Seung-Youn Lee

Modified component-labeling algorithms applied to grayscale images

In this paper, we proposed connected-component labeling algorithms applied to grayscale images. To develop the algorithms, three representative labeling algorithms for binary images which are raster-scan & label-equivalence-solving algorithm, searching & label propagation algorithms, and contour-tracing & label propagation algorithm are modified. The performance of these algorithms is evaluated in point of view of computational time consumption. Through the experiments, the advantages and disadvantages of each algorithm are compared. The modified algorithms and its results of test will be useful in labeling of various grayscale images and their applications.

Development of Target Signal Simulator for Multi-Beam Type FMCW Radar

To detect targets for autonomous navigation of unmanned ground vehicle, mounted sensors are required to work all-weather condition. In this point of view, the FMCW radar is quietly appropriate. In this paper, we present development results of target signal simulator for multi-beam type FMCW radar. A target signal simulator make pseudo target signals which simulates multiple moving targets. And we describe how to make hit information for each target in multi-beam type radar. The developed methods are utilized for target tracking device. Moreover it can be applied to similar target signal simulator.

A terrain classification method for UGV autonomous navigation based on SURF

The ability to navigate autonomously in off-road terrain is critical technology needed for unmanned ground vehicle (UGV). This paper presents a vision-based off-road terrain classification method that is robust despite environmental variation caused by weather changes. In order to cope with an overall image brightness variation, we use speeded-up robust features (SURF), and neural network classifier. Experimental results for real off-road images show that proposed method has a better performance than wavelet based one especially in case of large brightness variation.

A Range Estimation Algorithm for Anti-Aircraft Artillery

This paper proposes a range estimation algorithm for anti-aircraft artillery (AAA) which operated by man. The man is required to identify, acquire, and accurately track a maneuvering aircraft. However, the man brings to the AAA system various inherent limitations, such as reaction time delay and randomness, which limits his tracking ability thus missing measurement. To cope with these situations, an easy and efficient method is proposed that using preprocessing filters in the fire control system when the sensor data are frequently unreliable and missing. It computes probability matrix for state transition after modeling filter states as finite-state Markov chain, and computing false alarm and detection probability of each filter state under the measurement failure probability. The modified weighted least square method is used to estimate range according to preprocessing filters state. The simulation shows that the proposed algorithm is reasonable and appropriate when the sensor data have nonstationary characteristic

A Method of Fast Track Merging for Multi-Target Tracking under Heavy Clutter Environment

In this paper, we proposed a method of fast track merging which is the foundation of track to track association technique. The existing method of track merging is performed throughout comparison between tracks to tracks. Therefore, it has heavy calculation time. In our research, we developed a method for fast clustering by using nearest neighbor measurement identification. The simulation results show that the proposed method is more faster than previous method about 3.3%. We expect that this method could be effectively used in multi-target tracking particularly in heavy clutter environment.Keywords : Track Merging, Track-to-Track Association, Multi-Target Tracking, Clutter Environment

Vision Based Outdoor Terrain Classification for Unmanned Ground Vehicles

For effective mobility control of unmanned ground vehicles in outdoor off-road environments, terrain cover classification technology using passive sensors is vital. This paper presents a novel method far terrain classification based on color and texture information of off-road images. It uses a neural network classifier and wavelet features. We exploit the wavelet mean and energy features extracted from multi-channel wavelet transformed images and also utilize the terrain class spatial coordinates of images to include additional features. By comparing the classification performance according to applied features, the experimental results show that the proposed algorithm has a promising result and potential possibilities for autonomous navigation.