• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.10
• /
• pp.110-116
• /
• 2017

This paper presents an effective demosaicking algorithm for color filter array (CFA) images acquired from single-sensor devices based on directional interpolation and nonlocal properties of the image. We interpolate the G channel considering diagonal directions as well as horizontal and vertical directions, using a small number of pixels to reflect local properties of the image. Then, we overcome image degradations, such as zipper effects near edges and false colors, by applying nonlocal means (NLM) filtering to the interpolated pixels. R and B channels are reproduced by using directional interpolation with information of the reconstructed G channel and NLM filtering. Experimental results for various McMaster images with high saturation and color changes show that the proposed algorithm accomplishes high PSNR compared with conventional methods. Moreover, the proposed method demonstrates better subjective quality compared with existing methods in terms of reduction of quality degradation, like false colors, and preservation of the image structures, such as edges and textures.

• Journal of Korea Multimedia Society
• /
• v.19 no.12
• /
• 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.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.61 no.3
• /
• pp.55-65
• /
• 2019

Although crack on concrete exists from its early formation, crack requires attention as it affects stiffness of structure and can lead demolition of structure as it grows. Detecting cracks on concrete is needed to take action prior to performance degradation of structure, and deep learning can be utilized for it. In this study, transfer learning, one of the deep learning techniques, was used to detect the crack, as the amount of crack's image data was limited. Pre-trained Inception-v3 was applied as a base model for the transfer learning. Web scrapping was utilized to fetch images of concrete wall with or without crack from web. In the recognition of crack, image post-process including changing size or removing color were applied. In the visualization of crack, source images divided into 30px, 50px or 100px size were used as input data, and different numbers of input data per category were applied for each case. With the results of visualized crack image, false positive and false negative errors were examined. Highest accuracy for the recognizing crack was achieved when the source images were adjusted into 224px size under gray-scale. In visualization, the result using 50 data per category under 100px interval size showed the smallest error. With regard to the false positive error, the best result was obtained using 400 data per category, and regarding to the false negative error, the case using 50 data per category showed the best result.

• The KIPS Transactions:PartB
• /
• v.14B no.2
• /
• pp.65-70
• /
• 2007

Red tide is becoming hot issue of environmental problem worldwide since the 1990. Advanced nations, are progressing study that detect red tide area on early time using satellite for sea. But, our country most seashores bends serious. Also because there are a lot of turbid method streams on coast, hard to detect small red tide area by satellite for sea that is low resolution. Also, method by sea color that use one feature of satellite image for sea of existent red tide area detection was most. In this way, have a few feature in image with sea color and it can cause false negative mistake that detect red tide area. Therefore, in this paper, acquired texture information to use GLCM(Gray Level Co occurrence Matrix)'s texture 6 information about high definition land satellite south Coast image. Removed needless component reducing dimension through principal component analysis from this information. And changed into 2 principal component accumulation images, Experiment result 2 principal component conversion accumulation image's eigenvalues were 94.6%. When component with red tide area that uses only sea color image and all principal component image. displayed more correct result. And divided as quantitative,, it compares with turbid stream and the sea that red tide does not exist using statistical feature analysis about texture.

• Journal of Information Processing Systems
• /
• v.15 no.1
• /
• pp.159-168
• /
• 2019

Accurate forest fires detection algorithms remain a challenging issue, because, some of the objects have the same features with fire, which may result in high false alarms rate. This paper presents a new video-based, image processing forest fires detection method, which consists of four stages. First, a background-subtraction algorithm is applied to detect moving regions. Secondly, candidate fire regions are determined using CIE $L{\ast}a{\ast}b{\ast}$ color space. Thirdly, special wavelet analysis is used to differentiate between actual fire and fire-like objects, because candidate regions may contain moving fire-like objects. Finally, support vector machine is used to classify the region of interest to either real fire or non-fire. The final experimental results verify that the proposed method effectively identifies the forest fires.

• Journal of Space Technology and Applications
• /
• v.3 no.2
• /
• pp.154-164
• /
• 2023

In space exploration, spectroscopic observation is useful for understanding objects' composition and physical properties. There are various methods for analyzing spectral data, and there are differences depending on the object and the wavelength. This paper introduces a method for analyzing visible & nearinfrared (VNIR) spectral data, which is mainly applied in lunar exploration. The main analysis methods include false color ratio image processing, reflectance pattern analysis, integrated band depth (IBD) processing, and continuum removal as preprocessing before analysis. These spectroscopic analysis methods help to understand the mineral properties of the lunar surface in the VNIR region and can be applied to other celestial bodies such as Mars.

• Journal of Satellite, Information and Communications
• /
• v.8 no.4
• /
• pp.89-94
• /
• 2013

This paper presents color video flame detection algorithm based on wavelet transform to remove detection of flickering non-flame objects. Conventional flame detection algorithms consist of simple or mixed functions using colors, temporal and spatial characteristics. But those algorithms detect non-flame objects as flame regions sometimes. False alarm reasons are flame-like objects with regular flickering lights such as car signal lamps, alarm lights etc. The proposed algorithm is to reduce false detection which is occurred in periodic flickering lights. At first, It segments the candidate flame regions by using frame difference, flame colors. Then it distinguish flame regions and non flame regions including flickering car lights by analyzing wavelet coefficients. Computer simulation results showed that the proposed algorithm removes false detection due to the periodic flickering lamps by performing 97.9% of correct detection rate while false detection rate is 7.3%.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.12
• /
• pp.105-110
• /
• 2016

To reduce the cost and volume of a digital camera, a subsampled color filter array(CFA) image is used and demosaicking is applied to estimate the missing color values. However, aliasing, the overlaps of signals in the frequency domain, occurs when signals are subsampled. This causes aliasing artifacts such as false colors and zipper effects in demosaicking processes. In this paper, the algorithm estimating high-quality color images by removing aliasing artifacts in them is proposed. The aliasing region map is estimated using the sub-sampled signals of the CFA image. By using the aliasing region map and the estimated luminance image, the least squares problem of the observation models is designed and aliasing artifacts are eliminated. The experiments demonstrate that the proposed algorithm restores color images without aliasing artifacts.

• International Journal of Advanced Culture Technology
• /
• v.8 no.4
• /
• pp.229-234
• /
• 2020

Dehazing significantly improves image quality by restoring the loss of contrast and color saturation for images taken in the presence. However, when applied to images not taken according to the prior information, dehazing can cause unintended degradation of image quality. To avoid unintended degradations, we present a hazy scene detection algorithm using a single image based on the distributions of hue, saturation, and dark channel. Through a heuristic approach, we find out statistical characteristics of the distribution of hue, saturation, and dark channels in the hazy scene and make a detection model using them. The proposed method can precede the dehazing to prevent unintended degradation. The detection performance evaluated with a set of test images shows a high hit rate with a low false alarm ratio. Ultimately the proposed method can be used to control the effect of dehazing so that the dehazing can be applied to wide variety of images without unintended degradation of image quality.

• Proceedings of the IEEK Conference
• /
• 2003.11a
• /
• pp.529-532
• /
• 2003

In this paper, we describe new method to detect face in real-time. We use color information, edge information, and binary information to detect candidate regions of eyes from input image, and then extract face region using the detected eye pall. We verify both eye candidate regions and face region using Support Vector Machines(SVM). It is possible to perform fast and reliable face detection because we can protect false detection through these verification processes. From the experimental results, we confirmed the proposed algorithm shows very excellent face detection performance.