• 한국멀티미디어학회논문지
• /
• 제19권12호
• /
• pp.1909-1918
• /
• 2016

This paper presents a unified framework for joint Convolutional Neural Network (CNN) based vehicle detection by leveraging multi-spectral image pairs. With the observation that under challenging environments such as night vision and limited light source, vehicle detection in a single color image can be more tractable by using additional far-infrared (FIR) image, we design joint CNN architecture for both RGB and FIR image pairs. We assume that a score map from joint CNN applied to overall image can be considered as confidence of vehicle existence. To deal with various scale ratios of vehicle candidates, multi-scale images are first generated scaling an image according to possible scale ratio of vehicles. The vehicle candidates are then detected on local maximal on each score maps. The generation of overlapped candidates is prevented with non-maximal suppression on multi-scale score maps. The experimental results show that our framework have superior performance than conventional methods with a joint framework of multi-spectral image pairs reducing false positive generated by conventional vehicle detection framework using only single color image.

• 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.

• 대한임베디드공학회논문지
• /
• 제6권1호
• /
• pp.8-15
• /
• 2011

This paper presents an effective method for detecting vehicles in front of the camera-assisted car during nighttime driving. The proposed method detects vehicles based on detecting vehicle headlights and taillights using techniques of image segmentation and clustering. First, in order to effectively extract spotlight of interest, a pre-signal-processing process based on camera lens filter and labeling method is applied on road-scene images. Second, to spatial clustering vehicle of detecting lamps, a grouping process use light tracking method and locating vehicle lighting patterns. For simulation, we are implemented through Da-vinci 7437 DSP board with visible light mono-camera and tested it in urban and rural roads. Through the test, classification performances are above 89% of precision rate and 94% of recall rate evaluated on real-time environment.

• 한국멀티미디어학회논문지
• /
• 제21권8호
• /
• pp.888-896
• /
• 2018

In this paper, we report detection and recognition of vehicle logo from images captured from street CCTV. Image data includes both the front and rear view of the vehicles. The proposed method is a two-step process which combines image preprocessing and faster region-based convolutional neural network (R-CNN) for logo recognition. Without preprocessing, faster R-CNN accuracy is high only if the image quality is good. The proposed system is focusing on street CCTV camera where image quality is different from a front facing camera. Using perspective transformation the top view images are transformed into front view images. In this system, the detection and accuracy are much higher as compared to the existing algorithm. As a result of the experiment, on day data the detection and recognition rate is improved by 2% and night data, detection rate improved by 14%.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 1995년도 춘계공동학술대회논문집; 전남대학교; 28-29 Apr. 1995
• /
• pp.316-323
• /
• 1995

This paper presents an image processing technique to get traffic information such as vehicle volume, velocity, and occupancy for measuring the traffic congestion rate. To obtain these information, two horizontal lines are previously set on the screen. A moving vehicle is detected using the gray level difference on each line, and also template matching method at night. Threshold values are determined by sampling pavement grey level, and updated dynamically to cope with the change of ambient light conditions. These technique is successfully used to calculate vehicle volume, occupancy, and velocity. This study can be applied to traffic signal control system for minimizing traffic congestion in urban areas.

• 전자공학회논문지SC
• /
• 제42권2호
• /
• pp.11-18
• /
• 2005

본 논문은 CCD 카메라를 통해 입력받은 영상에서 차량을 검출하는 방법을 제안한다. 차량을 검출하기 위해서 먼저 영상을 독립적인 방향과 레벨을 가지는 스티어블 피라미드로 변환한다. 특징 벡터는 스티어블 피라미드로 변환된 서브밴드들을 연관되는 같은 위치의 픽셀들을 체인으로 연결하여 방향성 피라미드 특징을 가지는 다차원 벡터들로 구성한다. 차량의 검출은 특징 점의 특징 벡터들을 차량 검출에 사용하였다. 특징 점은 기하학적 위치 정보와 국부적인 방향 정보를 가지는데 실험을 위해서 격자 구조 모양으로 일정한 간격을 갖는 격자 점, 사람의 수작업을 통해서 만든 코너 점, 그리고 격자 내의 코너 점을 대상으로 했다. 차량 검출을 위해 미리 저장된 모델 영상의 특징 점들의 특징벡터들과 후보 영상으로부터 추출된 특징 벡터들의 정합을 통해 각 특징 점의 거리를 비교했다. 차량 검출을 위해 특징 점을 이용함으로써 후보 영상 전체를 비교하지 않고 특징 점의 위치에 대해서만 특징 벡터를 비교하기 때문에 비교 시간과 정확도를 높일 수 있었다. 또한 주변 밝기조건 및 그림자의 영향에 의해 차량 검출이 민감한 문제를 해결할 수 있었다. 도로에서 획득한 주간 영상(10,567)과 저녁 영상(624)을 대상으로 실험하였고, 검출율은 주간의 경우 $92.0\%$와 야간의 경우 $87.3\%$를 얻을 수 있었다.

