.png){kind=icon}
.png){kind=icon}
Return
Multi-scale energy optimization for object proposal generation
.png){kind=icon}
PRE
AI
DOI：10.1007/s11042-016-3616-7.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In this paper, we present an object proposal generation method by applying energy optimization into superpixel merging algorithms in a multiscale framework, which could generate possible object locations in one image. As images in object detection datasets always enjoy high diversity, we adopt two different energy functions with multi-scales. Thus, our method enjoys the strength of global search, which is strong in locating salient object by concerning the whole image at one merge iteration, as well as the strength of local search which is more likely to recall the un-salient instances. What's more, unlike most superpixel merging algorithms that are based on diversified segmentation results, our approach takes advantage of robust edge detection and segments each image only once, which greatly reduces the number of proposals. Experiments on PASCAL VOC 2007 test set show that the proposed method outperforms most previous superpixel merging based methods and also could compete with state-of-the-art proposal generators.
Keywords:
Object proposal
Multi scales
Saliency
Superpixel merging
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3
Papers:
1.9W
Citations:
3.2W