• 한국멀티미디어학회논문지
• /
• 제20권11호
• /
• pp.1729-1740
• /
• 2017

This paper describes a vision-based method that effectively recognize a traffic light. The method consists of two steps of traffic light detection and discrimination. Many related studies have used color information to detect traffic light, but color information is not robust to the varying illumination environment. This paper proposes a new method of traffic light detection based on intensity and saturation. When a traffic light is turned on, the light region usually shows values with high saturation and high intensity. However, when the light region is oversaturated, the region shows values of low saturation and high intensity. So this study proposes a method to be able to detect a traffic light under these conditions. After detecting a traffic light, it estimates the size of the body region including the traffic light and extracts the body region. The body region is compared with five models which represent specific traffic signals, then the region is discriminated as one of the five models or rejected as none of them. Experimental results show the performance of traffic light detection reporting the precision of 97.2%, the recall of 95.8%, and correct recognition rate of 94.3%. These results shows that the proposed method is effective.

• 대한임베디드공학회논문지
• /
• 제9권3호
• /
• pp.145-150
• /
• 2014

This paper presents an effective vision based method for LED traffic light detection at the daytime. First, the proposed method calculates horizontal coordinates to set region of interest (ROI) on input sequence images. Second, the proposed uses color segmentation method to extract region of green and red traffic light. Next, to classify traffic light and another noise, shape filter and haar-like feature value are used. Finally, temporal delay filter with weight is applied to remove blinking effect of LED traffic light, and state and weight of traffic light detection are used to classify types of traffic light. For simulations, the proposed method is implemented through Intel Core CPU with 2.80 GHz and 4 GB RAM, and tested on the urban and rural road video. Average detection rate of traffic light is 94.50 % and average recognition rate of traffic type is 90.24 %. Average computing time of the proposed method is 11 ms.

• 대한임베디드공학회논문지
• /
• 제10권2호
• /
• pp.101-108
• /
• 2015

In this paper, a robust traffic light detection method is proposed by using vision sensor and DGPS(Difference Global Positioning System). The conventional vision-based detection methods are very sensitive to illumination change, for instance, low visibility at night time or highly reflection by bright light. To solve these limitations in visual sensor, DGPS is incorporated to determine the location and shape of traffic lights which are available from traffic light database. Furthermore the geometric relationship between traffic light and vision sensor is used to locate the traffic light in the image by using DGPS information. The empirical results show that the proposed method improves by 51% in detection rate for night time with marginal improvement in daytime environment.

• 한국멀티미디어학회논문지
• /
• 제21권11호
• /
• pp.1244-1253
• /
• 2018

The color of traffic light is sensitive to various illumination conditions. Especially it loses the hue information when oversaturation happens on the lighting area. This paper proposes a traffic light recognition method robust to these illumination variations. The method consists of two steps of traffic light detection and recognition. It just uses the intensity and saturation in the first step of traffic light detection. It delays the use of hue information until it reaches to the second step of recognizing the signal of traffic light. We utilized a deep learning technique in the second step. We designed a deep convolutional neural network(DCNN) which is composed of three convolutional networks and two fully connected networks. 12 video clips were used to evaluate the performance of the proposed method. Experimental results show the performance of traffic light detection reporting the precision of 93.9%, the recall of 91.6%, and the recognition accuracy of 89.4%. Considering that the maximum distance between the camera and traffic lights is 70m, the results shows that the proposed method is effective.

• 반도체디스플레이기술학회지
• /
• 제21권4호
• /
• pp.92-98
• /
• 2022

This paper proposes a new method of the traffic signal detection and the recognition in an HSI color model. The proposed method firstly converts a ROI image in the RGB model to in the HSI model to segment the color of a traffic signal. Secondly, the segmented colors are dilated by the morphological processing to connect the traffic signal light and the signal light case and finally, it extracts the traffic signal light and the case by the aspect ratio using the connected component analysis. The extracted components show the detection and the recognition of the traffic signal lights. The proposed method is implemented using C language in Raspberry Pi 4 system with a camera module for a real-time image processing. The system was fixedly installed in a moving vehicle, and it recorded a video like a vehicle black box. Each frame of the recorded video was extracted, and then the proposed method was tested. The results show that the proposed method is successful for the detection and the recognition of traffic signals.

