• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -2
• /
• pp.769-772
• /
• 2000

In this paper, a new lateral offset estimation method, based on image processing techniques, is proposed for driver assistant system. A new description on lane markings in the image plane is presented, and its properties are discussed and used to detect lane markings. Multi-frame lane detection and analysis are adopted to improve the proposed lateral control method. An algorithm for obstacle detection is also developed. Experimental results show that the proposed method performs lateral control effectively.

• IEIE Transactions on Smart Processing and Computing
• /
• 제5권6호
• /
• pp.390-394
• /
• 2016

This paper presents a new comparison method for haze-removal algorithms in next-generation automotive systems. Compared to previous peak signal-to-noise ratio-based comparisons, which measure similarity, the proposed modulation transfer function-based method checks sharpness to select a more suitable haze-removal algorithm for lane detection. Among the practical filtering schemes used for a haze-removal algorithm, experimental results show that Gaussian filtering effectively preserves the sharpness of road images, enhancing lane detection accuracy.

• 대한임베디드공학회논문지
• /
• 제11권3호
• /
• pp.163-171
• /
• 2016

Lane detection is a widely researched topic. Although simple road detection is easily achieved by previous methods, lane detection becomes very difficult in several complex cases involving noisy edges. To address this, we use a Convolution neural network (CNN) for image enhancement. CNN is a deep learning method that has been very successfully applied in object detection and recognition. In this paper, we introduce a robust lane detection method based on a CNN combined with random sample consensus (RANSAC) algorithm. Initially, we calculate edges in an image using a hat shaped kernel, then we detect lanes using the CNN combined with the RANSAC. In the training process of the CNN, input data consists of edge images and target data is images that have real white color lanes on an otherwise black background. The CNN structure consists of 8 layers with 3 convolutional layers, 2 subsampling layers and multi-layer perceptron (MLP) of 3 fully-connected layers. Convolutional and subsampling layers are hierarchically arranged to form a deep structure. Our proposed lane detection algorithm successfully eliminates noise lines and was found to perform better than other formal line detection algorithms such as RANSAC

• 스마트미디어저널
• /
• 제6권3호
• /
• pp.15-20
• /
• 2017

최근 자동차 산업은 IT 기술을 접목하여 운전자에게 편의를 제공하기 위한 운전자 보조 시스템에 관한 연구가 진행되고 있다. 본 논문에서는 차선 이탈 방지 및 자율 주행에 적용 가능한 도로상태 변화에 강인한 차선 검출 방법을 제안한다. 제안하는 방법은 Otsu 임계값 결정 방법과 가우시안 필터와 에지를 통한 후보 영역 검출 방법을 이용한다. 또한, 허프 변환을 통한 차선의 기울기와 폭 정보를 이용하여 차선을 검출한다. 실선뿐만 아니라 점선 차선 검출을 위해 기존에 검출된 차선 정보를 이용하여 다음 프레임에서 차선이 위치할 경로를 계산해 가상의 차선을 그려주는 방법을 제안한다. 제안하는 알고리즘은 실선과 점선상황에서 차선 검출이 모두 가능했고 오픈소스 하드웨어인 라즈베리 파이 2에 적용할 경우 실시간 처리가 가능함을 확인했다.

• 제어로봇시스템학회논문지
• /
• 제20권9호
• /
• pp.950-956
• /
• 2014

In this paper, the real-time detection method of a DDP (Driving Direction Point) is proposed for an unmanned vehicle to safely follow the center of the road. Since the DDP is defined as a center point between two lanes, the lane is first detected using a web camera. For robust detection of the lane, the binary thresholding and the labeling methods are applied to the color camera image as image preprocessing. From the preprocessed image, the lane is detected, taking the intrinsic characteristics of the lane such as width into consideration. If both lanes are detected, the DDP can be directly obtained from the preprocessed image. However, if one lane is detected, the DDP is obtained from the inverse perspective image to guarantee reliability. To verify the proposed method, several experiments to detect the DDPs are carried out using a 4 wheeled vehicle ERP-42 with a web camera.

