• IEMEK Journal of Embedded Systems and Applications
• /
• v.10 no.5
• /
• pp.325-333
• /
• 2015

Vision based night-time vehicle detection has been an emerging research field in various advanced driver assistance systems(ADAS) and automotive vehicle as well as automatic head-lamp control. In this paper, we propose night-time vehicle detection method based on multi-class support vector machine(SVM) that consists of thresholding, labeling, feature extraction, and multi-class SVM. Vehicle light candidate blobs are extracted by local mean based thresholding following by labeling process. Seven geometric and stochastic features are extracted from each candidate through the feature extraction step. Each candidate blob is classified into vehicle light or not by multi-class SVM. Four different multi-class SVM including one-against-all(OAA), one-against-one(OAO), top-down tree structured and bottom-up tree structured SVM classifiers are implemented and evaluated in terms of vehicle detection performances. Through the simulations tested on road video sequences, we prove that top-down tree structured and bottom-up tree structured SVM have relatively better performances than the others.

• Smart Structures and Systems
• /
• v.25 no.3
• /
• pp.265-277
• /
• 2020

Recently, the concept of "drive-by" bridge monitoring system using indirect measurements from a passing vehicle to extract key parameters of a bridge has been rapidly developed. As one of the most key parameters of a bridge, the natural frequency has been successfully extracted theoretically and in practice using indirect measurements. The frequency of bridge is generally calculated applying Fast Fourier Transform (FFT) directly. However, it has been demonstrated that with the increase in vehicle velocity, the estimated frequency resolution of FFT will be very low causing a great extracted error. Moreover, because of the low frequency resolution, it is hard to detect the frequency drop caused by any damages or degradation of the bridge structural integrity. This paper will introduce a new technique of bridge frequency extraction based on Hilbert Transform (HT) that is not restricted to frequency resolution and can, therefore, improve identification accuracy. In this paper, deriving from the vehicle response, the closed-form solution associated with bridge frequency removing the effect of vehicle velocity is discussed in the analytical study. Then a numerical Vehicle-Bridge Interaction (VBI) model with a quarter car model is adopted to demonstrate the proposed approach. Finally, factors that affect the proposed approach are studied, including vehicle velocity, signal noise, and road roughness profile.

• Korean Journal of Remote Sensing
• /
• v.20 no.4
• /
• pp.261-274
• /
• 2004

The feature extraction using remotely sensed imagery has been recognized one of the important tasks in remote sensing applications. As the high-resolution imagery are widely used to the engineering purposes, need of more accurate feature information also is increasing. Especially, in case of the automatic extraction of linear feature such as road using mid or low-resolution imagery, several techniques was developed and applied in the mean time. But quantitatively comparative analysis of techniques and case studies for high-resolution imagery is rare. In this study, we implemented a computer program to perform and compare GDPA (Gradient Direction Profile Analysis) algorithm and Hough transformation. Also the results of applying two techniques to some images were compared with road centerline layers and boundary layers of digital map and presented. For quantitative comparison, the ranking method using commission error and omission error was used. As results, Hough transform had high accuracy over 20% on the average. As for execution speed, GDPA shows main advantage over Hough transform. But the accuracy was not remarkable difference between GDPA and Hough transform, when the noise removal was app]ied to the result of GDPA. In conclusion, it is expected that GDPA have more advantage than Hough transform in the application side.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.4
• /
• pp.11-19
• /
• 2000

Real-time extraction of traffic information such as the number of vehicles passing, speed, road-occupancy rate, distance between vehicles, and vehicle types from the traffic scenes acquired from the camera on the road, is a core component of the intelligent transportation system(lTS) We present a scheme of extracting the traffic informations based on the spatio-temporal image analysis, which is robust to the variation of weather conditions and the shades. The images of two detection regions for each traffic lane are classified into one of the three categories: the road, the vehicle, and the shade, using the statistical and structural features Quantitative traffic informations are retrieved by analysing the two spatio-temporal images. Since only the local images of detection regions are processed, the real-time operation of more than 30 frames per second is realized while ensuring the detection performance robust to the operating condition.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.12
• /
• pp.158-164
• /
• 2015

