• Journal of Korean Society of Transportation
• /
• v.27 no.6
• /
• pp.79-88
• /
• 2009

The objective of this study is to develop the new vehicle classification algorithm and minimize classification errors. The existing vehicle classification algorithm collects data from loop and piezo sensors according to the specification("Vehicle classification guide for traffic volume survey" 2006) given by the Ministry of Land, Transport and Maritime Affairs. The new vehicle classification system collects the vehicle length, distance between axles, axle type, wheel-base and tire type to minimize classification error. The main difference of new system is the "Wandering" sensor which is capable of measuring the wheel-base and tire type(single or dual). The wandering sensor obtains the wheel-base and tire type by detecting both left and right tire imprint. Verification tests were completed with the total traffic volume of 762,420 vehicles in a month for the new vehicle classification algorithm. Among them, 47 vehicles(0.006%) were not classified within 12 vehicle types. This results proves very high level of classification accuracy for the new system. Using the new vehicle classification algorithm will improve the accuracy and it can be broadly applicable to the road planning, design, and management. It can also upgrade the level of traffic research for the road and transportation infrastructure.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.469-472
• /
• 2022

With the recent development of intelligent transportation systems, various technologies applying deep learning technology are being used. To crackdown on illegal vehicles and criminal vehicles driving on the road, a vehicle type classification system capable of accurately determining the type of vehicle is required. This study proposes a vehicle type classification system optimized for mobile traffic control systems using YOLO(You Only Look Once). The system uses a one-stage object detection algorithm YOLOv5 to detect vehicles into six classes: passenger cars, subcompact, compact, and midsize vans, full-size vans, trucks, motorcycles, special vehicles, and construction machinery. About 5,000 pieces of domestic vehicle image data built by the Korea Institute of Science and Technology for the development of artificial intelligence technology were used as learning data. It proposes a lane designation control system that applies a vehicle type classification algorithm capable of recognizing both front and side angles with one camera.

• Journal of Korean Society of Transportation
• /
• v.27 no.4
• /
• pp.55-61
• /
• 2009

In order to observe the impact of a type of vehicles for traffic flows and pavement, vehicle classifications is conducted. Korean Ministry of Land, Transport and Maritime Affairs provides 12-type vehicle classifications on National expressways, National highways, and Provincial roads. Current AVC (Automatic Vehicle Classification) devices decide vehicle types comparing measurements of vehicle lengths, wheelbases, overhangs etc. to a reference table including those of all types of models. This study developed an algorithm for macroscopic vehicle classification which is less sensitive to tuning sensors and updating the reference table. For those characteristics, trend lines in vehicle lengths and wheelbases are employed. To assess the algorithm developed, vehicle lengths and wheelbases were collected from an AVC device. In this experiment, this algorithm showed the accuracy of 88.2 % compared to true values obtained from video replaying. Our efforts in this study are expected to contribute to developing devices for macroscopic vehicle classification.

• Journal of Convergence for Information Technology
• /
• v.8 no.6
• /
• pp.375-380
• /
• 2018

This paper proposes a classification method using the Convolutional Neural Network(CNN) which can obtain the type of trucks from the input image without the feature extraction step. To automatically classify vehicle images according to the type of truck cargo box, the top view images of the vehicle are used as input image and we design the structure of the CNN suitable for the input images. Learning images and correct output results is generated and the weights of neural network are obtained through the learning process. The actual image is input to the CNN and the output of the CNN is calculated. The classification performance is evaluated through comparison CNN output with actual vehicle types. Experimental results show that vehicle images could be classified with more than 90 percent accuracy according to the type of cargo box and this method can be used for pre-classification for inspecting loading defect.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.36 no.6
• /
• pp.1059-1068
• /
• 2016

The current operation method for the AVC (Automatic Vehicle Classification) equipment does not generate vehicle speed, traffic volume and vehicle type information when part of the sensors has failed. Inefficiency of current methods would not use the collected data from the normal sensor. In this study was conducted research on the calculating method at the traffic volume and vehicle speed in the sensor failure AVC equipment. The failure situation of the sensor was classified into 4 types. Calculating the traffic volume and vehicle speed information for each type, and accuracy of these informations were analyzed. Analysis results, traffic volume was possible to calculate a highly accurate value (accuracy: 100%, 98%, 97%). In the case of speed, the accuracy of the calculated speed value reaches a level that can be accepted sufficiently (RMSE value is less than 16.8). So, using the methodology proposed in this study are expected to be able to increase the operational efficiency of the AVC equipment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.5
• /
• pp.2171-2185
• /
• 2020

