检索结果-内蒙古大学图书馆

salient object segmentation via Effective Integration of Saliency and objectness

IEEE TRANSACTIONS ON MULTIMEDIA 2017年第8期19卷 1742-1756页

作者： Ye, Linwei Liu, Zhi Li, Lina Shen, Liquan Bai, Cong Wang, Yang Shanghai Univ Sch Commun & Informat Engn Shanghai 200444 Peoples R China Univ Manitoba Dept Comp Sci Winnipeg MB R3T 2N2 Canada Zhejiang Univ Technol Coll Comp Sci Hangzhou 311122 Zhejiang Peoples R China

This paper proposes an effective salient object segmentation method via the graph-based integration of saliency and objectness. Based on the superpixel segmentation result of the input image, a graph is built to represent superpixels using regular vertex, background seed vertex with the addition of a terminal vertex. The edge weights on the graph are defined by integrating the difference of appearance, saliency, and objectness between superpixels. Then, the object probability of each superpixel is measured by finding the shortest path from the corresponding vertex to the terminal vertex on the graph, and the resultant object probability map can generally better highlight salient objects and suppress background regions compared to both saliency map and objectness map. Finally, the object probability map is used to initialize salient object and background, and effectively incorporated into the framework of graph cut to obtain the final salient object segmentation result. Extensive experimental results on three public benchmark datasets show that the proposed method consistently improves the salient object segmentation performance and outperforms the state-of-the-art salient object segmentation methods. Furthermore, experimental results also demonstrate that the proposed graph-based integration method is more effective than other fusion schemes and robust to saliency maps generated using various saliency models.

关键词： Graph-based integration objectness map object probability salient object segmentation saliency map

来源：评论

学校读者我要写书评

暂无评论

salient object segmentation Based on Superpixel and Background Connectivity Prior

引用

IEEE ACCESS 2018年 6卷 56170-56183页

作者： Niu, Yuzhen Su, Chaoran Guo, Wenzhong Fuzhou Univ Coll Math & Comp Sci Fuzhou 350116 Fujian Peoples R China Fuzhou Univ Fujian Prov Key Lab Network Comp & Intelligent In Fuzhou 350116 Fujian Peoples R China Minist Educ Key Lab Spatial Data Min & Informat Sharing Fuzhou 350116 Fujian Peoples R China

salient object segmentation is well known for detecting and segmenting objects using saliency map as input. In this paper, we propose a salient object segmentation method which integrates saliency, superpixel, and background connectivity prior. First, our method extracts the superpixels of an image by the simple linear iterative clustering algorithm. Second, based on superpixel representation, we use background connectivity prior to characterize the spatial layout of each superpixel in a color space with respect to the image boundary. Third, considering both saliency and background connectivity values, we label four kinds of superpixel-level seeds and feed them to superpixel-level GrabCut method. Because superpixel representation generates only a few seeds, the optimization of GrabCut method converges fast. Finally, for further improvement, we crop a rectangular region which contains the segmented object obtained in the third step and apply GrabCut at the pixel level to produce the final segmentation result. Experimental results on eight typical datasets demonstrate that in terms of both performance and computational efficiency, the proposed segmentation method outperforms existing state-of-the-art methods.

关键词： Background connectivity prior GrabCut saliency map salient object segmentation superpixel

来源：评论

学校读者我要写书评

暂无评论

salient object segmentation based on depth-aware image layering

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2019年第9期78卷 12125-12138页

作者： Du, Huan Liu, Zhi Shi, Ran Shanghai Univ Shanghai Inst Adv Commun & Data Sci Shanghai 200444 Peoples R China Shanghai Univ Sch Commun & Informat Engn Shanghai 200444 Peoples R China Minist Publ Secur Res Inst 3 Technol Res & Dev Ctr Internet Things Shanghai 201204 Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing 210094 Jiangsu Peoples R China

This paper proposes an efficient salient object segmentation method via depth-aware image layering. First, based on the multiscale region segmentation results of an input color image, the depth consistency integration is utilized to generate the image pre-segmentation result. Then, under the guidance of the depth histogram division, the pre-segmented regions are divided into several different layers to differentiate salient object regions and background regions. Finally, an adaptive sample update and selection method based on layered image regions is used to select appropriate training samples for salient object segmentation. The depth information of the image is fully utilized in each step of the entire framework. Experimental results on two public datasets demonstrate that the proposed method achieves the better performance than the state-of-the-art depth-aware salient object segmentation methods.

