• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2012년도 추계학술대회
• /
• pp.887-890
• /
• 2012

Image recognition is one of the most important research directions of pattern recognition. Image based road automatic identification technology is widely used in current society, the intelligence has become the trend of the times. This paper studied the image segmentation algorithm theory and its application in road signs recognition system. With the help of image processing technique, respectively, on road signs automatic recognition algorithm of three main parts, namely, image segmentation, character segmentation, image and character recognition, made a systematic study and algorithm. The experimental results show that: the image segmentation algorithm to establish road signs recognition model, can make effective use of smart phone system and application.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권3호
• /
• pp.861-880
• /
• 2023

Semantic segmentation of road scene is the key technology of autonomous driving, and the improvement of convolutional neural network architecture promotes the improvement of model segmentation performance. The existing convolutional neural network has the simplification of learning knowledge and the complexity of the model. To address this issue, we proposed a road scene semantic segmentation algorithm based on multi-task collaborative learning. Firstly, a depthwise separable convolution atrous spatial pyramid pooling is proposed to reduce model complexity. Secondly, a collaborative learning framework is proposed involved with saliency detection, and the joint loss function is defined using homoscedastic uncertainty to meet the new learning model. Experiments are conducted on the road and nature scenes datasets. The proposed method achieves 70.94% and 64.90% mIoU on Cityscapes and PASCAL VOC 2012 datasets, respectively. Qualitatively, Compared to methods with excellent performance, the method proposed in this paper has significant advantages in the segmentation of fine targets and boundaries.

• 한국정보통신학회논문지
• /
• 제21권2호
• /
• pp.409-415
• /
• 2017

본 논문은 watershed를 이용한 차도 분할 알고리즘을 제안하고 있다. 제안된 알고리즘은 차량과 차선 정보를 이용해 차도 마커와 배경 마커를 자동 생성하는 automatic marked watershed를 이용한 영역 분할 알고리즘이고 이는 지나치게 많은 영역이나 마커를 위한 수작업 같은 watershed 기반 영역 분할의 문제점들을 해결할 수 있다. 차도 마커는 차선은 포함되나 차량은 배제되는 순수한 차도 영역을 위한 속성을 포함하고 배경 마커는 차량과 배경을 포함하는 나머지 영역을 위한 속성을 포함하고 있다. 실제 도로 영상에 적용된 영역 분할 결과들은 제안된 알고리즘은 다양한 환경에서 적절한 마커들을 생성할 수 있고, 주행 차로와 양옆 차로를 포함한 필수 차도 영역을 적절하게 분할할 수 있는 것을 보여주고, 성능 면에 있어서는 제안된 알고리즘은 수작업으로 생성된 마커를 사용한 기존 알고리즘과 대등함을 보여준다.

• 한국인공지능학회지
• /
• 제11권4호
• /
• pp.1-8
• /
• 2023

In this paper, we propose a black ice detection platform framework using Convolutional Neural Networks (CNNs). To overcome black ice problem, we introduce a real-time based early warning platform using CNN-based architecture, and furthermore, in order to enhance the accuracy of black ice detection, we apply a multi-scale dilation convolution feature fusion (MsDC-FF) technique. Then, we establish a specialized experimental platform by using a comprehensive dataset of thermal road black ice images for a training and evaluation purpose. Experimental results of a real-time black ice detection platform show the better performance of our proposed network model compared to conventional image segmentation models. Our proposed platform have achieved real-time segmentation of road black ice areas by deploying a road black ice area segmentation network on the edge device Jetson Nano devices. This approach in parallel using multi-scale dilated convolutions with different dilation rates had faster segmentation speeds due to its smaller model parameters. The proposed MsCD-FF Net(2) model had the fastest segmentation speed at 5.53 frame per second (FPS). Thereby encouraging safe driving for motorists and providing decision support for road surface management in the road traffic monitoring department.

• 한국도로학회논문집
• /
• 제18권4호
• /
• pp.1-8
• /
• 2016

PURPOSES : This study evaluates the reliability of the patterns of changes in the road surface temperature during winter using a statistical technique. In addition, a flexible road segmentation method is developed based on the collected road surface temperature data. METHODS : To collect and analyze the data, a thermal mapping system that could be attached to a survey vehicle along with various other sensors was employed. We first selected the test route based on the date and the weather and topographical conditions, since these factors affect the patterns of changes in the road surface temperature. Each route was surveyed a total of 10 times on a round-trip basis at the same times (5 AM to 6 AM). A correlation analysis was performed to identify whether the weather conditions reported for the survey dates were consistent with the actual conditions. In addition, we developed a method for dividing the road into sections based on the consecutive changes in the road surface temperature for use in future applications. Specifically, in this method, the road surface temperature data collected using the thermal mapping system was compared continuously with the average values for the various road sections, and the road was divided into sections based on the temperature. RESULTS : The results showed that the comparison of the reported and actual weather conditions and the standard deviation in the observed road surface temperatures could produce a good indicator of the reliability of the patterns of the changes in the road surface temperature. CONCLUSIONS : This research shows how road surface temperature data can be evaluated using a statistical technique. It also confirms that roads should be segmented based on the changes in the temperature and not using a uniform segmentation method.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.525-527
• /
• 2003

