Efficient Vehicle Detection and Orientation Estimation by Confusing Subsets Categorization
文献类型:会议论文
作者 | Li FM(李非墨)![]() ![]() ![]() ![]() ![]() |
出版日期 | 2017-05 |
会议日期 | 2016-12 |
会议地点 | 中国四川成都 |
关键词 | High Resolution Aerial Image Vehicle Detection Orientation Estimation |
英文摘要 | Aerial traffic surveillance requires algorithms that can accurately predict the locations and orientations of hundreds of vehicles in a large high resolution aerial image within seconds. Under this constraint, the classical cascaded detection framework based on boosting algorithms still remains an optimal choice. These methods, however, usually use many binary classifiers to enhance the localization performance resistant to orientation variances, which is not effective in distinguishing confusing orientations and subsets. This paper categorizes these confusing subsets automatically by analyzing the correlations between specific orientation angles and location deviations at local detection window regions, makes robust predictions on them by N-nary multi-class classifiers. This helps to reduce the required number of classifiers to less than half and improve both localization and orientation estimation accuracies, making it potential for additional speed optimization. |
源URL | [http://ir.ia.ac.cn/handle/173211/14580] ![]() |
专题 | 自动化研究所_综合信息系统研究中心 |
作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Li FM,Lan XS,Li SX,et al. Efficient Vehicle Detection and Orientation Estimation by Confusing Subsets Categorization[C]. 见:. 中国四川成都. 2016-12. |
入库方式: OAI收割
来源:自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。