检索结果-内蒙古大学图书馆

World Summit on Genetic and Evolutionary Computation (GEC 09)

作者： Zhang, Qian Liu, Suxing An, Ping Zhang, Zhaoyang Shanghai Univ Sch Commun & Informat Engn Minist Educ Shanghai Peoples R China

ISBN: (纸本)9781605583266

object segmentation plays an important role in multi-view video analysis. In this paper, we present a new object segmentation method for multi-view video in which only the disparity is used for segmentation and the motion estimation is neglected. Firstly, a modified locally adaptive support-weight approach is proposed for disparity estimation. Then, segmentation is realized by mean-shift algorithm. The experimental results show that proposed method could segment the semantically meaningful objects from complex background with high precision.

关键词： Disparity estimation locally adaptive support-weight approach object segmentation

来源：评论

学校读者我要写书评

暂无评论

Real-time object segmentation based on convolutional neural network with saliency optimization for picking

引用

Journal of Systems Engineering and Electronics 2018年第6期29卷 1300-1307页

作者： CHEN Jinbo WANG Zhiheng LI Hengyu School of Mechatronic Engineering and Automation Shanghai University

This paper concerns the problem of object segmentation in real-time for picking system. A region proposal method inspired by human glance based on the convolutional neural network is proposed to select promising regions, allowing more processing is reserved only for these regions. The speed of object segmentation is significantly improved by the region proposal *** the combination of the region proposal method based on the convolutional neural network and superpixel method, the category and location information can be used to segment objects and image redundancy is significantly reduced. The processing time is reduced considerably by this to achieve the real time. Experiments show that the proposed method can segment the interested target object in real time on an ordinary laptop.

关键词： convolutional neural network object detection object segmentation superpixel saliency optimization

来源：评论

学校读者我要写书评

暂无评论

Higher-order potentials for video object segmentation in bilateral space

引用

NEUROCOMPUTING 2020年 401卷 28-35页

作者： Hao, Chuanyan Chen, Yadang Yang, Zhi-Xin Wu, Enhua Nanjing Univ Posts & Telecommun Sch Educ Sci & Technol Nanjing 210023 Peoples R China Univ Macau State Key Lab Internet Things Smart City Macau 999078 Peoples R China Univ Macau Dept Electromech Engn Macau 999078 Peoples R China Univ Macau Fac Sci & Technol Taipa 999078 Macau Peoples R China

We propose an effective approach to make segmentation for objects in videos with an initial input of the object masks in a few frames of the source video. In this method, we cast the segmentation task as a Markov Random Field (MRF) labeling problem. Different from the conventional MRF models, our model uses an additional term of higher-order potential to better propagate the global consistency among frames. The higher-order potential presented in this paper is significant for the proposed method because of its capability to keep the long-range consistency during segmentation. In order to make the MRF energy minimized, we also introduce a smart skill that makes the intractable higher-order potential "invisible" during the optimization so that the problem can be solved simply by applying a standard graph cut algorithm. Besides, the entire process is operated in a bilateral space, where the labeling can be inferred efficiently on the vertices that are sampled regularly from the bilateral grid. The results of a comparison of our method with a number of recently developed methods show that it performs favorably against state-of-the-art algorithms on multiple benchmark data sets in view of accuracy and achieves a much faster runtime performance. (C) 2020 Published by Elsevier B.V.

关键词： Video object segmentation Markov random field Higher-order Bilateral space

来源：评论

学校读者我要写书评

暂无评论

Joint key-frame extraction and object segmentation for content-based video analysis

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2006年第7期16卷 904-914页

作者： Song, Xiaomu Fan, Guoliang Northwestern Univ Evanston IL 60208 USA Oklahoma State Univ Sch Elect & Comp Engn Stillwater OK 74078 USA

Key-frame extraction and object segmentation are usually implemented independently and separately due to the fact that they are on different semantic levels and involve different features. In this work, we propose a joint key-frame extraction and object segmentation method by constructing a unified feature space for both processes, where key-frame extraction is formulated as a feature selection process for object segmentation in the context of Gaussian mixture model (GMM)-based video modeling. Specifically, two divergence-based criteria are introduced for key-frame extraction. One recommends key-frame extraction that leads to the maximum pairwise interclass divergence between GMM components. The other aims at maximizing the marginal divergence that shows the intra-frame variation of the mean density. The proposed methods can extract representative key-frames for object segmentation, and some interesting characteristics of key-frames are also discussed. This work provides a unique paradigm for content-based video analysis.

