自动化学报
自動化學報
자동화학보
ACTA AUTOMATICA SINICA
2015年
4期
799-812
,共14页
显著性目标检测%层次估计%先验背景和前景%显著性中心加权%仿射传播聚类
顯著性目標檢測%層次估計%先驗揹景和前景%顯著性中心加權%倣射傳播聚類
현저성목표검측%층차고계%선험배경화전경%현저성중심가권%방사전파취류
Salient ob ject detection%hierarchical estimation%background and foreground prior%salient center weighting%a?nity propagation clustering
有效的显著性目标检测在计算机视觉领域一直是具有挑战性的问题。本文首先对图像进行树滤波处理，采用Quick shift 方法将其分解为超像素，再通过仿射传播聚类把超像素聚集为代表性的类。与以往方法不同，本文提出根据各类中拥有的超像素的类内和类间的空间离散程度及其位于图像边界的数目，自适应地估计先验背景，并提取条状背景区域；由目标性度量(Ob jectness measure)粗略地描述前景范围后，通过与各类之间的空间交互信息，估计先验前景；再经过连通区域优化前景与背景信息。最后，综合考虑各超像素与先验背景和前景在CIELab 颜色空间的距离，并进行显著性中心加权，得到显著图。在MSRA-1000和复杂的SOD 数据库上的实验结果表明，本文算法能准确、完整地检测出显著性目标，优于21种State-of-the-art算法，包括基于部分类似原理的方法。
有效的顯著性目標檢測在計算機視覺領域一直是具有挑戰性的問題。本文首先對圖像進行樹濾波處理，採用Quick shift 方法將其分解為超像素，再通過倣射傳播聚類把超像素聚集為代錶性的類。與以往方法不同，本文提齣根據各類中擁有的超像素的類內和類間的空間離散程度及其位于圖像邊界的數目，自適應地估計先驗揹景，併提取條狀揹景區域；由目標性度量(Ob jectness measure)粗略地描述前景範圍後，通過與各類之間的空間交互信息，估計先驗前景；再經過連通區域優化前景與揹景信息。最後，綜閤攷慮各超像素與先驗揹景和前景在CIELab 顏色空間的距離，併進行顯著性中心加權，得到顯著圖。在MSRA-1000和複雜的SOD 數據庫上的實驗結果錶明，本文算法能準確、完整地檢測齣顯著性目標，優于21種State-of-the-art算法，包括基于部分類似原理的方法。
유효적현저성목표검측재계산궤시각영역일직시구유도전성적문제。본문수선대도상진행수려파처리，채용Quick shift 방법장기분해위초상소，재통과방사전파취류파초상소취집위대표성적류。여이왕방법불동，본문제출근거각류중옹유적초상소적류내화류간적공간리산정도급기위우도상변계적수목，자괄응지고계선험배경，병제취조상배경구역；유목표성도량(Ob jectness measure)조략지묘술전경범위후，통과여각류지간적공간교호신식，고계선험전경；재경과련통구역우화전경여배경신식。최후，종합고필각초상소여선험배경화전경재CIELab 안색공간적거리，병진행현저성중심가권，득도현저도。재MSRA-1000화복잡적SOD 수거고상적실험결과표명，본문산법능준학、완정지검측출현저성목표，우우21충State-of-the-art산법，포괄기우부분유사원리적방법。
Effective salient object detection is still a challenging problem in computer vision. In this paper, images are processed by tree filter firstly. Then quick shift is adopted to decompose images into perceptually homogeneous superpixels. This is followed by using a?nity propagation clustering to aggregate all the superpixels into representative clusters. Different from previous methods, this paper proposes a novel adaptive background prior estimation strategy. The intra-cluster and inter-cluster spatial variances of superpixels owned by some cluster are calculated, and the numbers of superpixels located along the image boundary are counted to complete the processing. Also, the strip regions of background are extracted. The objectness measure is employed to get a coarse foreground scope, which is then used to compute the spatial interactive information with all the clusters, so as to get the foreground prior. After the optimization based on connected regions, A final foreground and background prior are confirmed. A saliency map is generated by measuring the differences of CIELab color space between all the superpixels and the background and foreground prior, enhanced by salient center weighting. Experimental results on MSRA-1000 and complicated SOD databases show that the proposed method can accurately detect the whole salient object. It is superior to the 21 state-of-the-art methods, including the methods partially based on similar principles.
