• Journal of Multimedia Information System
• /
• v.5 no.2
• /
• pp.131-138
• /
• 2018

This work describes a binary image based fast Difference of Gaussian (DoG) filter using zero-dimensional (0-d) convolution and state machine look up tables (LUTs) for image and video stitching hardware platforms. The proposed approach for using binary images to obtain DoG filtering can significantly reduce the data size compared to conventional gray scale based DoG filters, yet binary images still preserve the key features of the image such as contours, edges, and corners. Furthermore, the binary image based DoG filtering can be realized with zero-dimensional convolution and state machine LUTs which eliminates the major portion of the adder and multiplier blocks that are generally used in conventional DoG filter hardware engines. This enables fast computation time along with the data size reduction which can lead to compact and low power image and video stitching hardware blocks. The proposed DoG filter using binary images has been implemented with a FPGA (Altera DE2-115), and the results have been verified.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.1
• /
• pp.80-87
• /
• 2006

SONY corporation preoccupies $80\%$ of a market of the CCD used in a CCTV system. The CCD of SONY have high duality which can not follow the progress of capability. But there are some problems which differ the clock frequency used in CCD from the frequency used in common video encoder. To get the result by using common video encoder, the system needs a scaler that could adjust image size and PLL that synchronizes CCD's with encoder's clock So, this paper proposes the video encoder that is activated at equal clock used in CCD without scaler and PLL. The encoder converts ITU-R BT.601 4:2:2 or ITU-R BT.656 inputs from various video sources into NTSC or PAL signals in CVBS. Due to variable clock, property of filters used in the encoder is automatically changed by clock and filters adopt multiplier-free structures to reduce hardware complexity. The hardware bit width of programmable digital filters for luminance and chrominance signals, along with other operating blocks, are carefully determined to produce hish-quality digital video signals of ${\pm}1$ LSB error or less. The proposed encoder is experimentally demonstrated by using the Altera Stratix EP1S80B953C6ES device.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.11
• /
• pp.86-94
• /
• 2012

In this paper we propose a hardware architecture of high-speed CGH (computer generated hologram) generation processor, which particularly reduces the number of memory access times to avoid the bottle-neck in the memory access operation. For this, we use three main schemes. The first is pixel-by-pixel calculation rather than light source-by-source calculation. The second is parallel calculation scheme extracted by modifying the previous recursive calculation scheme. The last one is a fully pipelined calculation scheme and exactly structured timing scheduling by adjusting the hardware. The proposed hardware is structured to calculate a row of a CGH in parallel and each hologram pixel in a row is calculated independently. It consists of input interface, initial parameter calculator, hologram pixel calculators, line buffer, and memory controller. The implemented hardware to calculate a row of a $1,920{\times}1,080$ CGH in parallel uses 168,960 LUTs, 153,944 registers, and 19,212 DSP blocks in an Altera FPGA environment. It can stably operate at 198MHz. Because of the three schemes, the time to access the external memory is reduced to about 1/20,000 of the previous ones at the same calculation speed.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.11
• /
• pp.97-103
• /
• 2009

In this thesis, we discuss the implementation of parallel processing system which is able to get a high degree of efficiency(size, cost, performance and flexibility) by using $Nios^{(R)}$ II(32bit RISC(Reduced Instruction Set Computer) processor) embedded processor in DE2-$70^{(R)}$ reference board. The designed Parallel processing system is master-slave, shared memory and MIMD(Mu1tiple Instruction-Multiple Data stream) architecture with 4-processor. For performance test of system, N-point FFT is used. The result is represented speed-up as follow; in the case of using 2-processor(core), speed-up is shown as average 1.8 times as 1-processor's. When 4-processor, the speed-up is shown as average 2.4 times as it's.

• Journal of Korea Society of Industrial Information Systems
• /
• v.8 no.1
• /
• pp.83-91
• /
• 2003

High-speed QPSK demodulator has been in important design objective of any wireless communication systems, especially those offering broadband multimedia service. This paper describes all-digital QPSK demodulator for high-speed wireless communications, and its hardware structures are discussed. All-digital QPSK demodulator is mainly composed of symbol time circuit and carrier recovery circuit to estimate timing and phase-offsets. There are various schemes. Among them, we use Gardner algorithm and Decision-Directed carrier recovery algorithm which is most efficient scheme to warrant the fast acquisition and tacking to fabricate FPGA chip. The testing results of the implemented onto CPLD-EPF10K100GC 503-4 chip show demodulation speed is reached up to 2.6[Mbps]. If it is implemented a CPLD chip with speed grade 1, the demodulation speed can be faster by about 5 times. Actually in case of designing by ASIC, its speed my be faster than CPLD by 5 times. Therefore, it is possible to fabricate the all-digital QPSK demodulator chipset with speed of 50[Mbps].

• Journal of KIISE:Computer Systems and Theory
• /
• v.31 no.8
• /
• pp.453-464
• /
• 2004

In order to solve the well-known drawback of reduced flexibility that is associate with ASIC implementations, this paper proposes a novel arithmetic unit over GF(2$^{m}$ ) for field programmable gate arrays (FPGAs) implementations of elliptic curve cryptographic processor. The proposed arithmetic unit is based on the binary extended GCD algorithm and the MSB-first multiplication scheme, and designed as systolic architecture to remove global signals broadcasting. The proposed architecture can perform both division and multiplication in GF(2$^{m}$ ). In other word, when input data come in continuously, it produces division results at a rate of one per m clock cycles after an initial delay of 5m-2 in division mode and multiplication results at a rate of one per m clock cycles after an initial delay of 3m in multiplication mode respectively. Analysis shows that while previously proposed dividers have area complexity of Ο(m$^2$) or Ο(mㆍ(log$_2$$^{m}$ )), the Proposed architecture has area complexity of Ο(m), In addition, the proposed architecture has significantly less computational delay time compared with the divider which has area complexity of Ο(mㆍ(log$_2$$^{m}$ )). FPGA implementation results of the proposed arithmetic unit, in which Altera's EP2A70F1508C-7 was used as the target device, show that it ran at maximum 121MHz and utilized 52% of the chip area in GF(2$^{571}$ ). Therefore, when elliptic curve cryptographic processor is implemented on FPGAs, the proposed arithmetic unit is well suited for both division and multiplication circuit.