• 융합정보논문지
• /
• 제10권8호
• /
• pp.40-46
• /
• 2020

교통안전에 대한 관심이 높아짐에 따라 교통사고의 발생률을 줄이는 자율 주행에 대한 연구가 지속적으로 진행되고 있다. 객체의 인식과 탐지는 자율 주행을 위한 필수적인 요소이다. 때문에 도로 상황을 판단하기 위하여 교통 영상 빅데이터에서 객체 인식 및 탐지에 대한 연구가 활발히 진행 중이다. 하지만 기존 연구들은 대부분 주간 데이터만 사용하기 때문에 야간 도로에서 객체 인식이 어렵다. 특히 광원 객체의 경우 빛 번짐과 백화 현상으로 인해 주간의 특징을 그대로 사용하기 어렵다. 따라서 본 연구에서는 교통 영상 빅데이터 처리를 위한 Yolo 기반 광원 객체 탐지를 제안한다. 제안하는 방법은 야간 교통 영상을 대상으로 색상 모델 변화를 적용하여 이미지 처리를 수행한다. 이미지 처리를 통해서 객체의 특징을 추출하여 객체의 후보군을 결정한다. 후보군 데이터를 활용하여 딥러닝 모델을 통해 야간 도로에서 광원 객체 탐지의 인식률을 높이는 것이 가능하다.

• 반도체디스플레이기술학회지
• /
• 제15권2호
• /
• pp.43-48
• /
• 2016

In this paper, we propose a traffic light detection and recognition (TLDR) algorithm in the daytime. The proposed algorithm utilizes the color and shape information for the TLDR. At first, a traffic light is detected and recognized based on its shape information. Then, the color range of the detected traffic light is investigated in HSV color space. The input data of the proposed TLDR algorithm is the color image captured using the black box camera during driving. Our simulations demonstrate that the proposed algorithm can achieve a high detection and recognition performance for the images including traffic lights.

• International Journal of Contents
• /
• 제14권2호
• /
• pp.24-29
• /
• 2018

In this paper, we propose an efficient traffic light detection (TLD) method as an advanced driver assistance system (ADAS) for elderly drivers. Since an increase in traffic accidents is associated with the aging population and an increase in elderly drivers causes a serious social problem, the provision of ADAS for older drivers via TLD is becoming a necessary(Ed: verify word choice: necessary?) public service. Therefore, we propose an economical TLD method that can be implemented with a simple black box (built in camera) and a smartphone in the near future. The system utilizes a color pre-processing method to differentiate between the stop and go signals. A mathematical morphology algorithm is used to further enhance the traffic light detection and a circular Hough transform is utilized to detect the traffic light correctly. From the simulation results of the computer vision and image processing based on a proposed algorithm on Matlab, we found that the proposed TLD method can detect the stop and go signals from the traffic lights not only in daytime, but also at night. In the future, it will be possible to reduce the traffic accident rate by recognizing the traffic signal and informing the elderly of how to drive by voice.

• 제어로봇시스템학회논문지
• /
• 제21권12호
• /
• pp.1122-1129
• /
• 2015

This paper suggests a method of detecting traffic lights for vehicles by combining the HSV(hue saturation value) color model, morphometric characteristics, and location information appearing on consecutive images in daytime. In order to detect the traffic light, the color corresponding to the signal lights should be explored. It is difficult to detect traffic lights among colors of lights from buildings, taillight of cars, leaves, placards, etc. The proposed algorithm searches for the traffic lights from many candidates using morphometric characteristics and location information in consecutive images. The recognition process is divided into three steps. The first step is to detect candidates after converting RGB channel into HSV color model. The second step is to extract the boundaries between the housing of traffic lights and background by exploiting the assumption that the housing has lower brightness than the surrounding background. The last step is to recognize the signal light after eliminating the false candidates using morphometric characteristics and location information appearing on consecutive images. This paper demonstrates successful detection results of traffic lights from various images captured on the city roads.

• 방송공학회논문지
• /
• 제22권1호
• /
• pp.62-69
• /
• 2017

신호등 검출은 첨단운전자보조시스템에서 매우 중요하며 최근 신호등 검출 알고리즘의 연구가 활발히 진행 중이다. 그러나 기존의 영상처리 기반의 신호등검출 알고리즘은 조명의 변화에 민감하다는 문제점이 있다. 이러한 문제점을 해결하기 위하여 본 논문에서는 다음과 같은 신호등 검출 알고리즘을 제안한다. 먼저 제안하는 컬러맵과 HSV(hue-saturation-value)를 이용하여 신호등의 후보영역을 검출한다. 이후 검출된 신호등 후보영역으로부터 HOG(histogram of oriented gradient) 서술자와 SVM(support vector machine)을 이용하여 신호등을 검출한다. 검출된 신호등 영상을 이용하여 제안하는 Multilayer HOG 서술자를 이용하여 신호등의 방향 정보를 결정한다. 실험결과에서 확인할 수 있듯이 제안하는 알고리즘은 높은 검출성능과 실시간 처리가 가능하다.