关键词： Depth consistency integration Depth distribution Image layering Depth histogram Adaptive sample update and selection salient object segmentation

来源：评论

学校读者我要写书评

暂无评论

Focusing intermediate pixels loss for salient object segmentation

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2024年第7期83卷 19747-19766页

作者： Chen, Lei Cao, Tieyong Zheng, Yunfei Fang, Zheng Wang, Yang Fu, Bingyang Wang, Yekui Han, Tong Army Engn Univ PLA Nanjing 210007 Jiangsu Peoples R China PLA Army Acad Artillery & Air Def Hefei 230031 Anhui Peoples R China Key Lab Polarizat Imaging Detect Technol Hefei 230031 Anhui Peoples R China

To improve the network performance of salient object segmentation, many researchers modified the loss functions and set weights to pixel losses. However, these loss functions paid less attention to intermediate pixels of which the predicted probabilities lie in the intermediate region between correct and incorrect classification. To solve this problem, focusing intermediate pixels loss is proposed. Firstly, foreground and background are divided into correct and incorrect classified sets respectively to discover intermediate pixels which are difficult to determine the category. Secondly, the intermediate pixels are paid more attention according to the predicted probability. Finally, misclassified pixels are strengthened dynamically with the order of training epochs. The proposed method can 1) make the model focus on intermediate pixels that have more uncertainty;2) solve the vanishing gradient problem of Focal Loss for well-classified pixels. Experiment results on six public datasets and two different type of network structures show that the proposed method performs better than other state-of-the-art weighted loss functions and the average F-& beta;is increased by about 2.7% compared with typical cross entropy.

关键词： salient object segmentation Loss function Deep learning Intermediate pixels

来源：评论

学校读者我要写书评

暂无评论

SOSMaskFuse: An Infrared and Visible Image Fusion Architecture Based on salient object segmentation Mask

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2023年第9期24卷 10118-10137页

作者： Li, Guofa Qian, Xuanhu Qu, Xingda Chongqing Univ Coll Mech & Vehicle Engn Chongqing 400044 Peoples R China Shenzhen Univ Inst Human Factors & Ergon Coll Mechatron & Control Engn Shenzhen 518060 Guangdong Peoples R China

High-quality fusion images with infrared and visible information contribute to intelligent and safe driving. In the infrared and visible fusion images, the useless noise information in infrared image makes the fusion image unclear, which leads to the loss of texture information from visible image. In order to solve this problem, we propose a novel two-stage network (i.e., SOSMaskFuse) that can effectively reduce the noise and extract the important thermal information in infrared images as well as display sufficient texture details of visible images. In the first stage of this network, a salient object segmentation (SOS) network is proposed. Infrared images are fed into the SOS network to obtain the corresponding binarization mask of the region of interest. In the second stage, in each layer of features extracted by the encoder network, the newly proposed IMV-F (infrared mask visible fusion) fusion strategy uses the mask to decompose both infrared and visible images into infrared-foreground, visible-foreground, infrared-background and visible-background, and then fuses the foreground and background parts separately into fused-foreground and fused-background. Finally, the decoder network reconstructs the fused features into the final fused image. Compared with eighteen competitive algorithms on three public datasets, the experimental results indicate that our proposed network can produce high quality fused images with clear background texture information while highlighting infrared thermal information. Our proposed SOSMaskFuse generally outperforms the eighteen compared methods from both the quantitative and qualitative perspectives.

关键词： Intelligent transportation salient object segmentation image fusion visible image infrared image mask

来源：评论

学校读者我要写书评

暂无评论

Moving visual focus in salient object segmentation

引用

IET IMAGE PROCESSING 2015年第9期9卷 758-769页

作者： Chen, Zhi-Hua Liu, Yi Xiao, Xiao-Long Ying, Fang-Li Zhang, Jing Yuan, Yu-Bo E China Univ Sci & Technol Dept Comp Sci & Engn Shanghai 200237 Peoples R China Nanjing Univ State Key Lab Novel Software Technol Nanjing 210008 Jiangsu Peoples R China

Saliency detection plays an important role in image segmentation, object detection and retrieval, which attracts more attention in the field of computer vision recently. Most existing saliency detection algorithms have not considered the influence of visual focus (VF) shifting yet. In this study, a novel algorithm named moving region contrast (MRC) is proposed to analyse image saliency. The algorithm MRC is built on a novel concept of moving VF. The initial VF is defined as the geometric centre of the image. Then the VF is calculated iteratively by focus-moving technique where a saliency gravitation model is employed to determine the moving direction. The salient region is obtained according to the final VF. The experiments are conducted on the dataset with 1000 images released by Achanta. Experimental results show that the proposed algorithm achieves marked improvements in performance and outperforms other 11 popular algorithms.

关键词： image segmentation object detection computer vision image retrieval salient object segmentation image segmentation object detection object retrieval computer vision saliency detection algorithms visual focus shifting moving region contrast image saliency focus-moving technique saliency gravitation model

来源：评论

学校读者我要写书评

暂无评论

Unsupervised salient object segmentation Based on Kernel Density Estimation and Two-Phase Graph Cut

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2012年第4期14卷 1275-1289页

作者： Liu, Zhi Shi, Ran Shen, Liquan Xue, Yinzhu Ngan, King Ngi Zhang, Zhaoyang Shanghai Univ Sch Commun & Informat Engn Shanghai Peoples R China Shanghai Univ Minist Educ Key Lab Adv Display & Syst Applicat Shanghai Peoples R China Chinese Univ Hong Kong Dept Elect Engn Shatin Hong Kong Peoples R China