• 한국컴퓨터정보학회논문지
• /
• 제22권3호
• /
• pp.27-34
• /
• 2017

We propose a cascade lane detector that uses biased discriminant analysis (BDA) to work effectively even when there are various external factors on the road. The proposed cascade detector was designed with an existing lane detector and the detection module using BDA. By placing the BDA module in the latter stage of the cascade detector, the erroneously detected results by the existing detector due to sunlight or road fraction were filtered out at the final lane detection results. Experimental results on road images taken under various environmental conditions showed that the proposed method gave more robust lane detection results than conventional methods alone.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -1
• /
• pp.23-26
• /
• 2000

An improved inverse perspective mapping (IIPM) is proposed so as to reduce computational expense of recovery of 3D road surface. An experimental system based on IIPM is developed to detect lane parameters for a driver assistant system. A re-organized image is obtained quickly and exactly by IIPM. Efficient preprocessing techniques are used to enhance the information of lane and obstacles. Lane in the preprocessed. image is located with region identification. Lane parameters are estimated effectively. An algorithm to adaptively modify the parameters of IIPM is given. Properties of obstacle on 3D road surface are discussed and used to detect obstacles in the current lane and neighboring lanes. Experimental results show that the new method can extract lane state information effectively.

• 전자공학회논문지S
• /
• 제36S권1호
• /
• pp.93-103
• /
• 1999

본 논문은 주행중의 자동차에 장착된 카메라의 입력 영상으로부터 이동창을 활용하여 차선을 인식하고 장애물을 감지하는 기법을 기술한다. 영상 정보로부터 장애물을 감지하기 위해서 차선의 위치를 빠른 시간에 추출하는 것이 매우 중요하다. 이를 위하여 한 프레임의 영상에서 차선의 입력이 예상되는 일부분만을 선정하는 기법이 일반적이다. 본 논문에서는 주행 차량의 영상 정보로부터 장애물을 감지하기 위하여, 도로의 곡률에 따라 차선의 입력 예상 위치를 측정하여 크기가 조절된 이동하는 창을 설정하여 정확한 차선의 위치를 추출하고, 나아가 주행 차선 내에 위치하는 장애물을 점출할 수 있는 기법을 제안한다. 이를 고정창을 이용하는 경우와 레이저 혹은 레이터 센서를 사용하는 경우와 비교하여, 정확도가 높음을 보였다.

• 한국멀티미디어학회논문지
• /
• 제21권12호
• /
• pp.1396-1406
• /
• 2018

Lane detection is a key function in developing autonomous vehicle technology. In this paper, we propose a lane marker detection algorithm robust to environmental variation targeting low cost embedded computing devices. The proposed algorithm consists of two phases: initialization phase which is slow but has relatively higher accuracy; and the tracking phase which is fast and has the reliable performance in a limited condition. The initialization phase detects lane markers using a set of filters utilizing the various features of lane markers. The tracking phase uses Kalman filter to accelerate the lane marker detection processing. In a tracking phase, we measure the reliability of the detection results and switch it to initialization phase if the confidence level becomes below a threshold. By combining the initialization and tracking phases we achieved high accuracy and acceptable computing speed even under a low cost computing resources in which we cannot use the computing intensive algorithm such as deep learning approach. Experimental results show that the detection accuracy is about 95% on average and the processing speed is about 20 frames per second with Raspberry Pi 3 which is low cost device.

• 대한임베디드공학회논문지
• /
• 제4권4호
• /
• pp.180-189
• /
• 2009

Currently, most automobile companies are interested in research on intelligent autonomous vehicle. They are mainly focused on driver's intelligent assistant and driver replacement. In order to develop an autonomous vehicle, lateral and longitudinal control is necessary. This paper presents a lateral and longitudinal control system for autonomous vehicle that has only mono-vision camera. For lane detection, we present a new lane detection algorithm using clothoid parabolic road model. The proposed algorithm in compared with three other methods such as virtual line method, gradient method and hough transform method, in terms of lane detection ratio. For adaptive control, we apply a vanishing point estimation to fuzzy control. In order to improve handling and stability of the vehicle, the modeling errors between steering angle and predicted vanishing point are controlled to be minimized. So, we established a fuzzy rule of membership functions of inputs (vanishing point and differential vanishing point) and output (steering angle). For simulation, we developed 1/8 size robot (equipped with mono-vision system) of the actual vehicle and tested it in the athletics track of 400 meter. Through the test, we prove that our proposed method outperforms 98 % in terms of detection rate in normal condition. Compared with virtual line method, gradient method and hough transform method, our method also has good performance in the case of clear, fog and rain weather.