• 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.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2019년도 제59차 동계학술대회논문집 27권1호
• /
• pp.123-124
• /
• 2019

This paper proposes an improved deep learning method based on small data sets for animal image classification. Firstly, we use a CNN to build a training model for small data sets, and use data augmentation to expand the data samples of the training set. Secondly, using the pre-trained network on large-scale datasets, such as VGG16, the bottleneck features in the small dataset are extracted and to be stored in two NumPy files as new training datasets and test datasets. Finally, training a fully connected network with the new datasets. In this paper, we use Kaggle famous Dogs vs Cats dataset as the experimental dataset, which is a two-category classification dataset.

• 한국측량학회지
• /
• 제29권4호
• /
• pp.429-438
• /
• 2011

LiDAR technology is a combination of laser ranging, satellite positioning technology and digital image technology for study and determination with high accuracy of the true earth surface features in 3 D. Laser scanning data is typically a points cloud on the ground, including coordinates, altitude and intensity of laser from the object on the ground to the sensor (Wehr & Lohr, 1999). Data from laser scanning can produce products such as digital elevation model (DEM), digital surface model (DSM) and the intensity data. In Vietnam, the LiDAR technology has been applied since 2005. However, the application of LiDAR in Vietnam is mostly for topological mapping and DEM establishment using point cloud 3D coordinate. In this study, another application of LiDAR data are present. The study use the intensity image combine with some other data sets (elevation data, Panchromatic image, RGB image) in Bacgiang City to perform land cover classification using neural network method. The results show that it is possible to obtain land cover classes from LiDAR data. However, the highest accurate classification can be obtained using LiDAR data with other data set and the neural network classification is more appropriate approach to conventional method such as maximum likelyhood classification.

• Korean Journal of Geomatics
• /
• 제3권1호
• /
• pp.59-65
• /
• 2003

The merging of different scales or multi-sensor image data is becoming a widely used procedure of the complementary nature of various data sets. Ideally, the merging method should not distort the characteristics of the high-spatial and high-spectral resolution data used. To present an effective merging method for survey of reclaimed land using the high-resolution (6.6 m) Electro-Optical Camera (EOC) panchromatic image of the first Korea Multi-Purpose Satellite 1 (KOMPSA T-l) and the multispectral Moderate Resolution Imaging Spectroradiometer (MODIS) image data, this paper compares the results of Intensity Hue Saturation (IHS) and Principal Component Analysis (PCA) methods. The comparison is made by statistical and visual evaluation of three-color combination images of IHS and PCA results based on spatial and spectral characteristics. The use of MODIS bands 1, 2, and 3 with a contrast stretched EOC panchromatic image as a substitute for intensity was found to be particularly effective in this study.

• Nuclear Medicine and Molecular Imaging
• /
• 제42권2호
• /
• pp.172-180
• /
• 2008

PET/CT fused image with anatomical and functional information have improved medical diagnosis and interpretation. This fusion has resulted in more precise localization and characterization of sites of radio-tracer uptake. However, a motion during whole-body imaging has been recognized as a source of image quality degradation and reduced the quantitative accuracy of PET/CT study. The respiratory motion problem is more challenging in combined PET/CT imaging. In combined PET/CT, CT is used to localize tumors and to correct for attenuation in the PET images. An accurate spatial registration of PET and CT image sets is a prerequisite for accurate diagnosis and SUV measurement. Correcting for the spatial mismatch caused by motion represents a particular challenge for the requisite registration accuracy as a result of differences in PET/CT image. This paper provides a brief summary of the materials and methods involved in multiple investigations of the correction for respiratory motion in PET/CT imaging, with the goal of improving image quality and quantitative accuracy.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권1호
• /
• pp.454-475
• /
• 2018

This paper presents a novel Android malware classification model planned to classify and categorize Android malicious code at Drebin dataset. The amount of malicious mobile application targeting Android based smartphones has increased rapidly. In this paper, Restricted Boltzmann Machine and Deep Belief Network are used to classify malware into families of Android application. A texture-fingerprint based approach is proposed to extract or detect the feature of malware content. A malware has a unique "image texture" in feature spatial relations. The method uses information on texture image extracted from malicious or benign code, which are mapped to uncompressed gray-scale according to the texture image-based approach. By studying and extracting the implicit features of the API call from a large number of training samples, we get the original dynamic activity features sets. In order to improve the accuracy of classification algorithm on the features selection, on the basis of which, it combines the implicit features of the texture image and API call in malicious code, to train Restricted Boltzmann Machine and Back Propagation. In an evaluation with different malware and benign samples, the experimental results suggest that the usability of this method---using Deep Belief Network to classify Android malware by their texture images and API calls, it detects more than 94% of the malware with few false alarms. Which is higher than shallow machine learning algorithm clearly.

