• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.31-43
• /
• 2022

Traditional video compression has developed so far based on hybrid compression methods through motion prediction, residual coding, and quantization. With the rapid development of technology through artificial neural networks in recent years, research on image compression and video compression based on artificial neural networks is also progressing rapidly, showing competitiveness compared to the performance of traditional video compression codecs. In this paper, a new method capable of improving the performance of such an artificial neural network-based video compression model is presented. Basically, we take the rate-distortion optimization method using the auto-encoder and entropy model adopted by the existing learned video compression model and shifts some components of the latent information that are difficult for entropy model to estimate when transmitting compressed latent representation to the decoder side from the encoder side, and finally compensates the distortion of lost information. In this way, the existing neural network based video compression framework, MFVC (Motion Free Video Compression) is improved and the BDBR (Bjøntegaard Delta-Rate) calculated based on H.264 is nearly twice the amount of bits (-27%) of MFVC (-14%). The proposed method has the advantage of being widely applicable to neural network based image or video compression technologies, not only to MFVC, but also to models using latent information and entropy model.

• Journal of the Korean Society of Radiology
• /
• v.18 no.2
• /
• pp.153-159
• /
• 2024

In X-ray projection, Unskilled radiologists become skilled through fail exam. This causes the patient to be exposed to unnecessary radiation. In this study, pre-position unskilled radiologic technologist presented ways to improve clinical proficiency. presented a skull lateral x-ray projection practice method using visual, spatial, and assistive devices. In addition, the accuracy and usefulness of the use of assistive devices were evaluated. When X-ray images were taken based on learning, the rotational spacing, which indicates image distortion, was 7.85 ± 1.45 mm and the tiliting spacing was 4.84 ± 0.5 mm. When practicing using visual aids, the rotational spacing is 4.4 ± 0.76 mm and the inclination spacing is 3.01 ± 0.87 mm. using a spatial compensation device, the rotational spacing is 5.2 ± 0.69 mm and the tiliting spacing is 3.33 ± 0.61 mm. Skull lateral X-ray Image distortion caused by empirical photography practice decreased by 5.4%, but image distortion caused by tilting increased by 1.2%. When practicing using a visual assistive devices, the degree of rotational spacing by 40.1% and the tiliting spacing decreased by 30.7% compared to the empirical x-ray exposure practice. When using spatial assistive devices, the rotation interval was reduced by 41.7% and the tilting interval by 23.7% compared to conventional empirical x-ray exposure practice. Therefore, if an unskilled radiologist practices using visual and spatial aids,the accuracy will be improved in skull lateral x-ray projection.

• The KIPS Transactions:PartB
• /
• v.9B no.3
• /
• pp.351-358
• /
• 2002

Video compression based on DCT (Discrete Cosine Transform) has weakpoints of blocking artifacts and pixel loss when the resolution is changed. DWT (Discrete Wavelet Transform) based method can overcome such problems. In SAMCoW (Scalable Adaptive Motion Compensation Wavelet), one of wavelet based video coding algorithm, both intra frames and motion compensated error frames are encoded using EZW(Embedded Zerotree Wavelet) algorithm. However the property of wavelets transform coefficients of motion compensated error frames are different from that of still images. Signal energy is not highly concentrated in the lower bands which is true for most still image cases. Signal energy is rather evenly distributed over all frequency bands. This paper suggests a new video coding algorithm utilizing these properties. Spatial band coding which is known to be very effective for encoding images with relative1y high frequency components and not utilizing the interband coefficients correlation is applied instead of EZW to encode both intra and inter frames. In spatial band coding, the position and value of significant wavelet coefficients in each band are progressively transmitted. Unlike EZW, inter band coefficients correlations are not utilized in spatial band coding. It has been shown that spatial band coding gives better performance than EZW when applied to wavelet based video compression.

