Seok-Wun Ha

A Novel Approach Using PCA and SVM for Face Detection

Nowadays, face detection and recognition have gained importance in security and information access. In this paper, an efficient method of face detection based on principal components analysis (PCA) and support vector machine (SVM) is proposed. It firsly filter the face potential area using statistical feature which is generated by analyzing local histogram distribution. And then, SVM classifier is used to detect face feature in the test image, SVM has great performance in classification task. PCA is used to reduce dimension of sample data. After PCA transform, the feature vectors, which are used for training SVM classifier, are generated. Our tests in this paper are based on CMU face database. The experimental results demonstrate that the proposed method is encouraging with a successful detection rate.

ROI Based Natural Image Retrieval Using Color and Texture Feature

Region of interest(ROI) plays an important role in image analysis. In this paper, an efficient approach for content based image retrieval combining both color and texture features using three ROIs is proposed. Firstly, segment image to three parts using K-means algorithm. Secondly, select three ROIs from the three parts and then extract color features and texture features of ROIs. The similarity of two images will be determined by the similarities between pairs of ROIs. The experimental results demonstrate that the proposed method is encouraging with a successful retrieval rate.

A Novel Approach of Face Detection based on Skin Color Segmentation and PCA

Nowadays, face detection and recognition have gained importance in security and information access. In this paper, an efficient method of face detection based on skin color segmentation and principal components analysis(PCA) is proposed. Firstly, segmenting image using color model to filter candidate faces roughly; And then Eye-analogue segments at a given scale are discovered by finding regions which are darker than their neighborhoods to filter candidate faces farther; at the end, PCA method is used to extract the relevant information in human faces.

A GDB-based real-time tracing tool for remote debugging of SoC programs

Since embedded systems based on System-on-a-Chip(SoC) have limited resources, debugging programs in such systems requires a remote debugging system that has enough resources. However, existing JTAG based remote debugging system that uses GDB in Linux environment does not provide tracing function, so it is hard to monitor the executions of SoC program in real time. This paper adds a tracing facility to existing GDB remote debugging system to provide a real time monitoring tool. To demonstrate a real time tracing of synthetic program, Intel a Xscale PXA series processor based target system is used.

Hardware-in-the-loop simulation platform for image-based object tracking method using small UAV

In this paper, a hardware-in-the loop simulation (HILS) platform is presented for verifying the image-based object tracking method adopted in the small Unmanned Aerial Vehicle (sUAV). The platform is constructed by image processing module, scene generation module, and flight control module. In the image processing module, the motion of target object is measured by using the speeded-up robust features (SURF) algorithm and the feature matching technique. And then, control command is provided to allow the target object to be tracked by sUAV automatically. The JMAVSIM software developed by PX4 dev-team is used in the proposed platform to simulate the flight of sUAV and provide virtual scene and flight data. Pixhawk based on PX4 firmware which is a popular flight control computer is used as flight control module in the proposed platform. Experimental results show that the object tracking method based on sUAV is effectively tested and evaluated in the proposed HILS platform.

The Visualization Tool of the Open-Source Based for Flight Waypoint Tracking

Flight Waypoint visualization of the aircraft is the system which in order to be solved is used the threat against a low altitude task and terrain altitude widely. But, in order to compose a system with GPS about lower, it is widely used with the restriction must construct terrain information where it is huge to it is difficult. In this paper, flight Waypoint and economically visualization Moving Map systems of the Open-Source based for it proposes. First, UDP it leads first from X-Plane and synthetic flight path information, it acquires demonstration and terrain altitude information from the delivery receiving Google Earth. Moving from map systems terrain altitude of altitude and the present location of the aircraft about under mapping from map sever it leads and Waypoint visualization at map information which it brings. Also, altitude comparison of the terrain altitude which it follows in time interval and the aircraft it leads and indicates the terrain location which has the dangerous characteristic of collision at the projected course the monitoring screen which it provides. The outgrowth of this paper in objective of the flight algorithm research back and the flight visualization field could be used flight Waypoint visualization with the economic tool.

Leopard Image Retrieval using Region of Interest and Texture Feature

In content based image retrieval system, texture based natural image retrieval can not extract texture feature efficiently and accurately, because the nature image is very complex and most of method extract feature use the whole nature image. In this paper, a new method is proposed for leopard texture image retrieval. Usually, the habitat of leopard is grass or tree, there is large difference between leopard image background and foreground, so it is easy to separate the leopard region from background using Canny edge detection, and then extract region of interest of foreground. The similarity of two images will be determined by the similarities between pairs of region of interest. The experimental results on the leopard texture image database demonstrate that the proposed method is encouraging with an average successful retrieval rate of 95.66%

A flight data storage system with efficient compression and enhanced security

In general, all kinds of aircrafts have the flight data storage systems such as DTS, Black-box and etc. Data to be stored in such equipment contains very important information that is related to the flight performance and security. For effective storing of the critical information that is included in the flight data, the compression or encryption is essentially required. In present, the flight data is stored without compression unlike voice data, but the compression and secure processing are needed to the efficient storing and the security of flight data in case of the fighter. In this paper, we propose a real-time data storage system that is composed of the compression of the flight and voice data based on DPCM, the encryption of the compressed data using AES encryption algorithm and the re-arrangement of the encrypted data by shuffling technique. The proposed system is implemented in hardware using Verilog HDL and we tested the performance of the system with the simulation flight and voice data. As a result, we found that the proposed system compress the data efficiently and enhances security characteristics.

Real-Time 3D Simulation for the Trawl Fishing Gear Based on Parallel Processing of Sonar Sensor Data

A huge and a complex internal computation is required to visualize the underwater geometry of a fishing gear, because each particle of the gear should be calculated with consideration of several force vectors, such as the movements of the fishing vessel, the buoyancy of the gear, and the tension of pulling or pursing acting on the net panels. The internal computation is the main drawback for providing a real-time visualization that takes into account the force vectors and the changes of underwater environments which can be obtained from the multiple sonar sensors. This paper presents a three-dimensional (3D) visualization tool that offers real-time simulations of the trawl fishing gear using parallel processing for the particles applying the force vectors. This tool also offers different underwater geometries for each fishing gear through a multiview display. The tool employs OpenMP APIs and OpenGL libraries to calculate in parallel the particles and to draw the underwater shapes of fishing gears, respectively. This work can be applied to other simulation systems for analyzing the precise model of graphical geometries as well as modeling the underwater shapes of fishing gears.

Efficient data transmission scheme for real-time operation of mission computer

In this paper, we propose an efficient data transmission scheme for the real-time operation of mission computers (MC). The amount of flight data transmitted to MC has gradually increased as the performance of aircraft has improved which makes it difficult to satisfy the real-time constraint required for the MC. In order to overcome this problem, we develop a new data format and transmission algorithm by investigating ARINC-429. The proposed scheme is verified by observing the performance on the test platform based on real-time OS. The experimental results show that the proposed scheme achieves a computational time gain of 13% and a transmission data gain of 34%. In addition, the proposed scheme will be useful for extending the life of MC without changing the existing H/W.