Multimodal Mixed Conditional Random Field Model for Category-Independent Object Detection | |
Jian-Hua Zhang; Jian-Wei Zhang; Sheng-Yong Chen; and Ying Hu | |
2012 | |
会议名称 | IEEE First International Conference on Cognitive Systems and Information Processing |
会议地点 | 中国 |
英文摘要 | Category-independent object detection is extremely useful for many robot vision tasks. Most existing methods rank a lot of regions by measuring their object-likeness. However, to obtain a sufficient object covering rate too many regions need to be sampled. In this paper, we present a novel method that directly detects and localizes category-independent objects. We develop a novel model which is named as “mixed robust higher-order conditional random field” model which combines 2D and 3D data into a uniform framework. A set of novel features is developed based on 2D and 3D saliency and oversegments. The potentials used in this model are computed from these features. Extensive experiments are carried out on a public RGB-D dataset. By comparison with state-ofthe- art ranking methods, the experimental results show the comparable performance of category-independent object detection without sampling a large number of extra regions. |
收录类别 | EI |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.siat.ac.cn:8080/handle/172644/3855] |
专题 | 深圳先进技术研究院_集成所 |
作者单位 | 2012 |
推荐引用方式 GB/T 7714 | Jian-Hua Zhang,Jian-Wei Zhang,Sheng-Yong Chen,et al. Multimodal Mixed Conditional Random Field Model for Category-Independent Object Detection[C]. 见:IEEE First International Conference on Cognitive Systems and Information Processing. 中国. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论