• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06b
• /
• pp.504-506
• /
• 2012

운전자 지원 시스템(ADAS)은 최근 지능형 자동차 분야에서 중요한 이슈로 손꼽히는 기술 중 하나이다. 이 중에서 실시간 표지판 인식 기술은 운전자 지원 시스템의 하나로 운전자의 안전과 직결될 수 있어 높은 정확성과 실시간성이 요구된다. 그동안 표지판 인식 분야는 색상과 현상을 기반으로 연구가 진행되어왔으나, 교통 표지판은 국가별로 그 특징과 형태가 각기 상이하여 적용하는데 한계가 있다. 본 논문에서는 한국의 속도제한 표지판을 실시간으로 검출하고 인식하기 위하여, 1) 영상에서 색상 특징을 이용하여 후보 영역을 검출하고, 2) 형상 정보를 분석하여 표지판의 형태를 검증하고, 3) 검출된 후보영역의 내부문자(숫자)를 분할하고 인식하는 시스템을 제안한다.

• Journal of Broadcast Engineering
• /
• v.20 no.6
• /
• pp.938-949
• /
• 2015

In this paper, we propose a robust speed-limit sign recognition system which is durable to any sign changes caused by exterior damage or color contrast due to light direction. For recognition of speed-limit sign, we apply CNN which is showing an outstanding performance in pattern recognition field. However, original CNN uses multiple hidden layers to extract features and uses fully-connected method with MLP(Multi-layer perceptron) on the result. Therefore, the major demerit of conventional CNN is to require a long time for training and testing. In this paper, we apply randomly-connected classifier instead of fully-connected classifier by combining random forest with output of 2 layers of CNN. We prove that the recognition results of CNN with random forest show best performance than recognition results of CNN with SVM (Support Vector Machine) or MLP classifier when we use eight speed-limit signs of GTSRB (German Traffic Sign Recognition Benchmark).

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.12B
• /
• pp.1766-1774
• /
• 2010

This paper proposes a real-time algorithm of recognizing speed limit signs for intelligent vehicles. Contrary to previous works which use all the pixel values in the ROI (Region Of Interest) after preprocessing image at ROI and need a lot of operations, the proposed algorithm uses fewer DCT coefficients in the ROI as features of each image to reduce the number of operations. Choosing a portion of DCT coefficients which satisfy discriminant criteria for recognition, the proposed algorithm recognizes the speed limit signs using the information obtained in the selected features through LDA and MD. It selects one having the highest probability among the recognition results calculated by accumulating the classification results of consecutive individual frames. Experimental results show that the recognition rate for consecutive frames reaches to 100% with test images. When compared with the previous algorithm, the numbers of multiply and add operations are reduced by 58.6% and 38.3%, respectively.

• Journal of Broadcast Engineering
• /
• v.23 no.1
• /
• pp.93-103
• /
• 2018

This paper presents a method for speed limit sign recognition in images. Conventional sign recognition methods decreases recognition accuracy because they are very sensitive and include repeated features. The proposed method emphasizes color attributes based on the weighted YUV color space. Moreover, the recognition accuracy can be improved by extracting the local region of interest (ROI) in the candidates. The proposed method uses the Haar features and the Adaboost classifier for recognition. Experimental results confirm that the proposed algorithm is superior to conventional algorithms under various speed signs and conditions.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2000.04a
• /
• pp.668-671
• /
• 2000

본 논문은 노변과 차량간의 RF통신을 이용하여 차량의 속도를 제어하는 시스템이다. 본 시스템에서 노변의 RF송수신기는 운전자에게 도로의 제한속도를 포함하여 사고의 발생, 도로의 결빙과 같은 교통정보를 제공한다. 이때 차량의 속도가 제한속도 이상일 경우에는 차량 내 제어장치가 작동하여 차량의 속도를 제한속도 이하가 되도록 한다. 현재 도로를 주행중인 운전자는 제한속도표지판을 보아야 그 도로의 제한속도를 인식할 수 있다. 그러므로 자칫 제한속도표지판을 인식하지 못하고 지나치는 경우에 운전자는 무의식중에 과속운전을 할 수도 있다. 과속운전으로 인한 문제점은 우리나라에서 일어나는 교통사고의 상당부분을 차지할 정도로 크다. 따라서 본 개발 시스템은 운전자가 과속운전을 할 수 없도록 과속운전시 2∼3차례 경고방송을 하고 그래도 운전자가 속도를 줄이지 않을 경우 자동으로 차량의 속도를 제한속도이하가 되도록 한다.

