An Improved Approach for Object Proposals Generation

doi:10.3390/electronics10070794

	An Improved Approach for Object Proposals Generation
	Deng, Yao 1; Liang, Huawei 2; Yi, Zhiyan 3
刊名	ELECTRONICS
	2021-04-01
卷号	10
关键词	objectness detection fixation prediction salient object segmentation detection rate (DR)
DOI	10.3390/electronics10070794
通讯作者	Liang, Huawei(hwliang@iim.ac.cn)
英文摘要	The objectness measure is a significant and effective method used for generic object detection. However, several object detection methods can achieve accurate results by using more than 1000 candidate object proposals. In addition, the weight of each proposal is weak and also cannot distinguish object proposals. These weak proposals have brought difficulties to the subsequent analysis. To significantly reduce the number of proposals, this paper presents an improved generic object detection approach, which predicts candidate object proposals from more than 10,000 proposals. All candidate proposals can be divided, rather than preclassified, into three categories: entire object, partial object, and nonobject. These partial object proposals also display fragmentary information of the objectness feature, which can be used to reconstruct the object boundary. By using partial objectness to enhance the weight of the entire object proposals, we removed a huge number of useless proposals and reduced the space occupied by the true positive object proposals. We designed a neural network with lightweight computation to cluster the most possible object proposals with rerank and box regression. Through joint training, the lightweight network can share the features with other subsequent tasks. The proposed method was validated using experiments with the PASCAL VOC2007 dataset. The results showed that the proposed approach was significantly improved compared with the existing methods and can accurately detect 92.3% of the objects by using less than 200 proposals.
资助项目	National Key Research and Development Program of China[2020AAA0108103] ; National Key Research and Development Program of China[2016YFD0701401] ; National Key Research and Development Program of China[2017YFD0700303] ; National Key Research and Development Program of China[2018YFD0700602] ; Youth Innovation Promotion Association of the Chinese Academy of Sciences[2017488] ; Key Supported Project in the Thirteenth Five-year Plan of Hefei Institutes of Physical Science, Chinese Academy of Sciences[KP-2019-16] ; Natural Science Foundation of Anhui Province[1508085MF133] ; Technological Innovation Project for New Energy and Intelligent Networked Automobile Industry of Anhui Province
WOS研究方向	Computer Science ; Engineering ; Physics
语种	英语
出版者	MDPI
WOS记录号	WOS:000638349000001
资助机构	National Key Research and Development Program of China ; Youth Innovation Promotion Association of the Chinese Academy of Sciences ; Key Supported Project in the Thirteenth Five-year Plan of Hefei Institutes of Physical Science, Chinese Academy of Sciences ; Natural Science Foundation of Anhui Province ; Technological Innovation Project for New Energy and Intelligent Networked Automobile Industry of Anhui Province
内容类型	期刊论文
源URL	[http://ir.hfcas.ac.cn:8080/handle/334002/121807]
专题	中国科学院合肥物质科学研究院
通讯作者	Liang, Huawei
作者单位	1.Univ Sci & Technol China, Dept Automat, Hefei 230026, Peoples R China 2.Chinese Acad Sci, Hefei Inst Phys Sci, Hefei 230031, Peoples R China 3.Univ Utah, Dept Civil & Environm Engn, 110 Cent Campus Dr,RM 1650, Salt Lake City, UT 84112 USA
推荐引用方式 GB/T 7714	Deng, Yao,Liang, Huawei,Yi, Zhiyan. An Improved Approach for Object Proposals Generation[J]. ELECTRONICS,2021,10.
APA	Deng, Yao,Liang, Huawei,&Yi, Zhiyan.(2021).An Improved Approach for Object Proposals Generation.ELECTRONICS,10.
MLA	Deng, Yao,et al."An Improved Approach for Object Proposals Generation".ELECTRONICS 10(2021).