• Journal of Korean Institute of Industrial Engineers
• /
• v.24 no.3
• /
• pp.397-406
• /
• 1998

The purpose of this research is to develop an integrated quality inspection system using machine vision technology in the automotive engine assembly process. The system makes it possible for the inspected data to be entered directly from the machine vision system into the developed system without the need for intermediate operations. Such direct entry enables prompt corrective actions against process problems. An IVP-150 machine vision board is installed an the PC for image processing, and a template matching technology is implemented to precisely verify quality factors. The developed system is successfully installed in a manufacturing process, and it showed robustness to the problems of noise, distortion, and orientation.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.280-282
• /
• 2003

The downlink data rates of the space-born payloads such as high-resolution optical cameras, synthetic aperture radars (SAR) and hyper-spectral sensors are being rapidly increased. For example, the image transmission rates of KOMPSAT-2 MSC(Multi-Spectral Camera) is 320Mbps even if on-board image compression scheme is used.[1] In the near future, the data rates are expected to be a level 500${\sim}$600Mbps because the required resolution will be higher and the swath width will be increased. This paper describes many techniques they enable 500Mbps data receiving and archiving system.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.36.4-36
• /
• 2001

A robust and reliable path recognition system is one necessary component for the autonomous navigation of a mobile robot to help determining its current position in its navigation map. This paper describes a computer visual path-recognition system using on-board video camera as vision-based driving assistance for an autonomous navigation mobile robot. The common problem for a visual system is that its reliability was often influenced by different lighting conditions. Here, two different image processing methods for the path detection were developed to reduce the effect of the luminance: one is based on the RGB color model and features of the path, another is based on the HSV color model in the absence of luminance.

• Korean Journal of Remote Sensing
• /
• v.18 no.5
• /
• pp.281-289
• /
• 2002

Although EOC data have been frequently used in several applications since the launch of the KOMPSAT-1 satellite in 1999, its radiometric characteristics are not clear due to the inherent limitations of the on-board calibration system. The radiometric characteristics of remotely sensed imagery can be measured by the sensitivity of radiant flux coming from various surface features on the earth. The objective of this study is to analyze the radiometric characteristics of EOC data by simulating the sensor- received radiance. Initially, spectral reflectance values of reference targets were measured on the ground by using a portable spectre-radiometer at the EOC spectrum. A radiative transfer model, LOWTRAN, then simulated the sensor-received radiance values of the same reference target. By correlating the digital number (DN) extracted from the EOC image to the corresponding radiance values simulated from LOWTRAN, we could find the radiometric calibration coefficients for EOC image. The radiometric gain coefficients of EOC are very similar to those of other panchromatic optical sensors.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.12
• /
• pp.1742-1745
• /
• 2019

Hidden flame detection after allegedly extinguishing a fire cannot be emphasized enough. There are a few commercial hidden fire detection equipments which are imported, but the cost is relatively high. In this contribution, we propose a development of a low-cost, high-performance hidden flame detector using open-source hardware/software. We use Raspberry-pi based hardware board equipped with a TFT touch-screen LCD, a 3G modem, and an attachable battery device altogether integrated in a plastic case fabricated with a 3D printer. The proposed hidden flame detector shows the same performance of a commercial product FLIR E5 while consuming less than a half of the cost.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.3
• /
• pp.101-108
• /
• 2023

Optimizing the performance of deep neural networks on embedded systems is a challenging task that requires efficient compilers and runtime systems. We propose a TVM-based approach that consists of three steps: quantization, auto-scheduling, and ahead-of-time compilation. Our approach reduces the computational complexity of models without significant loss of accuracy, and generates optimized code for various hardware platforms. We evaluate our approach on three representative CNNs using ImageNet Dataset on the NVIDIA Jetson AGX Xavier board and show that it outperforms baseline methods in terms of processing speed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.10
• /
• pp.2443-2450
• /
• 2014

In the motion recognition system using depth image, the depth image is converted to the real world formed 3D point cloud data for efficient algorithm apply. And then, output depth image is converted by the projective world after algorithm apply. However, when coordinate conversion, rounding error and data loss by applied algorithm are occurred. In this paper, when convert 3D point cloud data to depth image, we proposed efficient conversion method and its hardware implementation without rounding error and data loss according image size change. The proposed system make progress using the OpenCV and the window program, and we test a system using the Kinect in real time. In addition, designed using Verilog-HDL and verified through the Zynq-7000 FPGA Board of Xilinx.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.2
• /
• pp.239-247
• /
• 2007

In this paper, we propose a system that the Linux is ported in embedded system with peripheral devices of CIS(CMOS Image Sensor) and GPS module. The system acquires GGA sentence from GPS module by recognizing camera and GPS is used module in Linux kernel. And then the received location information is used to include still image acquired through CIS According to this paper, We compose hardware for embedded system, attach board (including camera), port Linux BootLoader and Kernel. And. then we realize that it insert kernel in CIS control device driver and GPS module device driver.

• Proceedings of the KSRS Conference
• /
• 1999.11a
• /
• pp.375-380
• /
• 1999

Ocean Scanning Multispectral Imager (OSMI) is a payload on the KOMPSAT satellite to perform worldwide ocean color monitoring for the study of biological oceanography. The instrument images the ocean surface using a wisk-broom motion with a swath width of 800 km and a ground sample distance (GSD) of<1km over the entire field of view (FOV). The instrument is designed to have an on-orbit operation duty cycle of 20% over the mission lifetime of 3 years with the functions of programmable gain/offset and on-board image data compression/storage. The instrument also performs sun and dark calibration for on-board instrument calibration. The OSMI instrument is a multi-spectral imager covering the spectral range from 400nm to 900nm using CCD Focal Plane Array (FPA). The ocean colors are monitored using 6 spectral channels that can be selected via ground commands. KOMPSAT satellite with OSMI was integrated and the satellite level environment tests and instrument aliveness/functional test as well, such as launch environment, on-orbit environment (Thermal/vacuum) and EMl/EMC test were performed at KARI. Test results met the requirements and the OSMI data were collected and analyzed during each test phase. The instrument is launched on the KOMPSAT satellite in the late 1999 and the image is scheduled to start collecting ocean color data in the early 2000 upon completion of on-orbit instrument checkout.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.7
• /
• pp.1-8
• /
• 2020

In this paper, we present an implementation of high speed image data transfer using XDMA for a video signal generation / acquisition device developed as a military test equipment. The technology proposed in this study obtains efficiency by replacing the method of copying data using the system buffer in the kernel area with the transmission and reception through the DMA engine in the FPGA. For this study, the device was developed as a PXIe platform in consideration of life cycle, and performance was maximized by using a low-cost FPGA considering mass productivity. The video I/O board implemented in this paper was tested by changing the AXI interface clock frequency and link speed through the existing memory copy method. In addition, the board was constructed using the DMA engine of the FPGA, and as a result, it was confirmed that the transfer speed was increased from 5~8Hz to 140Hz. The proposed method will contribute to strengthening defense capability by reducing the cost of device development using the PXIe platform and increasing the technology level.