편광 및 웨이블릿 변환을 이용한 도로 표면 상태의 화상 인식
임성한, 류승기, 윤여환 · 대한토목학회논문집 D · 2007
Road surface conditions vary with changes of the weather as snow, rain, dust, shadow, So proper measures can be helpful in improving traffic conditions and safety. This research focus on developing algorithm that classifies road surfaces into four different categories, dry, wet, icy, and snowy surfaces by analyzing asphalt-paved road images taken in daylight. By using the polarization coefficients, the proportions of horizontally polarized components to vertically polarized components, regions with over 1.3 polarization coefficients are classified as wet surfaces. Except for wet surfaces, the algorithm applies time-frequency analysis to other parts by using the third order wavelet packet transform. in addition, by using the average frequency characteristics of dry and icy surfaces from image templates, decide which is closer to a test image, and finally identify dry and icy surfaces. It is confirmed that the proposed algorithm works well on various images. This can be interpreted as an indication that image-only road surface condition supervision is probable.
Cited by 0 works.