目標(biāo)尺寸先驗與圖像抽象的顯著性檢測
發(fā)布時間:2019-07-05 07:33
【摘要】:為了均勻突出顯著目標(biāo)并抑制小尺寸顏色獨特的非顯著目標(biāo)對顯著性檢測的影響,研究了顯著目標(biāo)尺寸分布規(guī)律和多尺寸超像素抽象顯著目標(biāo)一致性,進(jìn)而提出了基于目標(biāo)尺寸先驗的多尺寸超像素抽象顯著性檢測方法.該方法針對不同超像素尺寸抽象圖計算圖像的顏色獨特性和顏色分布性,從局部和全局搜尋場景中的顯著目標(biāo),并以尺寸分布規(guī)律指導(dǎo)顯著目標(biāo)的分割提取.通過對大量公開數(shù)據(jù)集中的圖像進(jìn)行測試的結(jié)果表明,該方法在有效檢測顯著目標(biāo)的同時還能抑制小尺寸高對比度的非顯著目標(biāo)對顯著性檢測的影響,并生成均勻的高亮顯著圖.
文內(nèi)圖片:
圖片說明:圖1顯著目標(biāo)及其尺寸分布圖抽象的尺寸選擇和
[Abstract]:In order to uniformly highlight the significant target and suppress the influence of the non-significant target with unique small size color on the significance detection, the size distribution law of the significant target and the consistency of the multi-size super-pixel abstract significant target are studied, and then a multi-size super-pixel abstract significance detection method based on the target size priori is proposed. In this method, the color uniqueness and color distribution of images are calculated according to different super-pixel size abstract maps, and the significant targets in the scene are searched from local and global images, and the segmentation and extraction of significant targets is guided by the law of size distribution. The results of testing a large number of images in public data sets show that the method can not only effectively detect significant targets, but also suppress the influence of small size and high contrast non-significant targets on significance detection, and generate uniform highlighted images.
【作者單位】: 西安建筑科技大學(xué)信息與控制工程學(xué)院;西北工業(yè)大學(xué)電子信息學(xué)院;
【基金】:國家自然科學(xué)基金資助項目(61420106007)
【分類號】:TP391.41
本文編號:2510361
文內(nèi)圖片:
圖片說明:圖1顯著目標(biāo)及其尺寸分布圖抽象的尺寸選擇和
[Abstract]:In order to uniformly highlight the significant target and suppress the influence of the non-significant target with unique small size color on the significance detection, the size distribution law of the significant target and the consistency of the multi-size super-pixel abstract significant target are studied, and then a multi-size super-pixel abstract significance detection method based on the target size priori is proposed. In this method, the color uniqueness and color distribution of images are calculated according to different super-pixel size abstract maps, and the significant targets in the scene are searched from local and global images, and the segmentation and extraction of significant targets is guided by the law of size distribution. The results of testing a large number of images in public data sets show that the method can not only effectively detect significant targets, but also suppress the influence of small size and high contrast non-significant targets on significance detection, and generate uniform highlighted images.
【作者單位】: 西安建筑科技大學(xué)信息與控制工程學(xué)院;西北工業(yè)大學(xué)電子信息學(xué)院;
【基金】:國家自然科學(xué)基金資助項目(61420106007)
【分類號】:TP391.41
【相似文獻(xiàn)】
相關(guān)期刊論文 前5條
1 黃小紅;馬云;陳曾平;;利用RCS序列估計空間目標(biāo)尺寸的方法研究[J];信號處理;2005年06期
2 林慶;陳遠(yuǎn)祥;王士同;詹永照;;目標(biāo)窗口尺寸自適應(yīng)變化的Mean-Shift跟蹤算法[J];計算機(jī)應(yīng)用;2009年12期
3 羅山;黃歡;劉繼紅;丁大_8;;基于可變帶寬Mean Shift的目標(biāo)跟蹤[J];微型電腦應(yīng)用;2009年05期
4 劉旭東;郭東;白正勤;;利用尺寸特性的水面目標(biāo)性質(zhì)識別[J];計算機(jī)與數(shù)字工程;2011年12期
5 ;[J];;年期
,本文編號:2510361
本文鏈接:http://sikaile.net/kejilunwen/ruanjiangongchenglunwen/2510361.html
最近更新
教材專著