Sequence-level object candidates based on saliency for generic object recognition on mobile systems
Sequence-level object candidates based on saliency for generic object recognition on mobile systems
复制标题
DOI：
10.1109/icra.2015.7138990
复制
发表时间：
2015-05
期刊：
影响因子：
--
通讯作者：
Esther Horbert;Germán Martín García;S. Frintrop;B. Leibe
中科院分区：
文献类型：
--
作者：
Esther Horbert;Germán Martín García;S. Frintrop;B. Leibe
本文提出了一种新的生成通用候选对象的方法，用于连续单目视频中的对象发现和识别。这类候选者最近已成为一种流行的替代基于窗口的穷举搜索作为分类的基础。与以往的方法不同，我们在整个视频序列的级别上而不是在单个图像级别上解决候选生成问题。我们提出了一种处理流水线，从单个区域候选开始，并随着时间的推移跟踪他们。这使我们能够对相似对象的候选对象进行分组，并自动筛选出不一致的区域。对于每帧候选的生成，我们引入了一种新颖的多尺度显著度方法，与现有的最新方法相比，该方法实现了更高的每帧召回率和更少的候选。这两个组件加在一起，与帧级别方法相比，显著减少了候选对象的数量，同时保持了一致的高召回率。
In this paper, we propose a novel approach for generating generic object candidates for object discovery and recognition in continuous monocular video. Such candidates have recently become a popular alternative to exhaustive window-based search as basis for classification. Contrary to previous approaches, we address the candidate generation problem at the level of entire video sequences instead of at the single image level. We propose a processing pipeline that starts from individual region candidates and tracks them over time. This enables us to group candidates for similar objects and to automatically filter out inconsistent regions. For generating the per-frame candidates, we introduce a novel multi-scale saliency approach that achieves a higher per-frame recall with fewer candidates than current state-of-the-art methods. Taken together, those two components result in a significant reduction of the number of object candidates compared to frame level methods, while keeping a consistently high recall.