완전 합성곱 신경망을 활용한 자동 포트홀 탐지 기술의 개발 및 평가

목차 (Table of Contents)

• 요약
• ABSTRACT
• Ⅰ. 서론
• Ⅱ. 완전 합성곱 신경망
• 1. 합성곱 신경망(Convolutional Neural Network, CNN)
• 2. 역합성곱 신경망(Deconvolutional Neural Network)
• 3. 배치 정규화(Batch Normalization) 및 활성화 함수(Activation Function)
• Ⅲ. 완전 합성곱 신경망을 활용한 자동 포트홀 탐지 기술
• 1. 학습 DB 생성
• 2. 신경망 구조
• Ⅳ. 성능결과 및 평가
• Ⅴ. 결론
• ACKNOWLEDGEMENTS
• REFERENCES

참고문헌 (Reference)

1 Han W., "Speech enhancement based on improved deep neural networks with MMSE pretreatment features" 2016

2 Badrinarayanan V., "SegNet: A deep convolutional encoder-decoder architecture for image segmentation" 39 (39): 2481-2495, 2017

3 Kim T., "Review and analysis of pothole detection methods" 5 (5): 603-608, 2014

4 Nair V., "Rectified linear units improve restricted boltzmann machines" 807-814, 2010

5 Mednis A., "Real time pothole detection using Android smartphones with accelerometers" 2011

6 Jo Y., "Pothole detection system using a black-box camera" 15 (15): 29316-29331, 2015

7 Krizhevsky A., "Imagenet classification with deep convolutional neural networks" 1097-1105, 2012

8 Long J., "Fully convolutional networks for semantic segmentation" 3431-3440, 2015

9 Ren S., "Faster R-CNN: towards real-time object detection with region proposal networks" 39 (39): 1137-1149, 2015

10 Yamada T., "Detection of road surface damage using mobile robot equipped with 2D laser scanner" 250-256, 2013

11 Eigen D., "Depth map prediction from a single image using a multi-scale deep network" 2366-2374, 2014

12 Goodfellow I., "Deep Learning" MIT Press 2016

13 Ioffe S., "Batch normalization: accelerating deep network training by reducing internal covariate shift" 448-456, 2015

14 Kingma D. P., "ADAM: a method for stochastic optimization" 1-15, 2015

15 Goutte C., "A probabilistic interpretation of precision, recall and F-score, with implication for evaluation" 345-359, 2005