• International journal of advanced smart convergence
• /
• 제10권4호
• /
• pp.263-272
• /
• 2021

At a time when securing driving safety is the most important in the development and commercialization of autonomous vehicles, AI and big data-based algorithms are being studied to enhance and optimize the recognition and detection performance of various static and dynamic vehicles. However, there are many research cases to recognize it as the same vehicle by utilizing the unique advantages of radar and cameras, but they do not use deep learning image processing technology or detect only short distances as the same target due to radar performance problems. Radars can recognize vehicles without errors in situations such as night and fog, but it is not accurate even if the type of object is determined through RCS values, so accurate classification of the object through images such as cameras is required. Therefore, we propose a fusion-based vehicle recognition method that configures data sets that can be collected by radar device and camera device, calculates errors in the data sets, and recognizes them as the same target.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2012년도 한국컴퓨터종합학술대회논문집 Vol.39 No.1(B)
• /
• pp.369-371
• /
• 2012

Shadow detection and elimination is a critical issue in vision-based system to improve the detection performance of moving objects. However, traditional algorithms are useless at night time because they used the chromaticity and brightness information from the color image sequence. To obtain the high detection performance, we can use the thermal camera and there are shadows by the heat not the light. We proposed a novel algorithm to detect and eliminate the shadows using the thermal intensity and the locality property. By combining two results of the intensity-based and locality-based, we can detect the shadows by the heat and improve the detection performance of moving object.

• 융합신호처리학회논문지
• /
• 제5권3호
• /
• pp.181-189
• /
• 2004

본 논문은 전조등의 특징을 이용하여 야간에 측후방에서 다가오는 차량을 탐지하는 방법을 설명한다. 야간 차량의 전조등은 검은색 배경의 야간 도로 영상에서 측후방 차량을 탐지하기 위한 좋은 특징이다. 입력 영상은 임계값 처리기법에 의해 검은색 배경과 흰색 영역으로 이루어지는 이진 영상으로 변환되고, 모폴로지 연산 중 열림 연산을 이용하여 잡음을 제거한다. 분할된 흰색 영역들에 대해 기하학적 특징과 모멘트 특징을 이용하여 전조등의 특징량을 측정하고, 의사 결정 트리에 의해 전조등 후보로 적당한 대상체들을 분류한다. 대상체들간의 위상학적 관계를 분석하여 한 쌍의 전조등을 탈지함으로써 측후방 차량을 탐지한다. 실험 결과 전조등 특징을 이용한 야간 측후방 차량 탐지 방법이 효과적임을 알 수 있었다. 제안한 방법은 야간 측후방 추돌경보시스템에 적용될 수 있으며, 향후에는 스테레오비전시스템을 사용하여 전조등 탐지 기반의 측후방 차량 거리 및 위치 측정에 관한 연구를 수행할 것이다.

• 대한임베디드공학회논문지
• /
• 제11권5호
• /
• pp.313-323
• /
• 2016

With the development of autonomous vehicle, there has been active research on advanced driver assistance system for road marking detection using vision sensor and 3D Laser scanner. However, vision sensor has the weak points that detection is difficult in situations involving severe illumination variance, such as at night, inside a tunnel or in a shaded area; and that processing time is long because of a large amount of data from both vision sensor and 3D Laser scanner. Accordingly, this paper proposes a road marking detection and classification method using single 2D Laser scanner. This method road marking detection and classification based on accumulation distance data and intensity data acquired through 2D Laser scanner. Experiments using a real autonomous vehicle in a real environment showed that calculation time decreased in comparison with 3D Laser scanner-based method, thus demonstrating the possibility of road marking type classification using single 2D Laser scanner.