|
|
- 2018
基于错误式学习的低空影像人行横道多角度自动识别
|
Abstract:
提出了一种基于特征的错误式学习分类器半自动迭代训练方法，该分类器能够自动识别多角度低空影像上的人行横道线，在人行横道线管控与数据库建立、道路网提取上有较好的应用。介绍了基于错误式学习的分类器训练思路与方法，并提出了将同一地区不同角度低空影像的识别结果进行合并，从而尽可能全面的检测出被城区高楼以及车辆遮挡的人行横道线的思路。通过对比实验该方法的鲁棒性，并在其基础上随机选取多组数据进行系列实验，证实了基于错误式学习的分类器比传统方式训练的分类器有更好的综合性能，能够在不降低识别耗时的前提下产生高准确率、低漏检率和低误识别率的识别结果
| [1] | Lienhart R, Maydt J. An Extended Set of Haar-Like Features for Rapid Object Detection[C]. International Conference on Image Processing, Rochester, USA, 2002 |
| [2] | Schapire R E, Singer Y. Improved Boosting Algorithms Using Confidence-rated Predictions[J]. <em>Machine Learning</em>. 1999, 37(3):297-336 |
| [3] | Sichelschmidt S, Sichelschmidt S, Haselhoff A, et al. Pedestrian Crossing Detecting as a Part of an Urban Pedestrian Safety System[C]. IEEE Intelligent Vehicles Symposium (IV), La Jolla, USA, 2010 |
| [4] | Boudet L, Midenet S. Pedestrian Crossing Detection Based on Evidential Fusion of Video-sensors[J]. <em>Transportation Research Part C:Emerging Technologies</em>, 2009, 17(5):484-497 |
| [5] | Herumurti D, Uchimura K, Koutaki G, et al. Urban Road Network Extraction Based on Zebra Crossing Detection From a Very High Resolution RGB Aerial Image and DSM Data[C]. International Conference on Signal-Image Technology & Internet-Based Systems (SITIS), Kyoto, Japan, 2013 |
| [6] | Ishino Y, Saji H. Extraction of Road Markings from Aerial Images[C]. SICE Annual Conference, Tokyo, Japan, 2008 |
| [7] | OpenCV Team. OpenCV 2.4.9 Documentation, 2014[OL]. http://docs.opencv.org/modules/objdetect/doc/cascade_classification.html,2014 |
| [8] | Zhang Zuxun. From Digital Photogrammetry Workstation (DPW) to Digital Photogrammetry Grid (DPGrid)[J]. <em>Geomatics and Information Science of Wuhan University</em>, 2007, 32(07):565-571(张祖勋. 从数字摄影测量工作站(DPW)到数字摄影测量网格(DPGrid)[J]. 武汉大学学报·信息科学版, 2007, 32(07):565-571) |
| [9] | Zhang Yongjun, Xiong Jinxin, Hao Lijuan. Photogrammetric Processing of Low-altitude Images Acquired by Unpiloted Aerial Vehicles[J]. <em>The Photogrammetric Record</em>, 2011, 26(134):190-211 |
| [10] | Li Deren, Liu Likun, Shao Zhenfeng. An Integration of Aerial Oblique Photogrammetry and Mobile Mapping System for Urban Geographical Conditions Monitoring[J]. <em>Geomatics and Information Science of Wuhan University</em>, 2015, 40(04):427-435(李德仁,刘立坤,邵振峰. 集成倾斜航空摄影测量和地面移动测量技术的城市环境监测[J]. 武汉大学学报·信息科学版, 2015, 40(04):427-435) |
