• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.49 no.1
• /
• pp.63-73
• /
• 2021

This paper presents a algorithm for automatic target recognition robust to the influence of the flame in order to track the target by EOTS(Electro-Optical Targeting System) equipped on UAV(Unmanned Aerial Vehicle) when there is aerial target or marine target with flame at the same time. The proposed method converts infrared images of targets and flames into a gradient vector field, and applies each gradient magnitude to a polynomial curve fitting technique to extract polynomial coefficients, and learns them in a shallow neural network model to automatically recognize targets and flames. The performance of the proposed technique was confirmed by utilizing the various infrared image database of the target and flame. Using this algorithm, it can be applied to areas where collision avoidance, forest fire detection, automatic detection and recognition of targets in the air and sea during automatic flight of unmanned aircraft.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.6
• /
• pp.1-15
• /
• 2009

In this paper, we have proposed an automated system that accurately measures the thickness and unbalanced wear of brake shoes, and the distance between brake shoes and wheels for travelling rolling stock. The images of brake shoes are captured automatically while rolling stock is passing by an inspection station. And in order to measure the thickness, etc. the locations of brake shoes are first determined because the locations are not the same in the captured image. Toward this goal, shadow regions between the brake shoes and wheels are utilized that are common in all captured images. The boundary of the shadow regions is modeled by an second order polynomial, and constrained curve fitting method is adopted to detect a curve (the initial curve) that passes through the regions. Then, three curves that correspond to the front, back of brake shoes and wheels, and a line that passes through the vertical surface of brake shoes are detected using the initial curve and intensity change information. Finally, the thickness, etc. are calculated using the detected curves and line, and experimental results showed that the brake shoe thickness was measured with an accuracy of 0.654mm.