwide shelters are located at a point within a five-minute radius for quick evacuation. Seoul's shelter capacity can hold 285% of its population. The problem is, however, that there is no knowing how many shelters are reachable within five minutes when considering walking speed according to individual differences in age, height, health state, and physical condition. In addition, available service areas become different according to the spatial allocation and distribution of shelters with possible vulnerable points. This study thus defined the pedestrian walking speed at 1m/s, 1.3m/s, and 2m/s by reviewing previous studies and conducted network analysis of the Location Allocation Model with the designated shelters and road networks in Seoul. The results identified the shelter service and vulnerable areas in each administrative district of Seoul according to walking speeds. It was analyzed that the vulnerable areas in which the elderly could not reach a shelter were more than twice as big as those of adult men and women with a fast walking speed.

• Journal of Digital Convergence
• /
• v.15 no.2
• /
• pp.173-181
• /
• 2017

In this paper, we have studied tracking as a training stage of considering the position and the scale of a person given its previous position, scale, as well as next and forward image fraction. Unlike other learning methods, CNN is thereby learning combines both time and spatial features from the image for the two consecutive frames. We introduce multiple path ways in CNN to better fuse local and global information. A creative shift-variant CNN architecture is designed so as to alleviate the drift problem when the distracting objects are similar to the target in cluttered environment. Furthermore, we employ CNNs to estimate the scale through the accurate localization of some key points. These techniques are object-independent so that the proposed method can be applied to track other types of object. The capability of the tracker of handling complex situations is demonstrated in many testing sequences. The accuracy of the SVM classifier using the features learnt by the CNN is equivalent to the accuracy of the CNN. This fact confirms the importance of automatically optimized features. However, the computation time for the classification of a person using the convolutional neural network classifier is less than approximately 1/40 of the SVM computation time, regardless of the type of the used features.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.23 no.2
• /
• pp.1-14
• /
• 2024

The most optimal route-search algorithm thus far has introduced a method of applying node labels and link labels. Node labels consider two nodes simultaneously in the optimal route-search process, while link labels consider two links simultaneously. This study proposes a turn-label-based optimal route-search technique that considers two turns simultaneously in the process. Turn-label-based optimal route search guarantees the optimal solution of dynamic programming based on Bellman's principle as it considers a two-turn search process. Turn-label-based optimal route search can accommodate the advantages of applying link labels because the concept of approaching the limit of link labels is applied equally. Therefore, it is possible to reflect rational cyclic traffic where nodes allow multiple visits without expanding the network, while links do not allow visits. In particular, it reflects the additional cost structure that appears in two consecutive turns, making it possible to express the structure of the travel-cost function more flexibly. A case study was conducted on the metropolitan urban railway network consisting of transportation card terminal readers, aiming to examine the scalability of the research by introducing parameters that reflect psychological resistance in travel with continuous pedestrian transfers into turn label optimal path search. Simulation results showed that it is possible to avoid conservative transfers even if the travel time and distance increase as the psychological resistance value for continuous turns increases, confirming the need to reflect the cost structure of turn labels. Nevertheless, further research is needed to secure diversity in the travel-cost functions of road and public-transportation networks.

• Journal of Korean Society of Transportation
• /
• v.26 no.3
• /
• pp.129-141
• /
• 2008

Portable navigation markets grew up to 95% last year. This study aims to develop a business model for pedestrian-oriented portable navigator for street shoppers. Related previous studies developed successfully the alogrithm for a portable navigator, and the current study seeks for diverse ways to turn this system into a new type of on & off line-based LBS business. The business model proposed in this study adopted two different approaches of benefit yields based on the structural analysis of so-called Wanavi navigation system. One is segmented approach seeking for benefits from each individual system component such as communication network, contents, and platform. The other approach is to run the business by integrating relevant system componts in every possible way to attract customers to this portable navigator. The purpose of this proposal is not limited to activate emerging walking navigator markets, but to aim at creating idealistic free market system where all the shoppers are furnished complete market information to the fullest extent when they go on shopping.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.3
• /
• pp.98-110
• /
• 2018

In this paper, we propose both Dense grid model and Anchor model to improve the recognition rate of dynamic objects. Two experiments are conducted to study the performance of two proposed CNNs models (Dense grid model and Anchor model), which are to detect dynamic objects. In the first experiment, YOLO-v2 network is adjusted, and then fine-tuned on KITTI datasets. The Dense grid model and Anchor model are then compared with YOLO-v2. Regarding to the evaluation, the two models outperform YOLO-v2 from 6.26% to 10.99% on car detection at different difficulty levels. In the second experiment, this paper conducted further training of the models on a new dataset. The two models outperform YOLO-v2 up to 22.40% on car detection at different difficulty levels.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.6
• /
• pp.203-209
• /
• 2016

Digital tourism is the digital support of the tourist experience before, during and after the tourist activity[1]. The GPS-enabled mobile phones provide location-based mobile applications such as tour guide and storytelling services. In this paper, we propose the smart tour guide service platform based on GIS and develop the mobile application to provide the smart tour guide service. The proposed smart tour guide service platform consists of CMS, the multi-modal navigation system, the tour attraction content creation and management system, the tour commodity creation and management system, the smart search system, and the user terminal. The smart tour guide application supports digital tourism in the pre-tour, during tour, and post-tour using the proposed smart tour guide service platform in the popular tourist attractions in Jeju.