• Journal of the Korea Society of Computer and Information
• /
• v.26 no.1
• /
• pp.45-55
• /
• 2021

This paper has proposed an algorithm that detecting for dense small vehicle in large image efficiently. It is consisted of two Ensemble Deep-Learning Network algorithms based on Coarse to Fine method. The system can detect vehicle exactly on selected sub image. In the Coarse step, it can make Voting Space using the result of various Deep-Learning Network individually. To select sub-region, it makes Voting Map by to combine each Voting Space. In the Fine step, the sub-region selected in the Coarse step is transferred to final Deep-Learning Network. The sub-region can be defined by using dynamic windows. In this paper, pre-defined mapping table has used to define dynamic windows for perspective road image. Identity judgment of vehicle moving on each sub-region is determined by closest center point of bottom of the detected vehicle's box information. And it is tracked by vehicle's box information on the continuous images. The proposed algorithm has evaluated for performance of detection and cost in real time using day and night images captured by CCTV on the road.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.3
• /
• pp.563-570
• /
• 2024

This paper proposes a method to recognize and track drivable lane areas to assist the driver. The main topic is designing a deep-based network that predicts drivable road areas using computer vision and deep learning technology based on images acquired in real time through a camera installed in the center of the windshield inside the vehicle. This study aims to develop a new model trained with data directly obtained from cameras using the YOLO algorithm. It is expected to play a role in assisting the driver's driving by visualizing the exact location of the vehicle on the actual road consistent with the actual image and displaying and tracking the drivable lane area. As a result of the experiment, it was possible to track the drivable road area in most cases, but in bad weather such as heavy rain at night, there were cases where lanes were not accurately recognized, so improvement in model performance is needed to solve this problem.

• Journal of Korea Multimedia Society
• /
• v.13 no.1
• /
• pp.66-75
• /
• 2010

We proposed an occupant sensing system using single video camera and ultrasonic sensor for the advanced airbag. To detect the occupant form and the face position in real-time, we used the skin color and motion information. We made the candidate face block image using the threshold value of the color difference signal corresponding to skin color and difference value of current image and previous image of luminance signal to gel motion information. And then it detects the face by the morphology and the labeling. In case of night without color and luminance information, it detects the face by using the threshold value of the luminance signal get by infra-red LED instead of the color difference signal. To evaluate the performance of the proposed occupant detection system, it performed various experiments through the setting of the IEEE camera, ultrasonic sensor, and infra-red LED in vehicle jig.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.37 no.6
• /
• pp.1017-1023
• /
• 2017

Duration induced by freeway crashes has a critical influence on traffic congestion. In general, crash duration composes detection and verification, response, and clearance time. Of these, the crash clearance time determined by a crash clearance team has attracted considerable attention in the freeway congestion management since the interest of the first two time stages faded away with increasing ubiquitous mobile phone users. The objective of this study is to identify the critical factors that affect freeway crash clearance time using a Cox's proportional hazard model. In total, 6,870 crash duration data collected from 30 major Korean freeways in 2013 were used. As a result, it was found that crashes during the night, with trailer or larger size truck, and in tunnel section contribute to increasing clearance time. Crashes associated with fatality, completed damage of crashed vehicle (s), and vehicles' fire or rollover after crash also lead to increasing clearance time. Additionally, an increase in the number of vehicles involved resulted in longer clearance time. On the other hand, crashes in the vicinity of tollgate, by passenger car, during spring, on flat section, and of car-facility type had longer clearance time. On the basis of the results, this paper suggested some strategic plans and mitigation measures to reduce crash clearance time on Korean freeway systems.