주행 안전을 위한 joint deep learning 기반의 도로 노면 파손 및 장애물 탐지 알고리즘
Detection Algorithm of Road Damage and Obstacle Based on Joint Deep Learning for Driving Safety
0
조회
0
다운로드
5
인용
0
참고문헌
키워드
초록
인구의 감소 및 고령화 사회가 진행되면서 운전자의 평균 연령은 높아지게 된다. 그에 따라잠재적인 사고의 위험성이 높은 고령 운전자들은 자율 주행형 개인 이동체가 필요하게 된다. 이러한 이동체가 도로 주행 중에 안전성을 확보하기 위하여 여러 장애물에 대응할 기술이 요구된다. 그 중에서도 주행 중에 마주할 수 있는 차량, 자전거, 사람과 같은 동적 장애물뿐만아니라 도로 노면의 불량 상태와 같은 정적 장애물을 인식하는 기술이 가장 우선적으로 필요하다. 이를 위해서 본 논문에서는 두 종류의 장애물을 동시에 탐지할 수 있는 심층 신경망 알고리즘을 제안했다. 이 알고리즘을 개발하기 위해서 1,418장의 영상을 이용하여 7종의 동적 장애물에 표기한 annotation data와 도로 노면 파손을 표시한 label 영상을 확보했다. 이를 이용하여 학습한 결과, 46.22%의 평균 정확도로 동적 장애물을 탐지하고 74.71%의 mean intersection over union으로 도로 노면 파손을 탐지했다. 또한 한 장의 영상을 처리하는데 평균 소요시간은89ms로 일반 차량보다 느린 개인 이동 차량에 사용하기 적합한 알고리즘을 개발했다. 향후 주행 중 마주할 있는 도로 장애물을 탐지하는 기술을 활용하여 개인 이동 차량의 주행 안전성이향상되길 기대한다.
Abstract
As the population decreases in an aging society, the average age of drivers increases. Accordingly, the elderly at high risk of being in an accident need autonomous-driving vehicles. In order to secure driving safety on the road, several technologies to respond to various obstacles are required in those vehicles. Among them, technology is required to recognize static obstacles, such as poor road conditions, as well as dynamic obstacles, such as vehicles, bicycles, and people, that may be encountered while driving. In this study, we propose a deep neural network algorithm capable of simultaneously detecting these two types of obstacle. For this algorithm, we used 1,418 road images and produced annotation data that marks seven categories of dynamic obstacles and labels images to indicate road damage. As a result of training, dynamic obstacles were detected with an average accuracy of 46.22%, and road surface damage was detected with a mean intersection over union of 74.71%. In addition, the average elapsed time required to process a single image is 89ms, and this algorithm is suitable for personal mobility vehicles that are slower than ordinary vehicles. In the future, it is expected that driving safety with personal mobility vehicles will be improved by utilizing technology that detects road obstacles.
참고문헌 (37)
- Argyros A., "Semi-autonomous navigation of a robotic wheelchair", Journal of Intelligent and Robotic Systems, 34(3), pp.315~329 (2002)
- Bang S., "Encoder-decoder network for pixel-level road crack detection in black-box images", Computer Aided Civil and Infrastructure Engineering, 34(8), pp.713~727 (2019)
- Borowsky A., "Age, skill, and hazard perception in driving", Accident Analysis & Prevention, 42(4), pp.1240~1249 (2010)
- Buza E., "A pothole detection with image processing and spectral clustering", Proc. the 2nd International Conference on Information Technology and Computer Networks, pp.48~53 (2013)
- Chen L., "Driving scene perception network: Real-time joint detection, depth estimation and semantic segmentation", Proc. 2018 IEEE Winter Conference on Applications of Computer Vision(WACV), pp.1283~1291 (2018)
- Chen X., "3d object proposals using stereo imagery for accurate object class detection", IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(5), pp.1259~1272 (2017)
- "A guide to convolution arithmetic for deep learning, arXiv:1603.07285" (2016)[URL]
- Fayyad J., "Deep learning sensor fusion for autonomous vehicle perception and localization: A review", Sensors, 20(15), pp.4220~ (2020)
- Feng D., "Deep multi-modal object detection and semantic segmentation for autonomous driving: Datasets, methods, and challenges", IEEE Transactions on Intelligent Transportation Systems, 22(3), pp.1~20 (2020)
- Girshick R., "Fast r-cn", Proc. the IEEE International Conference on Computer Vision(ICCV), pp.1440~1448 (2015)
- Glorot X., "Understanding the difficulty of training deep feedforward neural networks", Proc. 13th International Conference on Artificial Intelligence and Statistics(AISTATS), pp.249~256 (2010)
