Automatic large-scale data acquisition via crowdsourcing for crosswalk classification: A deep learning approach

WHO: World Health Organization. Visual impairment and blindness. 2014. URL http://www.who.int/mediacentre/factsheets/fs282/en/. Ivanchenko, 2008, Detecting and locating crosswalks using a camera phone, 1 Wang, 2014, Rgb-d image-based detection of stairs, pedestrian crosswalks and traffic signs, J Vis Commun Image Represent, 25, 263, 10.1016/j.jvcir.2013.11.005 Riveiro, 2015, Automatic detection of zebra crossings from mobile LiDAR data, Opt Laser Technol, 70, 63, 10.1016/j.optlastec.2015.01.011 Ghilardi, 2016, Crosswalk localization from low resolution satellite images to assist visually impaired people, IEEE Comput Gr Appl, 10.1109/MCG.2016.50 Foucher, 2011, Detection and recognition of urban road markings using images, 1747 Berriel, 2017, Ego-Lane Analysis System (ELAS): Dataset and Algorithms, Image Vis Comput, 10.1016/j.imavis.2017.07.005 Berriel, 2017, Deep learning based large-scale automatic satellite crosswalk classification, IEEE Geosci Remote Sens Lett, 10.1109/LGRS.2017.2719863 Poggi, 2015, Crosswalk recognition through point-cloud processing and deep-learning suited to a wearable mobility aid for the visually impaired, 282 Ahmetovic, 2015, Zebra crossing spotter: automatic population of spatial databases for increased safety of blind travelers, 251 Hara, 2015, Characterizing and visualizing physical world accessibility at scale using crowdsourcing, computer vision, and machine learning, ACM SIGACCESS Access Comput, 13, 10.1145/2850440.2850442 Simonyan K., Zisserman A. Very deep convolutional networks for large-scale image recognition. 2014. Arxiv:1409.1556. Russakovsky, 2015, ImageNet large scale visual recognition challenge, Int J Comput Vis (IJCV), 115, 211, 10.1007/s11263-015-0816-y Glorot, 2010, Understanding the difficulty of training deep feedforward neural networks, 9, 249 Casella, 2002, 2 Chetlur S., Woolley C., Vandermersch P., Cohen J., Tran J., Catanzaro B., et al. cuDNN: efficient primitives for deep learning. 2014. Arxiv:1410.0759. Jia Y., Shelhamer E., Donahue J., Karayev S., Long J., Girshick R., et al. Caffe: convolutional architecture for fast feature embedding. 2014. Arxiv:1408.5093. Krizhevsky, 2012, ImageNet classification with deep convolutional neural networks, 1097 de Paula, 2014, Automatic on-the-fly extrinsic camera calibration of onboard vehicular cameras, Expert Syst Appl, 41, 1997, 10.1016/j.eswa.2013.08.096