• Journal of Broadcast Engineering
• /
• v.15 no.6
• /
• pp.768-782
• /
• 2010

Because of the different shooting position between multi-view cameras and the imperfect camera calibration, Illumination mismatches of multi-view video can happen. This variation can bring about the performance decrease of multi-view video coding(MVC) algorithm. A histogram matching algorithm can be applied to recompensate these inconsistencies in a prefiltering step. Once all camera frames of a multi-view sequence are adjusted to a predefined reference through the histogram matching, the coding efficiency of MVC is improved. However the histogram distribution can be different not only between neighboring views but also between sequential views on account of movements of camera angle and some objects, especially human. Therefore the histogram matching algorithm which references all frames in chose view is not appropriate for compensating the illumination differences of these sequence. Thus we propose new algorithms both the image classification algorithm which is applied two criteria to improve the correlation between inter-view frames and the histogram matching which references and matches with a group of pictures(GOP) as a unit to advance the correlation between successive frames. Experimental results show that the compression ratio for the proposed algorithm is improved comparing with the conventional algorithms.

• Journal of Advanced Navigation Technology
• /
• v.22 no.1
• /
• pp.20-26
• /
• 2018

In this paper, we propose a moving object detection and tracking algorithm based on multi-frame feature point tracking information to reduce false positives. However, there are problems of detection error and tracking speed in existing studies. In order to compensate for this, we first calculate the corner feature points and the optical flow of multiple frames for camera movement compensation and object tracking. Next, the tracking error of the optical flow is reduced by the multi-frame forward-backward tracking, and the traced feature points are divided into the background and the moving object candidate based on homography and RANSAC algorithm for camera movement compensation. Among the transformed corner feature points, the outlier points removed by the RANSAC are clustered and the outlier cluster of a certain size is classified as the moving object candidate. Objects classified as moving object candidates are tracked according to label tracking based data association analysis. In this paper, we prove that the proposed algorithm improves both precision and recall compared with existing algorithms by using quadrotor image - based detection and tracking performance experiments.

• Design & Manufacturing
• /
• v.14 no.1
• /
• pp.8-14
• /
• 2020

In general, auto parts production assembly line is assembled and produced by automatic mounting by an automated robot. In such a production site, quality problems such as misalignment of parts (doors, trunks, roofs, etc.) to be assembled with the vehicle body or collision between assembly robots and components are often caused. In order to solve such a problem, the quality of parts is manually inspected by using mechanical jig devices outside the automated production line. Automotive inspection technology is the most commonly used field of vision, which includes surface inspection such as mounting hole spacing and defect detection, body panel dents and bends. It is used for guiding, providing location information to the robot controller to adjust the robot's path to improve process productivity and manufacturing flexibility. The most difficult weighing and measuring technology is to calibrate the surface analysis and position and characteristics between parts by storing images of the part to be measured that enters the camera's field of view mounted on the side or top of the part. The problem of the machine vision device applied to the automobile production line is that the lighting conditions inside the factory are severely changed due to various weather changes such as morning-evening, rainy days and sunny days through the exterior window of the assembly production plant. In addition, since the material of the vehicle body parts is a steel sheet, the reflection of light is very severe, which causes a problem in that the quality of the captured image is greatly changed even with a small light change. In this study, the distance between the car body and the door part and the door are acquired by the measuring device combining the laser slit light source and the LED pattern light source. The result is transferred to the joint robot for assembling parts at the optimum position between parts, and the assembly is done at the optimal position by changing the angle and step.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.27 no.9
• /
• pp.854-864
• /
• 2016

The use of small drone platform has become a popular topic in these days but its application for SAR operation has been little known due to the burden of the payload implementation. Drone platforms are distinguished from the conventional UAV system by the increased vulnerability to the turbulences, control-errors and poor motion stability. Consequently, sophisticated motion compensation may be required to guarantee the successful acquisition of high quality SAR imagery. Extremely limited power and mass budgets may prevent the use of additional hardwares for motion compensation and the difficulty of SAR focusing is further aggravated. In this paper, we have carried out a feasibility study of mico-SAR drone operation. We present the image acquisition results from the preliminary flight tests and a quality assessment is followed on the experimental SAR images. The in-flight motion errors derived from the unique drone movements are investigated and attempts have been made to compensate for the geometrical and phase errors caused by motions against the nominal trajectory. Finally, the successful operation of drone SAR system is validated through the focussed SAR images taken over test sites.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.1
• /
• pp.73-80
• /
• 2012