Lane detection is one of the key parts among autonomous vehicle technologies because lane keeping and path planning are based on lane detection. Camera is used for lane detection but there are severe limitations such as narrow field of view and effect of illumination. On the other hands, Lidar sensor has the merits of having large field of view and being little influenced by illumination because it uses intensity information. Existing researches that use methods such as Hough transform, histogram hardly handle multiple lanes in the co-occuring situation of lanes and road marking. In this paper, we propose a method based on RANSAC and regularization which provides a stable and precise detection result in the co-occuring situation of lanes and road marking in highway scenarios. This is performed by precise lane point extraction using circular model RANSAC and regularization aided least square fitting. Through quantitative evaluation, we verify that the proposed algorithm is capable of multi lane detection with high accuracy in real-time on our own acquired road data.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.27 no.2
• /
• pp.281-288
• /
• 2009

In the paper, we try to develop the methodology for updating road networks of large-scale digital maps by using construction drawing data. For the purpose, it is pre-requite step to merge road networks detached in CAD drawing data. As such, tie points are identified in neighboring drawings and used for solving the parameters of 2D conformal transformation between drawings. Then, the merged road network in CAD data is transformed to the coordinate system of digital maps. In the process, IPs in the drawings are considered as control information and 2D affine transformation is selected for coordinate transformation. Through the experiments with real dataset, we can identify that the developed method is valid and generally applicable.

• Journal of Korean Society for Geospatial Information Science
• /
• v.10 no.1 s.19
• /
• pp.91-100
• /
• 2002

Recently, many studies on the construction of management system for road facility have been accomplished, and in its process the digital map is used as the essential data for spatial database. But in case where the existing topographical map or completion map of construction data is not sufficient for Data Base construction, the compilation, modification or renewal of digital map should be conflicted with large obstacles. This study intended to extract the road facility information using the image data of various form such as aerial photographs, terrestrial photographs and so on. The terrestrial photographic images are taken by hand-held camera, digital camera and video camera which are widely used and of low price in general. This study used the single frame images only for the raw image data, and the extracted spatial and attribute data from the images are used for modifying and updating the database. In addition, the creating possibility of the digital map in the relative scale using the spatial data extracted from the single images was tried.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.12
• /
• pp.1835-1845
• /
• 2021

To accurately identify black ice and warn the drivers of information in advance so they can control speed and take preventive measures. In this paper, we propose a lightweight black ice detection network based on infrared road images. A black ice recognition network model based on CNN transfer learning has been developed. Additionally, to further improve the accuracy of black ice recognition, an enhanced lightweight network based on MobileNetV2 has been developed. To reduce the amount of calculation, linear bottlenecks and inverse residuals was used, and four bottleneck groups were used. At the same time, to improve the recognition rate of the model, each bottleneck group was connected to a 3×3 convolutional layer to enhance regional feature extraction and increase the number of feature maps. Finally, a black ice recognition experiment was performed on the constructed infrared road black ice dataset. The network model proposed in this paper had an accurate recognition rate of 99.07% for black ice.

• Journal of Digital Contents Society
• /
• v.18 no.6
• /
• pp.1041-1047
• /
• 2017

There are many methods for surveying the status of a road, and the use of unmanned aerial vehicle (UAV) photo is one such method. When the UAV images are too large to be processed and suspected to be redundant, a texture extraction technique is used to transform the data into a reduced set of feature representations. This is an important task in 3D simulation using UAV images because a huge amount of data can be inputted. This paper presents a texture extraction method from UAV images to obtain high-resolution images of bridges. The proposed method is in three steps: firstly, we use the 3D bridge model from the V-World database; secondly, textures are extracted from oriented UAV images; and finally, the extracted textures from each image are blended. The result of our study can be used to update V-World textures to a high-resolution image.

• Journal of Advanced Navigation Technology
• /
• v.19 no.6
• /
• pp.484-491
• /
• 2015

Aerial scene is greatly increased by the introduction and supply of the image due to the growth of digital optical imaging technology and development of the UAV. It has been used as the extraction of ground properties, classification, change detection, image fusion and mapping based on the aerial image. In particular, in the image analysis and utilization of deep learning algorithm it has shown a new paradigm to overcome the limitation of the field of pattern recognition. This paper presents the possibility to apply a more wide range and various fields through the segmentation and classification of aerial scene based on the Deep learning(ConvNet). We build 4-classes image database consists of Road, Building, Yard, Forest total 3000. Each of the classes has a certain pattern, the results with feature vector map come out differently. Our system consists of feature extraction, classification and training. Feature extraction is built up of two layers based on ConvNet. And then, it is classified by using the Multilayer perceptron and Logistic regression, the algorithm as a classification process.