• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.56 no.1
• /
• pp.19-22
• /
• 2007

We developed a low cost digital X-Ray image capturing system using a CCD camera, instead of using the high cost image plate and image intensifier. In order to reduce the system volume, we directly made the dark box shorter than the previous model. Using the graphic language, we developed a program in order for post-processing the images captured by the CCD camera. This program improves the image resolving power.

• Journal of Information Processing Systems
• /
• v.14 no.3
• /
• pp.600-606
• /
• 2018

Smart city is currently the main direction of development. The automatic management of instrumentation is one task of the smart city. Because there are a lot of old instrumentation in the city that cannot be replaced promptly, how to makes low-cost transformation with Internet of Thing (IoT) becomes a problem. This article gives a low-cost method that can identify code wheel instrument information. This method can effectively identify the information of image as the digital information. Because this method does not require a lot of memory or complicated calculation, it can be deployed on a cheap microcontroller unit (MCU) with low read-only memory (ROM). At the end of this article, test result is given. Using this method to modify the old instrumentation can achieve the automatic management of instrumentation and can help build a smart city.

• ETRI Journal
• /
• v.43 no.4
• /
• pp.684-693
• /
• 2021

This paper presents a low-cost two-stage approximate multiplier for bfloat16 (brain floating-point) data processing. For cost-efficient approximate multiplication, the first stage implements Mitchell's algorithm that performs the approximate multiplication using only two adders. The second stage adopts the exact multiplication to compensate for the error from the first stage by multiplying error terms and adding its truncated result to the final output. In our design, the low-cost multiplications in both stages can reduce hardware costs significantly and provide low relative errors by compensating for the error from the first stage. We apply our approximate multiplier to the convolutional neural network (CNN) inferences, which shows small accuracy drops with well-known pre-trained models for the ImageNet database. Therefore, our design allows low-cost CNN inference systems with high test accuracy.

• Proceedings of the KSRS Conference
• /
• 1999.11a
• /
• pp.43-47
• /
• 1999

In this paper, we describe the configuration of the KITSAT-3 image data receiving, archiving, processing and distribution system in operation. Following the low-cost and software-based design concept, the whole system is composed of three PCs : two for data receiving, archiving and processing which provide a full dual-redundant configuration and one for image catalog browsing which can be accessed by public users. Except that receiving and archiving PCs have serial data ingest boards plugged in, they are configured by general peripherals. This basic and simple hardware configuration made it possible to show that a very low cost system can support a full ground operation for the utilization of high-resolution satellite image data.

• Journal of Information Processing Systems
• /
• v.1 no.1 s.1
• /
• pp.27-31
• /
• 2005

Vehicle detector system based on image processing technology is a significant domain of ITS (Intelligent Transportation System) applications due to its advantages such as low installation cost and it does not obstruct traffic during the installation of vehicle detection systems on the road[1]. In this paper, we propose architecture for vehicle detection by using image processing. The architecture consists of two main parts such as an image processing part, using high speed FPGA, decision and calculation part using CPU. The CPU part takes care of total system control and synthetic decision of vehicle detection. The FPGA part assumes charge of input and output image using video encoder and decoder, image classification and image memory control.

• Korean Journal of Remote Sensing
• /
• v.4 no.1
• /
• pp.31-40
• /
• 1988

Low-cost microcomputer systems can be assembled which possess computing power, color display, memory, and storage capacity approximately equal to graphic workstactions. A low-cost, flexible, and user-friendly IBM/PC/XT/AT based image processing system has been developed and named as KMIPS(KAIST (Korea Advanced Institute of Science & Technology) Map and Image Processing Station). It can be easily utilized by the resource managers who are not computer specialists. This system can: * directly access Landsat MSS and TM, SPOT, NOAA AVHRR, MOS-1 satellite imagery and other imagery from different sources via magnetic tape drive connected with IBM/PC; * extract image up to 1024 line by 1024 column and display it up to 480 line by 672 column with 512 colors simultaneously available; * digitize photographs using a frame grabber subsystem(512 by 512 picture elements); * perform a variety of image analyses, GIS and terrain analyses, and display functions; and * generate map and hard copies to the various scales. All raster data input to the microcomputer system is geographically referenced to the topographic map series in any rater cell size selected by the user. This map oriented, georeferenced approach of this system enables user to create a very accurately registered(.+-.1 picture element), multivariable, multitemporal data sets which can be subsequently subsequently subjected to various analyses and display functions.

• IEIE Transactions on Smart Processing and Computing
• /
• v.5 no.2
• /
• pp.143-151
• /
• 2016

This paper presents new prediction methods to improve compression performance of the so-called near-lossless RGB-domain image coder, which is designed to effectively decrease the memory bandwidth of a system-on-chip (SoC) for image processing. First, variable block size (VBS)-based intra prediction is employed to eliminate spatial redundancy for the green (G) component of an input image on a pixel-line basis. Second, inter-color prediction (ICP) using spectral correlation is performed to predict the R and B components from the previously reconstructed G-component image. Experimental results show that the proposed algorithm improves coding efficiency by up to 30% compared with an existing algorithm for natural images, and improves coding efficiency with low computational cost by about 50% for computer graphics (CG) images.

• Proceedings of the KSRS Conference
• /
• 1999.11a
• /
• pp.25-30
• /
• 1999

This paper covers the development of a highly portable and low cost SPOT image data receiving system. We followed two design approaches. One is the software-based approach by which most of the real-time processing is handled by software. With the complete software-based design, it is simple to add a function for receiving any additional satellite data. Satellite-specific format handlers including error correction, decompression and decryption can easily be accommodated. On the other approach. we used a general hardware platform, IBM-PC and a low cost SCSI RAID (Redundant Away of Independent Disks), and therefore, we can make a low cost system.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.6
• /
• pp.379-383
• /
• 2015

This paper presents an approach to detect object distance with the use of the recently developed low-cost Kinect sensor. The technique is based on Kinect color depth-image processing and can be used to design various computer-vision applications, such as object recognition, video surveillance, and autonomous path finding. The proposed technique uses keypoint feature detection in the Kinect depth image and advantages of depth pixels to directly obtain the feature distance in the depth images. This highly reduces the computational overhead and obtains the pixel distance in the Kinect captured images.

• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.1
• /
• pp.210-218
• /
• 2021

CNN (Convolutional Neural Network), a type of deep learning algorithm, is a type of artificial neural network used to analyze visual images. In deep learning, it is classified as a deep neural network and is most commonly used for visual image analysis. Accordingly, an AI autonomous driving model was constructed through real-time image processing, and a crosswalk image of a road was used as an obstacle. In this paper, we proposed a low-cost model that can actually implement autonomous driving based on the CNN model. The most well-known deep neural network technique for autonomous driving is investigated and an end-to-end model is applied. In particular, it was shown that training and self-driving on a simulated road is possible through a practical approach to realizing lane detection and keeping.