arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1702.04292cs.CVcs.RO
收藏

整合视觉注意的三种机制实现主动视觉搜索

Integrating Three Mechanisms of Visual Attention for Active Visual Search

York University(约克大学)

Amir Rasouli, John K. Tsotsos

摘要:

机器人视觉搜索的算法可以受益于视觉注意方法的使用,以减少计算成本。在这里,我们描述了三种不同的视觉注意力机制可以集成和有效地用于提高搜索性能。第一个是视点选择,如之前已经提出的,使用概率占用网格表示上的贪婪搜索。第二种是使用直方图反投影方法的自上而下的基于对象的注意力,也在前面描述过。第三是视觉显著性。这是新颖的意义上说,它不是用作当前图像的感兴趣区域的方法,而是作为一种非组合形式的前瞻性搜索未来的视点选择。此外,在一个单一的框架内,这三个注意力计划的整合是独一无二的,以前没有研究过。我们研究我们提出的方法在场景中很少或没有关于环境的信息。通过对移动机器人的大量实验,我们表明,我们的方法通过减少所需的时间和动作数量来提高视觉搜索性能。

英文摘要:

Algorithms for robotic visual search can benefit from the use of visual attention methods in order to reduce computational costs. Here, we describe how three distinct mechanisms of visual attention can be integrated and productively used to improve search performance. The first is viewpoint selection as has been proposed earlier using a greedy search over a probabilistic occupancy grid representation. The second is top-down object-based attention using a histogram backprojection method, also previously described. The third is visual saliency. This is novel in the sense that it is not used as a region-of-interest method for the current image but rather as a noncombinatorial form of look-ahead in search for future viewpoint selection. Additionally, the integration of these three attentional schemes within a single framework is unique and not previously studied. We examine our proposed method in scenarios where little or no information regarding the environment is available. Through extensive experiments on a mobile robot, we show that our method improves visual search performance by reducing the time and number of actions required.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