• Journal of Korean Society of Transportation
• /
• v.25 no.4
• /
• pp.7-19
• /
• 2007

The purpose of posted speeds is to provide a speed that ensures the safety of vehicle flow according to given road situations. Because of this, posted speeds must be carefully examined, and posted speeds at freeway exits and entrances in particular should consider car characteristics. Posted speeds at freeway exits and entrances must take changing speeds due to curve radiuses into consideration and in this study, an 85th percentile speed becomes the most important element to consider. When it is considered that most traffic accidents occur because of variations in speed between cars, posted speeds should be set after considering car traveling characteristics. Within these dimensions, instead of putting significance on an upper direction regulation or lower direction regulation, speed distributions which fit to the characteristics of each road should be fully considered. Accordingly, this study evaluated appropriate posted speeds that will reduce the dangers of traffic accidents through posted speed regulations of roads now in operation by offering a posted speed setting method theory, using entries at Yangji, Yongin, and Cheongwon interchanges as subjects.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.12B
• /
• pp.1574-1585
• /
• 2011

This paper proposes a real-time algorithm for speed limit sign recognition for advanced safety vehicle system. The proposed algorithm uses Block-DCT in extracting features from a given ROI(Region Of Interest) instead of using entire pixel values as in previous works. The proposed algorithm chooses parts of the DCT coefficients according to the proposed discriminant factor, uses correlation coefficients and variances among ROIs from training samples to reduce amount of arithmetic operations without performance degradation in classification process. The algorithm recognizes the speed limit signs using the information obtained during training process by calculating LDA and Mahalanobis Distance. To increase the hit rate of recognition, it uses accumulated classification results computed for a sequence of frames. Experimental results show that the hit rate of recognition for sequential frames reaches up to 100 %. When compared with previous works, numbers of multiply and add operations are reduced by 69.3 % and 67.9 %, respectively. Start after striking space key 2 times.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.3
• /
• pp.46-57
• /
• 2019

Generally speeding appeared to be the most contributing factor of fatalities occurred in work zones, and highway agencies in South Korea have concerned of the safety of workers and drivers in the poor circumstances. In this study, a portable variable message signs (PVMS) system as an alternative of control speeding in work zones was implemented. This study evaluated the safety effectiveness of the PVMS based on speeds and the compliance with the speed limit. Linear regression and logistic regression models were adopted to quantify the safety effect of the PVMS between the 'before' and 'after'. The results showed that most of points had statistically significant speeds reduction experience after PVMS installation. Also, the percentage of vehicle exceeding the speed limit by 10 km/h or more was decreased significantly between 50 and 80% in the 'after' periods compared to the 'before' periods. Therefore, the PVMS would be contributed to benefit safety in work zones which there is a difference in design speed of the adjacent normal section.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.4
• /
• pp.47-54
• /
• 2019

In the worldwide, The issue comes up which is the danger of car accidents from climate-change effects. We are considering about various types of speed limit signs for setting restricts to high-speed vehicles. South Korea has 4 seasons in the land. At Summer or Winter seasons have heavy rains and fogs or snow, In these seasons need to enforce speed limit laws or methods to prevent car collision. But South korea is using stationary speed limiters that is not enough to proof against rear-end car accidents in these climates. In this paper shows the necessity of independent LED speed limits display to reduce car accidents. And explaining the prototype model which is a combination of rain sensor and wiper systems. This model is independently changed the speed limits to 50%, 80%, 100% of standards by raindrops and snowflake. Also it is freely setting speed limits on each places anywhere it settled in. Visual effects of the model as being speed-down of vehicles helps to prevent rear-ending car accidents and traffic beforehand.

• Journal of Drive and Control
• /
• v.20 no.4
• /
• pp.92-99
• /
• 2023

Autonomous vehicles should recognize and respond to the specified speed to drive in compliance with regulations. To recognize the specified speed, the most representative method is to read the numbers of the signs by recognizing the speed signs in the front camera image. This study proposes a method that utilizes YOLO-Labeling-Labeling-EfficientNet. The sign box is first recognized with YOLO, and the numeric digit is extracted according to the pixel value from the recognized box through two labeling stages. After that, the number of each digit is recognized using EfficientNet (CNN) learned with the virtual environment dataset produced directly. In addition, we estimated the depth of information from the height value of the recognized sign through regression analysis. We verified the proposed algorithm using the virtual racing environment and GTSRB, and proved its real-time performance and efficient recognition performance.