• Journal of Korea Multimedia Society
• /
• v.17 no.2
• /
• pp.143-151
• /
• 2014

In images degraded by bad weather, edges representing object boundaries become weak and faint. In this paper we present an image enhancement method, which increases image visibility by making edges as clear as possible. First, we choose edge candidate regions by finding local maxima and minima in an image intensity field, and then build a histogram using image intensities of pixels located at the two sides of candidate edges. Second, we decompose this histogram into multiple modes, which are determined by local minima in the histogram. Once modes are computed, we find modes connected by edges in the image intensity field and build link chains of connected modes. Finally we choose the longest link chain of modes and make the distances between every connected modes as large as possible. The darkest mode and the brightest mode should be within the image intensity range. This stretch makes edges clear and increases image visibility. Experiments show that the proposed method real-time enhances images degraded by bad weather as good as well known time-consuming methods.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.3
• /
• pp.669-676
• /
• 2018

The Geostationary Ocean Color Imager(: GOCI) detects the sea fog at a high horizontal resolution of $500m{\times}500m$ using the Rayleigh corrected reflectance of 8 bands. The visible and the near infrared waves strongly reflect the characteristics of the earth surface, causing errors in cloud and fog detection. A threshold of the Band7 reflectance was set to detect the sea fog entering the land. When the region on which Band4 reflectance is larger than Band8 is determinated as cloud, the error over-estimated as sea fog is corrected by comparing the average reflectance with the surrounding region. The improved algorithm has been verified by comparing the fog images of the Cheollian satellite (COMS: Communication, Ocean, and Meteorological Satellite) as well as the visibility data from the Korea Meteorological Administration.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1451-1466
• /
• 2023

In the context of maritime emergencies, the utilization of drones has rapidly increased, with a particular focus on their application in search and rescue operations. Deep learning models utilizing drone images for the rapid detection of distressed vessels and other maritime drift objects are gaining attention. However, effective training of such models necessitates a substantial amount of diverse training data that considers various weather conditions and vessel states. The lack of such data can lead to a degradation in the performance of trained models. This study aims to enhance the performance of deep learning models for distress ship detection by developing a maritime environment simulator to augment the dataset. The simulator allows for the configuration of various weather conditions, vessel states such as sinking or capsizing, and specifications and characteristics of drones and sensors. Training the deep learning model with the dataset generated through simulation resulted in improved detection performance, including accuracy and recall, when compared to models trained solely on actual drone image datasets. In particular, the accuracy of distress ship detection in adverse weather conditions, such as rain or fog, increased by approximately 2-5%, with a significant reduction in the rate of undetected instances. These results demonstrate the practical and effective contribution of the developed simulator in simulating diverse scenarios for model training. Furthermore, the distress ship detection deep learning model based on this approach is expected to be efficiently applied in maritime search and rescue operations.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.12
• /
• pp.2355-2362
• /
• 2016

Seg fog removal is an important issue concerned by both computer vision and image processing. Sea fog or haze removal is widely used in lots of fields, such as automatic control system, CCTV, and image recognition. Color image dehazing techniques have been extensively studied, and expecially the dark channel prior(DCP) technique has been widely used. This paper propose a fast and efficient image prior - dark channel prior to remove seg-fog from a single digital image based on the GPU. We implement the basic parallel program and then optimize it to obtain performance acceleration with more than 250 times. While paralleling and the optimizing the algorithm, we improve some parts of the original serial program or basic parallel program according to the characteristics of several steps. The proposed GPU programming algorithm and implementation results may be used with advantages as pre-processing in many systems, such as safe navigation for ship, topographical survey, intelligent vehicles, etc.

• Journal of the Semiconductor & Display Technology
• /
• v.17 no.2
• /
• pp.76-80
• /
• 2018

In recent years, with the development of automobile technology, smart system technology that assists safe driving has been developed. A camera is installed on the front and rear of the vehicle as well as on the left and right sides to detect and warn of collision risks and hazards. Beyond the technology of simple black-box recording via cameras, we are developing intelligent systems that combine various computer vision technologies. However, most related studies have been developed to optimize performance in laboratory-like environments that do not take environmental factors such as weather into account. In this paper, we propose a method to detect object by restoring visibility in image with degraded image due to weather factors such as fog. First, the image quality degradation such as fog is detected in a single image, and the image quality is improved by restoring using an intermediate value filter. Then, we used an adaptive feature extraction method that removes unnecessary elements such as noise from the improved image and uses it to recognize objects with only the necessary features. In the proposed method, it is shown that more feature points are extracted than the feature points of the region of interest in the improved image.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.2
• /
• pp.335-343
• /
• 2024

Real-time target signal processing techniques for FMCW LiDAR are described in this paper. FMCW LiDAR is gaining attention as the next-generation LiDAR for self-driving cars because of its detection robustness even in adverse environmental conditions such as rain, snow and fog etc. in addition to its long range measurement capability. The hardware architecture which is required for high-speed data acquisition, data transfer, and parallel signal processing for frequency-domain signal processing is described in this article. Fourier transformation of the acquired time-domain signal is implemented on FPGA in real time. The paper also details the C-FAR algorithm for ensuring robust target detection from the transformed target spectrum. This paper elaborates on enhancing frequency measurement resolution from the target spectrum and converting them into range and velocity data. The 3D image was generated and displayed using the 2D scanner position and target distance data. Real-time target signal processing and high-resolution image acquisition capability of FMCW LiDAR by using the proposed parallel signal processing algorithms based on FPGA architecture are verified in this paper.