• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.10 no.5
• /
• pp.47-52
• /
• 2011

Vehicle classification data are considerably used in the almost all fields of transportation planning and engineering. Highway agencies use a large number of vehicle classification schemes. Vehicles on the national highway are classified by 12-Category classification system, using number of axles, distances between axles, vehicle length, overhang, and other factors. In the case of using existing axle-sensor-based classification counters (that is, 12-category classification system), two-axle vehicles(Class 1 to 4) can be erroneously classified because a passenger vehicle becomes larger and similar with class 3 and 4. In this reason, this study proposes the vehicle classification scheme based on using vehicle height profiles obtained by a laser sensors. Also, the accuracy of the proposed method are tested through a field study.

• International Journal of Highway Engineering
• /
• v.12 no.4
• /
• pp.47-51
• /
• 2010

A vehicle classification data is essential for traffic road planning and pavement. In this study, the vehicle height, vehicle criteria for classification applied to measure the height of the car driving has devised a way to install equipment. It is capable of measuring the vehicle height was confirmed to field experiments, the measurement system is obtained to the vehicle length and height data. In this experiment, results showed the accuracy of 88.6% compared to classification data using the discriminant function obtained from video replaying. The height of vehicle applying the classification criteria can be utilized to determine the vehicle class.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.1D
• /
• pp.45-51
• /
• 2010

Traffic volume is essential data for traffic control or maintenance and rehabilitation planning. The volume especially with respect to the type of vehicles can facilitate to those road operations. In this research, a method for vehicle classification was developed using skewed sensors which can generate traffic signatures. In order to characterize vehicle types, the method investigates whether the second axle of each vehicle consists of dual tires. The presence of dual tire is determined by the discriminate function obtained from discriminant analysis. The validation using 1,878 vehicles recorded from a highway using a CCTV camera indicated significantly accurate results: 96.92% for class 1, 82.91% for class 3 and 79.13% for class 4.

• 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.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.791-794
• /
• 2021

범죄차량 판독 시스템, 지능화된 CCTV 등 차량과 관련된 시각지능에 관한 연구가 큰 관심을 받고 있다. 이 중 차량 분류 기술은, 특정 차량을 인식하는 핵심기술이다. 이와 관련한 기존 연구들은 큰 차종으로만 분류하거나, 분류 가능한 차종의 수, 정확도 등이 낮아 실용성 및 신뢰성이 떨어진다는 단점이 있다. 따라서, 본 논문에서는 차종을 정확하게 분류할 수 있는 2단계 차종 분류 알고리즘을 제안한다. 제안 시스템은 CNN으로 학습된 모델을 기반으로 1차로 차량의 유형을 분류하고, 2차로 정확한 차종을 분류한다. 실험 결과, 52개의 차종을 분류함에 있어 단일 분류 모델에 비해 5.3%p 더 높은 90.2%의 분류 정확도를 보였다. 이를 통해, 더욱 정확한 차종 분류가 가능하다.

• KIISE Transactions on Computing Practices
• /
• v.23 no.7
• /
• pp.408-416
• /
• 2017

This paper proposes a real-time side-rear vehicle detection algorithm that detects vehicles quickly and accurately in blind spot areas when driving. The proposed algorithm uses a cascade classifier created by AdaBoost Learning using the MCT (modified census transformation) feature vector. Using this classifier, the smaller the detection window, the faster the processing speed of the MCT classifier, and the larger the detection window, the greater the accuracy of the MCT classifier. By considering these characteristics, the proposed algorithm uses two classifiers with different detection window sizes. The first classifier quickly generates candidates with a small detection window. The second classifier accurately verifies the generated candidates with a large detection window. Furthermore, the vehicle classifier and the wheel classifier are simultaneously used to effectively detect a vehicle entering the blind spot area, along with an adjacent vehicle in the blind spot area.

• Proceedings of the KSRS Conference
• /
• 2009.03a
• /
• pp.350-353
• /
• 2009

본 논문에서는 국토모니터링 기술의 한 부분으로서 도로 지역에 대한 효율적인 실시간 교통모니터링을 위해 도로상의 차량 정보를 LiDAR 데이터로부터 취득하는 과정을 실험하였다. 도로영역의 데이터를 추출하기 위해서 좌표 변환된 수치지도와 LiDAR 데이터를 이용하였고, 국지적 임계치 필터링을 사용하여 추출된 도로영역의 데이터를 차량과 도로의 자료로 분리시키는 작업을 수행하였으며, 추출된 차량의 포인트들을 이용하여 차량을 표현할 수 있는 기본 속성값을 추출하였다. 마지막으로, 분리된 차량의 포인트에 대해서 MDC(Minimum Distance Classification) 클러스터링를 이용하여 차량의 종류를 분류하였다. 결과적으로 본 연구를 통하여 차량인식과 차량의 종류에 대한 분류를 수행할 수 있음을 확인하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.238-241
• /
• 2019

In this paper, a "Vehicle Analysis System(VAS) using cloud and data mining" is proposed that store all the sensor data measured in the vehicle in the cloud, analyze the stored data using the classification model, and provide the analyzed data in real time to the driver's display. The VAS consists of two modules. First, Sensor Data Communication Module(SDCM) stores the sensor data measured in the vehicle in a table of the cloud server and transfers the stored data to the analysis module. Second, Sensor Data Analysis Module(SDAM) analyzes the received data using the genetic algorithm and provides analyzed result to the driver in real time. The VAS stores sensor data collected in the vehicle in the cloud server without accumulating it in the vehicle, and stored data is analyzed in the cloud server, so that the sensor data can be quickly and efficiently managed without overloading the vehicle. In addition, the information desired by the driver can be visualized on the display, thereby increasing the stability of the autonomous vehicle.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06c
• /
• pp.429-432
• /
• 2010

주차장에서는 다양한 형태의 사건 사고가 발생하는데, 기존 DVR(CCTV)는 단순 영상녹화 기능만 지원하므로, 이를 효과적으로 분석하는데는 한계가 있다. 따라서, DVR의 영상카메라와 마이크를 통해서 입력되는 영상과 사운드 신호를 대상으로, 해당 영상이 발생하는 음향 신호의 종류를 파악하여, 특정 음향이 발생한 영상구간을 저장하여 이를 검색할 수 있다면, 주차장 관리자가 효과적으로 사건 사고를 대처할 수 있게 된다. 본 연구에서는 주차장에서 발생하는 차량관련 음향(충돌음, 과속음, 경적음, 유리파손, 비명)을 분류하기 위해 효과적인 특징벡터를 제안하고, 제안한 특징벡터를 이용하여 신경망 차량음향분류기를 설계하여 성능을 평가함으로써, 효과적으로 차량음향을 분류하기 위한 방법을 제안하였다. 또한, 신경망 차량음향분류기를 DVR시스템과 연동하여, 마이크로부터 입력되는 음향신호를 실시간 분석하고, 특정 소리가 발생한 영상구간을 기록함으로써, 음향 키워드에 의해서 해당 사고영상을 검색 및 디스플레이하는 시스템을 개발하였다.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.4D
• /
• pp.549-551
• /
• 2006

Vehicle License Plate Recognition System reads information from vehicles license plate using image detection devices. Of many applications provided by Vehicle License Plate Recognition System, some, such as speed enforcing system, can be problematic when the system incorrectly scans letters or numbers from a vehicle's license plate. Using Cautious Classifier avoids such problems by discarding the scanned information when the confidence level is doubted to be low. This study develops the License Plate Recognition System using Cautious Classifier and investigates effectiveness of applying the Weighted Instance Method to improve the performance of Cautious Classifier.