In this paper, we propose an unsupervised salient object segmentation approach based on kernel density estimation (KDE) and two-phase graph cut. A set of KDE models are first constructed based on the pre-segmentation result of the input image, and then for each pixel, a set of likelihoods to fit all KDE models are calculated accordingly. The color saliency and spatial saliency of each KDE model are then evaluated based on its color distinctiveness and spatial distribution, and the pixel-wise saliency map is generated by integrating likelihood measures of pixels and saliency measures of KDE models. In the first phase of salient object segmentation, the saliency map based graph cut is exploited to obtain an initial segmentation result. In the second phase, the segmentation is further refined based on an iterative seed adjustment method, which efficiently utilizes the information of minimum cut generated using the KDE model based graph cut, and exploits a balancing weight update scheme for convergence of segmentation refinement. Experimental results on a dataset containing 1000 test images with ground truths demonstrate the better segmentation performance of our approach.

关键词： Color saliency graph cut kernel density estimation saliency model salient object segmentation seed adjustment spatial saliency

来源：评论

学校读者我要写书评

暂无评论

Contour-Aware Loss: Boundary-Aware Learning for salient object segmentation

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2021年 30卷 431-443页

作者： Chen, Zixuan Zhou, Huajun Lai, Jianhuang Yang, Lingxiao Xie, Xiaohua Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou 510006 Peoples R China Sun Yat Sen Univ Guangdong Prov Key Lab Informat Secur Technol Guangzhou 510006 Peoples R China Sun Yat Sen Univ Minist Educ Key Lab Machine Intelligence & Adv Comp Guangzhou 510006 Peoples R China

We present a learning model that makes full use of boundary information for salient object segmentation. Specifically, we come up with a novel loss function, i.e., Contour Loss, which leverages object contours to guide models to perceive salient object boundaries. Such a boundary-aware network can learn boundary-wise distinctions between salient objects and background, hence effectively facilitating the salient object segmentation. Yet the Contour Loss emphasizes the boundaries to capture the contextual details in the local range. We further propose the hierarchical global attention module (HGAM), which forces the model hierarchically to attend to global contexts, thus captures the global visual saliency. Comprehensive experiments on six benchmark datasets show that our method achieves superior performance over state-of-the-art ones. Moreover, our model has a real-time speed of 26 fps on a TITAN X GPU.

关键词： object segmentation Feature extraction Visualization Semantics Image segmentation Decoding Aggregates salient object segmentation deep learning contour attention

来源：评论

学校读者我要写书评

暂无评论

Personalized image observation behavior learning in fixation based personalized salient object segmentation

引用

NEUROCOMPUTING 2021年 445卷 255-266页

作者： Shi, Ran Li, Gongyang Wei, Weijie Zhou, Xiaofei Liu, Zhi Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing Peoples R China Shanghai Univ Sch Commun & Informat Engn Shanghai Peoples R China Hangzhou Dianzi Univ Inst Informat & Control Sch Automat Hangzhou Peoples R China

Fixation as representation of one viewer's attention are very intuitive to reflect the viewer's observation procedure. The viewer's observation behavior can be further revealed by analyzing fixations features. In this paper, we propose a fixation based personalized salient object segmentation method involving personal observation behavior learning. Concretely, we design three neural networks and deploy a meta learning method. The first network is a base segmentation network that can be converted into a meta segmentation network by meta-learning. The meta-segmentation network can learn one viewer's observation behavior from only one sample and then generates the viewer's segmentation network to segment the other samples. Moreover, a fusion network plays an important role in alleviating an unsuitable transmission problem and generating a final segmentation result. The experimental results demonstrate the reasonability of our observation behavior learning and the effectiveness of the three proposed neural networks. (c) 2021 Elsevier B.V. All rights reserved.

关键词： Fixation salient object segmentation Meta-learning

来源：评论

学校读者我要写书评

暂无评论

SSG: superpixel segmentation and GrabCut-based salient object segmentation

引用

VISUAL COMPUTER 2019年第3期35卷 385-398页

作者： Zhou, Xianen Wang, Yaonan Zhu, Qing Xiao, Changyan Lu, Xiao Hunan Univ Natl Engn Lab Robot Visual Percept & Control Tech Changsha 410082 Hunan Peoples R China Hunan Normal Univ Changsha 410082 Hunan Peoples R China

Saliency detection is a popular topic for image processing recently. In this paper, we propose a simple, robust and fast salient object segmentation framework. Firstly, we develop a novel saliency map segmentation strategy, named SSG which consists of superpixel region growing, superpixel Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering and iterated graph cuts (GrabCut), where DBSCAN makes similar background regions cluster as a whole, region growing groups similar regions together as much as possible, GrabCut segments salient objects accurately. Then, the proposed SSG is combined with saliency detection to abstract salient objects. Experimental results on three benchmark datasets demonstrate that the proposed method achieves the favorable performance than many recent state-of-the-art methods in terms of precision, recall, F-measure and execution time.

关键词： salient object segmentation Superpixel segmentation GrabCut Region growing DBSCAN clustering

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：