• 한국정보통신학회논문지
• /
• 제23권5호
• /
• pp.540-546
• /
• 2019

본 연구는 야간조명 영상에 대한 정보손실을 최소화하는 이진화 방법을 제안한다. 야간조명 영상의 대상은 조명의 영향으로 초점이 맞지 않으며 식별이 불가능한 영상이다. 또한 영상은 명도 히스토그램에서 일부 영역에만 치우친 명도 영역을 가지고 있다. 그래서 기존의 단순한 이진화 방법은 좋은 결과를 얻기에는 힘들다. 제안한 이진화 방법은 영상을 분할하는 방법과 영상 합병 방법을 사용한다. 단계별로 분할된 블록 내에서는 삼각형 타입의 퍼지논리를 이용하여 두 영역으로 구분한다. 소속도의 값이 0은 현 단계에서 이진화하며 소속도의 값이 1은 다음 단계 이후에 이진화를 한다. 실험 결과는 검은색부분에 밀집된 명도 영역에서 정보손실이 최소화된 야간조명 영상을 취득할 수 있었다.

• Current Optics and Photonics
• /
• 제6권6호
• /
• pp.608-618
• /
• 2022

By analyzing the signal-to-noise ratio (SNR) theory of the conventional true color night vision system, we found that the output image SNR is limited by the wavelength range of the system response λ₁ and λ₂. Therefore, we built a double-channel four-band true color night vision system to expand the system response to improve the output image SNR. In the meantime, we proposed an image fusion method based on principal component analysis (PCA) and nonsubsampled shearlet transform (NSST) to obtain the true color night vision images. Through experiments, a method based on edge extraction of the targets and spatial dimension decorrelation was proposed to calculate the SNR of the obtained images and we calculated the correlation coefficient (CC) between the edge graphs of obtained and reference images. The results showed that the SNR of the images of four scenes obtained by our system were 125.0%, 145.8%, 86.0% and 51.8% higher, respectively, than that of the conventional tri-band system and CC was also higher, which demonstrated that our system can get true color images with better quality.

• 한국멀티미디어학회논문지
• /
• 제22권1호
• /
• pp.44-54
• /
• 2019

Recently, image-based object detection has made great progress with the introduction of Convolutional Neural Network (CNN). Many trials such as Region-based CNN, Fast R-CNN, and Faster R-CNN, have been proposed for achieving better performance in object detection. YOLO has showed the best performance under consideration of both accuracy and computational complexity. However, these data-driven detection methods including YOLO have the fundamental problem is that they can not guarantee the good performance without a large number of training database. In this paper, we propose a data sampling method using CycleGAN to solve this problem, which can convert styles while retaining the characteristics of a given input image. We will generate the insufficient data samples for training more robust object detection without efforts of collecting more database. We make extensive experimental results using the day-time and night-time road images and we validate the proposed method can improve the object detection accuracy of the night-time without training night-time object databases, because we converts the day-time training images into the synthesized night-time images and we train the detection model with the real day-time images and the synthesized night-time images.

• 한국멀티미디어학회논문지
• /
• 제20권12호
• /
• pp.1901-1912
• /
• 2017

Traffic lights at night are usually framed in the image as bright regions bigger than the real size due to glow effect. Moreover, the colors of lighting region saturate to white. So it is difficult to distinguish between different traffic lights at night. Many related studies have tried to decrease the glow effect in the process of capturing images. Some studies drastically decreased the shutter time of the camera to reduce the adverse effect by the glow. However, this makes the video too dark. This study proposes a new idea which utilizes the glow effect. It examines the outer radial region of traffic light. It presents an algorithm to discriminate the color of traffic light by the analysis of the outer radial region. The advantage of the proposed method is that it can recognize traffic lights in the image captured by an ordinary black box camera. Experimental results using seven short videos show the performance of traffic light recognition reporting the precision of 96.4% and the recall of 98.2%. These results show that the proposed method is valid and effective.

• 한국자동차공학회논문집
• /
• 제21권1호
• /
• pp.51-60
• /
• 2013

In this paper, to control the existing headlamp control system using steering wheel angle more efficiently and more actively, image processing algorithm which improved the detection rate of lane at night based on camera was suggested. And to recognize road lane more clearly in the conditions of low illumination, new algorithms were developed in the aspects of improving brightness, extracting clear lane edge and using the characteristics of lane. Through this research, it turned out that lane detection ability by using the normalized stretching, angular mask and expected-area scan have good performance in the night compare to existing algorithms.