In order to judge that whether the vehicles in different images which are captured by surveillance cameras represent the same vehicle or not, we proposed a novel vehicle face recognition algorithm based on improved Nonnegative Matrix Factorization (NMF), different from traditional vehicle recognition algorithms, there are fewer effective features in vehicle face image than in whole vehicle image in general, which brings certain difficulty to recognition. The innovations mainly include the following two aspects: 1) we proposed a novel idea that the vehicle type can be determined by a few key regions of the vehicle face such as logo, grille and so on; 2) Through adding weight, sparseness and classification property constraints to the NMF model, we can acquire the effective feature bases that represent the key regions of vehicle face image. Experimental results show that the proposed algorithm not only achieve a high correct recognition rate, but also has a strong robustness to some non-cooperative factors such as illumination variation.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.10 no.3
• /
• pp.179-188
• /
• 2015

We propose obstacle classification method based on 2D LIDAR(Light Detecting and Ranging) database. The existing obstacle classification method based on 2D LIDAR, has an advantage in terms of accuracy and shorter calculation time. However, it was difficult to classifier the type of obstacle and therefore accurate path planning was not possible. In order to overcome this problem, a method of classifying obstacle type based on width data of obstacle was proposed. However, width data was not sufficient to improve accuracy. In this paper, database was established by width, intensity, variance of range, variance of intensity data. The first classification was processed by the width data, and the second classification was processed by the intensity data, and the third classification was processed by the variance of range, intensity data. The classification was processed by comparing to database, and the result of obstacle classification was determined by finding the one with highest similarity values. An experiment using an actual autonomous vehicle under real environment shows that calculation time declined in comparison to 3D LIDAR and it was possible to classify obstacle using single 2D LIDAR.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.193-196
• /
• 2010

In this paper, we propose a method to classify the types of vehicle as full, medium, or small size. The proposed method is composed of three steps. First, after obtaining vehicle contour from template candidate image, edge distance template is created by distance transform of the vehicle's contour. Second, the vehicle type of input image is classified as the type of template which has minimal edge distance with input image. The edge distance value means the measurement of distance between input image and template at each pixel which is part of vehicle contour. Experimental results demonstrate that our method presented a good performance of 80% about test images.

• Smart Structures and Systems
• /
• v.13 no.5
• /
• pp.849-868
• /
• 2014

An indirect approach is explored for structural health bridge monitoring allowing for wide, yet cost-effective, bridge stock coverage. The detection capability of the approach is tested in a laboratory setting for three different reversible proxy types of damage scenarios: changes in the support conditions (rotational restraint), additional damping, and an added mass at the midspan. A set of frequency features is used in conjunction with a support vector machine classifier on data measured from a passing vehicle at the wheel and suspension levels, and directly from the bridge structure for comparison. For each type of damage, four levels of severity were explored. The results show that for each damage type, the classification accuracy based on data measured from the passing vehicle is, on average, as good as or better than the classification accuracy based on data measured from the bridge. Classification accuracy showed a steady trend for low (1-1.75 m/s) and high vehicle speeds (2-2.75 m/s), with a decrease of about 7% for the latter. These results show promise towards a highly mobile structural health bridge monitoring system for wide and cost-effective bridge stock coverage.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.9
• /
• pp.13-20
• /
• 2022

It's proposed and analyzed ML(Machine Learning) models to predict vehicle FC(Fuel Consumption) in real-time. The test driving was done for a car to measure vehicle speed, acceleration, road gradient and FC for training dataset. The various ML models were trained with feature data of speed, acceleration and road-gradient for target FC. There are two kind of ML models and one is regression type of linear regression and k-nearest neighbors regression and the other is classification type of k-nearest neighbors classifier, logistic regression, decision tree, random forest and gradient boosting in the study. The prediction accuracy is low in range of 0.5 ~ 0.6 for real-time FC and the classification type is more accurate than the regression ones. The prediction error for total FC has very low value of about 0.2 ~ 2.0% and regression models are more accurate than classification ones. It's for the coefficient of determination (R²) of accuracy score distributing predicted values along mean of targets as the coefficient decreases. Therefore regression models are good for total FC and classification ones are proper for real-time FC prediction.