Recently, the spatial resolution of earth observation satellites is significantly increased to a few meters. Such high spatial resolution images definitely will provide lots of information for detail-thirsty remote sensing users. However, it is more difficult to develop automated image algorithms for automated image feature extraction and pattern recognition. In this study, we propose a two-stage procedure to extract road information from high resolution satellite images. At first stage, a watershed segmentation technique is developed to classify the image into various regions. Then, a knowledge is built for road and used to extract the road regions. In this study, we use panchromatic and multi-spectral images of the IKONOS satellite as test dataset. The experiment result shows that the proposed technique can generate suitable and meaningful road objects from high spatial resolution satellite images. Apparently, misclassified regions such as parking lots are recognized as road needed further refinement in future research.

• 한국정보통신학회논문지
• /
• 제24권11호
• /
• pp.1437-1444
• /
• 2020

컴퓨터 비전 시스템의 발달로 보안, 생체인식, 의료영상, 자율주행 등의 분야에 많은 발전이 있었다. 자율주행 분야에서는 특히 딥러닝을 이용한 객체인식, 탐지 기법이 주로 사용되는데, 자동차가 갈 수 있는 영역을 판단하기 위한 도로영역 인식이 특히 중요한 문제이다. 도로 영역은 일반적인 객체탐지에서 활용되는 사각영역인식과는 달리 비정형적인 형태를 띠므로, ROI 기반의 객체인식 구조는 적용할 수 없다. 본 논문에서는 Semantic segmentation 기법을 사용한 비정형적인 도로영역 인식에 맞는 심층 신경망 구조를 제안한다. 또한 도로영역에 특화된 네트워크 구조인 Multi-scale semantic segmentation 기법을 사용하여 성능이 개선됨을 입증하였다.

• 한국인터넷방송통신학회논문지
• /
• 제13권2호
• /
• pp.233-237
• /
• 2013

이미지 인식은 패턴인식의 중요한 한 연구 분야이다. 본 논문은 이미지 세그멘테이션 알고리즘을 소개하고, 이의 응용으로 도로 Sign 인식시스템에 적용하여 그 결과를 고찰하였다. 본 논문에서, 우리는 이미지 프로세싱 기술의 도움으로 도로 Sign 의 체계적인 연구를 하였고, 이에 해당하는 알고리즘을 만들었다. 도로 Sign을 인식하기 위하여, 본 논문은 이미지 세그멘테이션 알고리즘 파트와 이미지 인식파트의 두 부분으로 나누어서 기술하였다. 인식실험은 도로 Sign 인식 알고리즘 모델이 스마트 폰에 유용하게 사용될 것과, 그 외 여러분야에 사용될 수 있음을 보여 준다.

• Journal of information and communication convergence engineering
• /
• 제10권4호
• /
• pp.378-383
• /
• 2012

This paper presents the implementation of an automatic road sign recognizer for an intelligent transport system. In this system, lists of road signs are processed with actions such as line segmentation, single sign segmentation, and storing an artificial sign in the database. The process of taking the video stream and extracting the road sign and storing in the database is called the road sign recognition. This paper presents a study on recognizing traffic sign patterns using a segmentation technique for the efficiency and the speed of the system. The image is converted from one scale to another scale such as RGB to grayscale or grayscale to binary. The images are pre-processed with several image processing techniques, such as threshold techniques, Gaussian filters, Canny edge detection, and the contour technique.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2015년도 추계학술대회
• /
• pp.687-690
• /
• 2015

전방 추돌 경보 시스템(FCWS) 및 차선 이탈 경보 시스템(LDWS)에서 차선 및 객체 검출을 위한 관심영역은 차도영역으로 설정되어야 한다. 분수계 분할(watershed segmentation)방법은 차도영역을 분리하기에 효과적인 알고리즘이다. 이 알고리즘은 초기 seed에 속해있는 watershed line과 국부 최소값에 따라서 분할 결과가 다르게 나타나는데 차도 seed에 그 이외의 영역이나 차량이 포함될 경우에 차도 이외의 부분이 차도영역으로 포함되어 분할된다. 이런 문제점을 보완하기 위해 도로 환경에 따라 차도 seed를 적응적으로 변경해야 한다. 그 방법으로 영상을 여러 개의 관심영역으로 분할하여 차선을 검출하고 자기차선을 잇는 직선을 초기 seed로 설정한다. 설정된 seed에 차량이 검출되면 seed 위치를 조정하고 조정된 위치에서 차선을 지나지 않는다면 차선을 지나도록 seed의 크기를 조정하여 최종적인 seed를 결정한다. 최종적으로 결정된 seed를 통해서 도로환경에 따라 적응적으로 차도영역을 검출을 가능하게 한다.