Abstract
Cracks are among the most commonly found road surface degradations, requiring periodical road surveys for monitoring pavement quality. Images of road pavement surface can be automatically processed, typically employing segmentation algorithms to identify cracks. However, a set of distinct connected components often result, leading to the detection of several independent crack segments, although they may belong to the same pavement surface defect. This is often observed for cracks that exhibit a longer linear development or present several branches. This paper presents a new strategy to identify cracks on images captured during road pavement surveys, even when those cracks appear with a complex shape. The proposed crack segmentation algorithm includes two stages: (i) selection of prominent “crack seeds”, adopting an efficient segmentation procedure, after appropriate image smoothing, minimizing the detection of false positives; (ii) iterative binary pixel classification, into the crack or non-crack classes, extendingthe “seeds” to identify the complete crack shape. The paper also tests the combination of the proposed two stage crack segmentation with three smoothing techniques, to evaluate their suitability for crack detection. As a final step the system classifies the identified cracks as longitudinal, transversal or miscellaneous types. Tests performed with images acquired from different types of sensors (active and non-active), show improved crack segmentation results.
균열은 가장 흔히 발견되는 도로 문제이며 정기적인 조사가 필요하다.
도로 이미지는 균열을 식별하는 segmentation 알고리즘을 사용하여 자동적으로 프로세스화 할 수 있다.
그러나 동일한 포장 표면 결함에 속할지라도, 서로 다른 균열일 수 있다.
이러한 현상은 여러 갈래로 쪼개져 있거나 긴 균열에서 주로 발생한다.
이 논문은 도로 조사기간에 모아진 이미지들에 나타나는, 복잡한 모양을 포함한 균열을 인식하는 새로운 전략을 제시한다.
2가지 단계로 이루어져 있다.
- 적절한 image smoothing 적용 후 false positive를 최소화하는 효율적인 segmentation procedure를 채택하는 crack seed 선택
- crack, non-crack class로 이루어진 binary-pixel classification을 진행하여 seed를 확장하여 균열 모양 식별.
균열 탐지에 대한 안정성을 평가하기 위해 3가지 smoothing 기법에 새로 제안한 2가지 단계를 혼합시켰다.
최종 단계로서 시스템은 종, 횡 또는 기타 균열로 분류한다.
active, non-active로 이루어진 이미지로 테스트하였으며 향상된 결과를 도출했다.
Reference
Oliveira, H., & Correia, P. L. (2017). Road surface crack detection: Improved segmentation with pixel-based refinement. In 2017 25th European Signal Processing Conference (EUSIPCO) (pp. 2026-2030). IEEE.
'# Paper Abstract Reading' 카테고리의 다른 글
| Distilling the Knowledge in a Neural Network (0) | 2019.05.25 |
|---|---|
| Reverse Classification Accuracy: Predicting Segmentation Performance in the Absence of Ground Truth (0) | 2019.05.20 |
| Deep Photo Style Transfer (0) | 2019.04.15 |
| Playing Atari with Deep Reinforcement Learning (0) | 2019.04.14 |
| Neural Turing Machines (0) | 2019.04.13 |