SegNet과 ResNet을 조합한 딥러닝에 기반한 횡단보도 영역 검출

목차 (Table of Contents)

• Abstract
• 초록
• 1. 서론
• 2. 연구방법과 네트워크 구조
• 3. 제안한 모델의 구조
• 4.모델 훈련과 실험결과
• 5. 결론
• References

참고문헌 (Reference)

1 Yang, M., "Zebracrossing automatic recognition and early warning for intelligent driving, International Journal of Signal Processing" 9 (9): 263-274, 2016

2 Mascetti, S., "ZebraRecognizer : Pedestrian crossing recognition for people with visual impairment or blindness" 60 : 405-419, 2016

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

4 Roters, J., "Recognition of traffic lights in live video streams on mobile devices" 21 (21): 1497-1511, 2011

5 Zhao, H., "Pyramid scene parsing network" 6230-6239, 2017

6 Fernandes, A. O., "Machine vision applications and development aspects" 1274-1278, 2011

7 Zhong, J., "Improved U-net for zebra-crossing image segmentation" 388-393, 2020

8 Taie, M. A., "ITS navigation and live timetables for the blind based on RFID robotic localization algorithms and ZigBee broadcasting" 139-144, 2013

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

10 Chen, L. -C., "DeepLab : Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs" 40 (40): 834-848, 2018

11 He, K., "Deep residual learning for image recognition" 770-778, 2016

12 Zhai, Y., "Crosswalk detection based on MSER and ERANSAC" 2770-2775, 2015