• Journal of Korean Society of Transportation
• /
• v.29 no.1
• /
• pp.47-55
• /
• 2011

The purpose of this study was to determine the legibility distance for traffic road sign and traffic sign, fixation duration and number of fixation during the time of recognition of traffic road signs under different vision conditions. This experiment was conducted on a closed-road circuit which has realistic driving road and environment Each participant drove the real vehicle for the experiment and specially built traffic road sign for the experiment and traffic road signs on the side of closed-road circuit were used. Different vision conditions were simulated using spectacle lenses to reach visual acuity 1.0 and 0.8 and it was 1.2 without spectacles and each participant tested under 3 vision conditions.. The result of this study demonstrated that there was a significant difference on legibility distance between visual acuity of 1.2 and 0.8 and there were also significant difference on fixation duration and number of fixations with smaller traffic signs. This study demonstrated the importance of vision correction for driving at night-time, also showed there would be difference on legibility distance and efficiency of eye movement such as fixation duration and number of fixation despite of satisfied visual acuity for driver's license requirement.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.3
• /
• pp.147-157
• /
• 2022

Recently, many studies have been conducted to analyze traffic or object recognition that classifies vehicles through artificial intelligence-based prediction models using CCTV (Closed Circuit TeleVision)or drone images. In order to develop an object recognition deep learning model for accurate traffic estimation, systematic data construction is required, and related standardized guidelines are insufficient. In this study, previous studies were analyzed to derive guidelines for establishing artificial intelligence-based training data for traffic estimation using drone images, and business reports or training data for artificial intelligence and quality management guidelines were referenced. The guidelines for data construction are divided into data acquisition, preprocessing, and validation, and guidelines for notice and evaluation index for each item are presented. The guidelines for data construction aims to provide assistance in the development of a robust and generalized artificial intelligence model in analyzing the estimation of road traffic based on drone image artificial intelligence.

• Journal of Korean Society of Transportation
• /
• v.33 no.3
• /
• pp.284-293
• /
• 2015

The objective of this paper is to determine the conditions of road surface by utilizing the images collected from closed-circuit television (CCTV) cameras installed on roadside. First, a technique was examined to detect wet surfaces at nighttime. From the literature reviews, it was revealed that image processing using polarization is one of the preferred options. However, it is hard to use the polarization characteristics of road surface images at nighttime because of irregular or no light situations. In this study, we proposes a new discriminant for detecting wet and dry road surfaces using CCTV image data at night. To detect the road surface conditions with night vision, we applied the wavelet packet transform for analyzing road surface textures. Additionally, to apply the luminance feature of night CCTV images, we set the intensity histogram based on HSI(Hue Saturation Intensity) color model. With a set of 200 images taken from the field, we constructed a detection criteria hyperplane with SVM (Support Vector Machine). We conducted field tests to verify the detection ability of the wet road surfaces and obtained reliable results. The outcome of this study is also expected to be used for monitoring road surfaces to improve safety.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.3
• /
• pp.269-279
• /
• 2020

Traffic estimation mainly involves surveying equipment such as automatic vehicle classification, vehicle detection system, toll collection system, and personnel surveys through CCTV (Closed Circuit TeleVision), but this requires a lot of manpower and cost. In this study, we proposed a method of estimating traffic volume using deep learning and stereo CCTV to overcome the limitation of not detecting the entire vehicle in case of single CCTV. COCO (Common Objects in Context) dataset was used to train deep learning models to detect vehicles, and each vehicle was detected in left and right CCTV images in real time. Then, the vehicle that could not be detected from each image was additionally detected by using affine transformation to improve the accuracy of traffic volume. Experiments were conducted separately for the normal road environment and the case of weather conditions with fog. In the normal road environment, vehicle detection improved by 6.75% and 5.92% in left and right images, respectively, than in a single CCTV image. In addition, in the foggy road environment, vehicle detection was improved by 10.79% and 12.88% in the left and right images, respectively.