• 디지털융복합연구
• /
• 제19권2호
• /
• pp.365-371
• /
• 2021

분 논문은 도시의 야간 조명연출에 사용되고 있는 조명 기술 및 유형에 대해 연구하였다. 현 사회의 생활방식과 생활양식이 지속적으로 변화하고 혁신되어지면서 도시의 다양한 기능은 끊임없이 발전하고 있다. 현재 도시의 야간 조명은 낮 시간대의 경관을 조명기구를 통해 밤에 밝히는 것에 머물지 않고, 새로운 디지털 조명기술을 활용하여 독창적이고 지속적인 변화가 가능한 혁신적인 디지털 야경을 연출하고 있다. 이러한 도시의 야간 조명연출은 현대적인 디지털 아트와 융합하면서 도시의 브랜드 이미지를 높이고, 경제적 발전에도 영향력을 미친다. 그러므로 새로운 도시의 건설에서 야간 경관을 결정하는 디지털 조명연출은 중요한 연구가치를 가지게 되었으며, 혁신적인 조명연출 기술의 발달로 앞으로도 도시의 야경은 더욱 다양한 영상디자인적 경험을 제공 할 것으로 사료된다.

• 한국전자통신학회논문지
• /
• 제18권5호
• /
• pp.919-926
• /
• 2023

본 논문에서는 주야간 움직임 감지 시스템 개발을 위한 주야간 촬영이 가능한 카메라 시스템을 구현하였다. 이를 위해 CMOS 이미지 센서는 물론 IR-LED를 이용하여 야간에도 선명한 영상 캡처가 가능하도록 설계하였다. 또한 칼라모델 분리를 통해 비교적 단순한 움직임 감지 알고리즘을 제안하였다. 칼라모델에서 H채널만 추출한 후, 영상을 블럭으로 나눈 다음 연속 프레임간의 평균 색상값을 이용하여 블록 매칭방식을 적용함으로써 움직임을 감지할 수 있다. 촬영 중 움직임이 감지되면 자동으로 경보음이 울리면서 화면을 캡처하여 PC에 저장할 수 있는 주야간 움직임 감지 시스템을 구현하였다.

• 한국실내디자인학회논문집
• /
• 제24권6호
• /
• pp.137-144
• /
• 2015

Light was the symbol of the city's prosperity and culture. People can walk around the city at the night time with safe. Now light is used with beauty and function at the same time. This study is the example how to draw the lighting design concept in specific city and district based on the citizen-minded survey. The citizen-minded survey makes a new chance taking the goodness and characteristics from local city specially and select the site for applying the specific opinion and requirement in the city. The expression of design concept on night landscape design gives the fresh image to the city during the night time. Because people feel the free and dynamic mood in the night landscape lighting, it is very important to set and express the design concept on night landscape design. The result of this study was applied in the Daegu city. In particular, the distribution complex's night landscape lighting in the Daegu was designed with specific concept expression from the citizen-minded survey. Making and expressing the design concept on night landscape design is basic for unity and diversity in the city.

• 한국멀티미디어학회논문지
• /
• 제24권10호
• /
• pp.1311-1318
• /
• 2021

Agriculture is being damaged by harmful animals such as wild boars and water deer. It need to get permission to catch a wild boar and farmers are using a lot of methods to chase harmful animals. The methods through deep learning and image processing capture harmful animals with cameras. It is difficult to analyze harmful animals that are active at night. In this case, In this case, using deep learning by image correction can achieve a higher recognition rate.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권12호
• /
• pp.4292-4307
• /
• 2021

For the research field of night infrared surveillance video, the target imaging in the video is easily affected by the light due to the characteristics of the active infrared camera and the classical ViBe algorithm has some problems for moving target extraction because of background misjudgment, noise interference, ghost shadow and so on. Therefore, an improved ViBe algorithm (I-ViBe) for moving target extraction in night infrared surveillance video is proposed in this paper. Firstly, the video frames are sampled and judged by the degree of light influence, and the video frame is divided into three situations: no light change, small light change, and severe light change. Secondly, the ViBe algorithm is extracted the moving target when there is no light change. The segmentation factor of the ViBe algorithm is adaptively changed to reduce the impact of the light on the ViBe algorithm when the light change is small. The moving target is extracted using the region growing algorithm improved by the image entropy in the differential image of the current frame and the background model when the illumination changes drastically. Based on the results of the simulation, the I-ViBe algorithm proposed has better robustness to the influence of illumination. When extracting moving targets at night the I-ViBe algorithm can make target extraction more accurate and provide more effective data for further night behavior recognition and target tracking.