- He K., "Mask r-cnn", Proc. the IEEE International Conference on Computer Vision(ICCV), pp.2961~2969 (2017)
- He K., "Deep residual learning for image recognition", Proc. the IEEE Conference on Computer Vision and Pattern Recognition(CVPR), pp.770~778 (2016)
- Ilas C., "Electronic sensing technologies for autonomous ground vehicles: A review", Proc. 8th International Symposium on Advanced Topics in Electrical Engineering(ATEE), pp.1~6 (2013)
- Jenkins M. D., "A deep convolutional neural network for semantic pixel-wise segmentation of road and pavement surface cracks", Proc. 26th European Signal Processing Conference(EUSIPCO), pp.2120~2124 (2018)
- Jo Y., "Pothole detection based on the features of intensity and motion", Journal of the Transportation Research Board, (2595), pp.18~28 (2016)
- "Adam: A method for stochastic optimization, arXiv:1412.6980" (2014)[URL]
- Kobayashi Y., "Robotic wheelchair based on observations of people using integrated sensors", Proc. 2009 IEEE, 2009, 2013~2018
- Koch C., "Pothole detection in asphalt pavement images", Advanced Engineering Information, 25(1), pp.507~515 (2011)
- Li P., "Stereo vision-based semantic 3d object and ego-motion tracking for autonomous driving", Proc. the European Conference on Computer Vision(ECCV), pp.646~661 (2018)
- Li P., "Stereo r-cnn based 3d object detection for autonomous driving", Proc. the IEEE, 2019, 7644~7652
- Liu W., "Ssd: Single shot multibox detector", Proc. European Conference on Computer Vision (ECCV), pp.21~37 (2016)
- Madli R., "Automatic detection and notification of potholes and humps on roads to aid drivers", IEEE Sensors Journal, 15(8), pp.4313~4318 (2015)
- Maeda H., "Road damage detection and classification using deep neural networks with smart phone images", Computer-Aided Civil and Infrastructure Engineering, 33(12), pp.1127~1141 (2018)
- Muramatsu N., "Japan: Super-aging society preparing for the future", The Gerontologist, 51(4), pp.425~432 (2011)
- Nakane J., "Elder care in Japan", Perspectives(Gerontological Nursing Association(Canada)), 28(1), pp.17~24 (2004)
- "Yolov3: An incremental improvement, arXiv:1804.02767" (2018)[URL]
- "Faster r-cnn: Towards real-time object detection with region proposal networks, arXiv:1506.01497" (2015)[URL]
- Ronneberger O., "U-net: Convolutional networks for biomedical image segmentation", Proc. International Conference on Medical Image Computing and Computer-Assisted Intervention(MICCAI), pp.234~241 (2015)
- Shi Y., "Automatic road crack detection using random structured forests", IEEE Transactions on Intelligent Transportation Systems, 17(12), pp.3434~3445 (2016)
- Shim S., "Lightweight semantic segmentation for road-surface damage recognition based on multiscale learning", IEEE Access, 8, pp.102680~102690 (2020)
- Critical reasons for crashes investigated in the national motor vehicle crash causation survey, "Singh S.", National Center for Statistics and Analysis, ~, pp.Traffic Safety Facts Crash Stats. Report No. DOT HS 812 115 (2015)
- "Real-time joint object detection and semantic segmentation network for automated driving, arXiv:1901.03912" (2019)[URL]
- Tinnila M., "Impact of future trends on personal mobility services", International Journal of Automotive Technology and Management, 15(4), pp.401~417 (2015)
- Zhang S., "Single-shot refinement neural network for object detection", Proc. the IEEE, 2018, 4203~4212
- Zhao Q., "M2det: A single-shot object detector based on multi-level feature pyramid network", Proc. the AAAI Conference on Artificial Intelligence, 33(1), pp.9259~9266 (2019)
- Zou Q., "DeepCrack: Learning hierarchical convolutional features for crack detection", IEEE Transactions on Image Processing, 28(3), pp.1498~1512 (2019)