• Ecology and Resilient Infrastructure
• /
• v.3 no.3
• /
• pp.169-176
• /
• 2016

Roads are widely accepted to be as a major cause of habitat fragmentation. The wildlife road-crossing structure is one of the most acceptable alternatives among the solutions to provide connectivity between patches isolated by roads. We investigated noise disturbance, vegetation structure and wildlife crossing and habitation at a wildlife road-crossing structure located at the Jingmaei-Pass in Incheon, Korea, to monitor and evaluate its conservation value and ecological performance and to propose measures for their adaptive management. From the result of noise measurement, the noise disturbance from the road traffic was not properly blocked out at the wildlife crossing structure. The survey results of vegetation structure showed that the early-successional plant species such as Ambrosia trifida, Erigeron annuus, Pueraria lobata, Rosa multiflora invaded widely on the crossing structure. An efficient management of the vegetation should be necessarily considered for the facilitation of vegetation succession and the improvement of animal habitat. The crossing structure was used by limited mammal species: Apodemus agrarius, Nyctereutes procyonoides, Mogera wogura and Sciurus vulgaris coreae as the results of the monitoring using footprints and closed-circuit television. In conclusion, The Jingmaei-Pass wildlife crossing structure is unable to function properly as a biological corridor because of the interference of noise and flourishing disturbed vegetation. Therefore, proper alternatives are required for improving animal habitats and mobile environments to enhance the ecological function of a wildlife corridor.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.2
• /
• pp.48-61
• /
• 2020

The objective of this study is to estimate traffic capacity based on the heavy-vehicle ratio in a two-lane freeway work zone where one lane is blocked by construction. For this, closed circuit television (CCTV) video data of the freeway work zone was collected, and the congestion at an upstream point was observed. The traffic volume at a downstream point was analyzed after a bottleneck was created by the blockage due to the upstream congestion. A distribution model was estimated using observed-time headway, and the road capacity was analyzed using a goodness-of-fit test. Through this process, the general capacity and an equation for capacity based on the heavy-vehicle ratio passing through the work zone were presented. Capacity was estimated to be 1,181~1,422 passenger cars per hour per lane (pcphpl) at Yeongdong, and 1,475~1,589pcphpl at Jungbu Naeryuk. As the ratio of heavy vehicles increased, capacity gradually decreased. These findings can contribute to the proper capacity estimation and efficient traffic operation and management for two-lane freeway work zones that block one lane due to a work zone.

• International Journal of Highway Engineering
• /
• v.10 no.2
• /
• pp.159-166
• /
• 2008

Video image processing systems (VIPS) offer numerous benefits to transportation models and applications, due to their ability to monitor traffic in real time. VIPS based on a wide-area detection algorithm provide traffic parameters such as flow and velocity as well as occupancy and density. However, most current commercial VIPS utilize a tripwire detection algorithm that examines image intensity changes in the detection regions to indicate vehicle presence and passage, i.e., they do not identify individual vehicles as unique targets. If VIPS are developed to track individual vehicles and thus trace vehicle trajectories, many existing transportation models will benefit from more detailed information of individual vehicles. Furthermore, additional information obtained from the vehicle trajectories will improve incident detection by identifying lane change maneuvers and acceleration/deceleration patterns. However, unlike human vision, VIPS cameras have difficulty in recognizing vehicle movements over a detection zone longer than 100 meters. Over such a distance, the camera operators need to zoom in to recognize objects. As a result, vehicle tracking with a single camera is limited to detection zones under 100m. This paper develops a methodology capable of monitoring individual vehicle trajectories based on image processing. To improve traffic flow surveillance, a long distance tracking algorithm for use over 200m is developed with multi-closed circuit television (CCTV) cameras. The algorithm is capable of recognizing individual vehicle maneuvers and increasing the effectiveness of incident detection.