Recent research efforts have focused on combining high dynamic range imaging with super-resolution reconstruction to enhance both the intensity range and resolution of images. The processes developed to date start with a set of multiple-exposure input images with low dynamic range (LDR) and low resolution (LR), and require several procedural steps: conversion from LDR to HDR, SR reconstruction, and tone mapping. Input images captured with irregular exposure steps have an impact on the quality of the output images from this process. In this paper, we present a simplified framework to replace the separate procedures of previous methods that is also robust to different sets of input images. The proposed method first calculates weight maps to determine the best visible parts of the input images. The weight maps are then applied directly to SR reconstruction, and the best visible parts for the dark and highlighted areas of each input image are preserved without LDR-to-HDR conversion, resulting in high dynamic range. A new luminance control factor (LCF) is used during SR reconstruction to adjust the luminance of input images captured during irregular exposure steps and ensure acceptable luminance of the resulting output images. Experimental results show that the proposed method produces SR images of HDR quality with luminance compensation.

• Polymer(Korea)
• /
• v.35 no.4
• /
• pp.337-341
• /
• 2011

To expand the viewing angle of vertical alignment liquid crystal display (VA-LCD), a wide-band compensation film has been newly developed. VA-LCD needs a retardation film with improved oblique viewing property. The retardation film for VA-LCD has been fabricated by solvent casting and subsequent drawing triacetylcellulose (TAC) containing optical additives. Here, optical birefringence and wavelength dispersion of the retardation film strongly depend on the chemical structures of optical additives. Utilizing quantum mechanical computation, the polarizing anisotropy of retardation film was calculated with respect to additives. It is also realized that the wavelength dispersion of polarizing anisotropy depends on the type and location of substituent to the selected main isomer. When two propionates are substituted to the meta position of the selected main isomer, the wavelength dispersion of polarizing anisotropy shows the most gentle slop, which is well matched with the experimental results. The most gentle slop of wavelength dispersion means that the viewing angle characteristics of LCD are less influenced according to the wavelength of light source of LCD, and it's possible to make better image quality than the present level.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.13 no.3
• /
• pp.81-85
• /
• 2009

Purpose: The examination of nuclear medicine observes the change in accordance with the time elapsed in the same region purposed and there are many examinations to acquire the image during the same term. At this time, the same parameter should be applied. The hepatobiliary scan, lung scan etc, are the acquired examination in the divided time with a regular term. Pre-set time that is applied in continued next image is set in order to acquire the fixed counts. The same scan time should be applied for each image. This study will look for the rational plan and analyze the change of scan time in accordance with the time of the decision of scan time at examination that pre-set time is applied. Methods: The hapatobiliary scan that use the radio pharmaceutical $^{99m}Tc$-mebrofenin is choosed as compensation from Jan. 2009 to Mar. 2009 in the department of nuclear medicine in ASAN MEDICAL CENTER. Scan is started after 5 minutes from when 222 MBq (6 mCi) is injected to patient. We let patient stand up between both detectors, and possibly close to the front of detector. When scan time reach 10%, 25%, 50%, 75% of total scan time, we measured the expected total scan time. After finishing all of scan, we compared the total scan time and the expected total scan time, while image is acquiring. and we observed the change of scan time in accordance with radio activity by using phantom. Results: After starting scan, a difference of when scan time reach 10%, 25%, 50%, 75% of total scan time is that the biggest difference is 5 seconds on 10%. There statistically is difference between 25% (t:2.88, p<0.01) and 50% (t:2.05, p<0.01). Conclusions: When the same the scan time is applied in the examination that acquire the many frame, concluding the same scan time has a important effect on a quantitative analysis. Although method that decide the scan time after finish all of the examinations, there is a few problem to apply practical affairs. This may cause an inaccurate result on the examination that need a quantitative analysis. We think that operator should try to improve it. At least, after reach 50% of total scan time, deciding the total scan time mean that you can minimize error of a quantitative analysis caused by unmatched scan time from a gap of image.