• 한국가금학회지
• /
• 제22권4호
• /
• pp.233-238
• /
• 1995

A computer vision system was built to generate images of a single, stationary egg. This system includes a CGD camera, a frame grabber, and incandescent back lighting system. Image processing algorithms were developed to inspect egg shell and to sort eggs. Those values of both gray level and area of dark spots in the egg image were used as criteria to detect holes in egg and those values of both area and roundness of dark spots in the egg image were used to detect cracks in egg. For a sample of 300 eggs, this system was able to correctly analyze an egg for the presence of a defect 97.5% of the time. The weights of eggs were found to be linear to both the projected area and the perimeter of eggs viewed from above. Those two values were used as criteria to sort eggs. The coefficients of determination(r$^2$) for the regression equations between weights and those two values were 0.967 and 0.972 in the two sets of experiment. Accuracies in grading were found to be 95.6% and 96.7% as compared with results from sizing by electronic weight scale.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2003년도 춘계학술발표회 논문집
• /
• pp.171-180
• /
• 2003

The merging of different scales or multi-sensor image data is becoming a widely used procedure of the complementary nature of various data sets. Ideally, the merging method should not distort the characteristics of the high-spatial and high-spectral resolution data used. To present an effective merging method for survey of reclaimed land, this paper compares the results of Intensity Hue Saturation (IHS), Principal Component Analysis (PCA), Color Normalized(CN) and High Pass Filter(HPF) methods used to merge the information contents of the high-resolution (6.6 m) Electro-Optical Camera (EOC) panchromatic image of the first Korea Multi-Purpose Satellite 1 (KOMPSAT-1) and the multi-spectral Moderate Resolution Imaging Spectroradiometer (MODIS) image data. The comparison is made by visual evaluation of three-color combination images of IHS, PCA, CN and HPF results based on spatial and spectral characteristics. The use of a contrasted EOC panchromatic image as a substitute for intensity in merged images with MODIS bands 1, 2 and 3 was found to be particularly effective in this study.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제52권4호
• /
• pp.212-222
• /
• 2003

The ability to efficiently and robustly recover accurate 3D terrain models from sets of stereoscopic images is important to many civilian and military applications. A stereo matching has been an important tool for reconstructing three dimensional terrain. However, there exist many factors causing stereo matching error, such as occlusion, no feature or repetitive pattern in the correlation window, intensity variation, etc. Among them, occlusion can be only resolved by true multi-image stereo. In this paper, we present multi-image stereo method using DEM fusion as one of efficient and reliable true multi-image methods. Elevations generated by all pairs of images are combined by the fusion process which accepts an accurate elevation and rejects an outlier. We propose three fusion schemes: THD(Thresholding), BPS(Best Pair Selection) and MS(Median Selection). THD averages elevations after rejecting outliers by thresholding, while BPS selects the most reliable elevation. To determine the reliability of a elevation or detect the outlier, we employ the measure of self-consistency. The last scheme, MS, selects the median value of elevations. We test the effectiveness of the proposed methods with a quantitative analysis using simulated images. Experimental results indicate that all three fusion schemes showed much better improvement over the conventional binocular stereo in natural terrain of 29 Palms and urban site of Avenches.

• 디지털산업정보학회논문지
• /
• 제11권4호
• /
• pp.89-97
• /
• 2015

In this paper, a method of color image segmentation based on DBSCAN(Density Based Spatial Clustering of Applications with Noise) using compactness of superpixels and texture information is presented. The DBSCAN algorithm can generate clusters in large data sets by looking at the local density of data samples, using only two input parameters which called minimum number of data and distance of neighborhood data. Superpixel algorithms group pixels into perceptually meaningful atomic regions, which can be used to replace the rigid structure of the pixel grid. Each superpixel is consist of pixels with similar features such as luminance, color, textures etc. Superpixels are more efficient than pixels in case of large scale image processing. In this paper, superpixels are generated by SLIC(simple linear iterative clustering) as known popular. Superpixel characteristics are described by compactness, uniformity, boundary precision and recall. The compactness is important features to depict superpixel characteristics. Each superpixel is represented by Lab color spaces, compactness and texture information. DBSCAN clustering method applied to these feature spaces to segment a color image. To evaluate the performance of the proposed method, computer simulation is carried out to several outdoor images. The experimental results show that the proposed algorithm can provide good segmentation results on various images.