关键词： cluster divergence feature selection Gaussian mixture model key-frame extraction object segmentation

来源：评论

学校读者我要写书评

暂无评论

Evaluation and modeling of depth feature incorporated visual attention for salient object segmentation

引用

NEUROCOMPUTING 2013年 120卷 24-33页

作者： Lei, Jianjun Zhang, Hailong You, Lei Hou, Chunping Wang, Laihua Tianjin Univ Sch Elect Informat Engn Tianjin Peoples R China

Visual attention has been used widely, such as region of interest (ROI) based image compression, imitating fixation region and salient object segmentation. The output saliency map range from spotlight map to object-based map which is related to different applications. We compare previously proposed saliency models and propose a new depth feature incorporated saliency model focusing on suppression of background saliency through piecewise function. We also produce an object-contour based ground truth database in order to evaluate several depth feature incorporated saliency models. Our method outperforms existing depth feature combination methods on the precision rate, when evaluated using the ground truth. At the same time, the effectiveness of using the depth feature in assisting salient object segmentation is verified. (c) 2013 Elsevier B.V. All rights reserved.

关键词： Stereoscopic visual attention Region of interest (ROI) Depth object segmentation

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Guided segmentation Network for Geospatial object segmentation

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2024年 17卷 5824-5833页

作者： Jia, Hongyu Yang, Wenwu Wang, Lin Li, Haolin Dalian Maritime Univ Sch Maritime Econ & Management Dalian 116026 Peoples R China

Geospatial objects pose significant challenges, including dense distribution, substantial interclass variations, and minimal intraclass variations. These complexities make achieving precise foreground object segmentation in high-resolution remote sensing images highly challenging. Current segmentation approaches often rely on the standard encoder-decoder architecture to extract object-related information, but overlook the inherent uncertainty issues that arise during the process. In this article, we aim to enhance segmentation by introducing an uncertainty-guided decoding mechanism and propose the uncertainty-guided segmentation network (UGSNet). Specifically, building upon the conventional encoder-decoder architecture, we initially employ the pyramid vision transformer to extract multilevel features containing extensive long-range information. We then introduce an uncertainty-guided decoding mechanism, addressing both epistemic and aleatoric uncertainties, to progressively refine segmentation with higher certainty at each level. With this uncertainty-guided decoding mechanism, our UGSNet achieves accurate geospatial object segmentation. To validate the effectiveness of UGSNet, we conduct extensive experiments on the large-scale ISAID dataset, and the results unequivocally demonstrate the superiority of our method over other state-of-the-art segmentation methods.

关键词： Uncertainty Image segmentation Decoding Transformers Feature extraction object segmentation Convolution Geospatial object segmentation remote sensing (RS) semantic segmentation uncertainty decoding mechanism

来源：评论

学校读者我要写书评

暂无评论

Adaptive Selection of Reference Frames for Video object segmentation

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2022年 31卷 1057-1071页

作者： Hong, Lingyi Zhang, Wei Chen, Liangyu Zhang, Wenqiang Fan, Jianping Fudan Univ Sch Comp Sci Shanghai Key Lab Intelligent Informat Proc Shanghai Peoples R China Lenovo Res AI Lab Beijing 100085 Peoples R China

Video object segmentation is a challenging task in computer vision because the appearances of target objects might change drastically along the time in the video. To solve this problem, space-time memory (STM) networks are exploited to make use of the information from all the intermediate frames between the first frame and the current frame in the video. However, fully using the information from all the memory frames may make STM not practical for long videos. To overcome this issue, a novel method is developed in this paper to select the reference frames adaptively. First, an adaptive selection criterion is introduced to choose the reference frames with similar appearance and precise mask estimation, which can efficiently capture the rich information of the target object and overcome the challenges of appearance changes, occlusion, and model drift. Secondly, bi-matching (bi-scale and bi-direction) is conducted to obtain more robust correlations for objects of various scales and prevents multiple similar objects in the current frame from being mismatched with the same target object in the reference frame. Thirdly, a novel edge refinement technique is designed by using an edge detection network to obtain smooth edges from the outputs of edge confidence maps, where the edge confidence is quantized into ten sub-intervals to generate smooth edges step by step. Experimental results on the challenging benchmark datasets DAVIS-2016, DAVIS-2017, YouTube-VOS, and a Long-Video dataset have demonstrated the effectiveness of our proposed approach to video object segmentation.

关键词： object segmentation Optical imaging Correlation Adaptation models Predictive models Bidirectional control Task analysis Video object segmentation space-time memory adaptive reference selection deep convolutional networks

来源：评论

学校读者我要写书评

暂无评论

Beyond Appearance: Multi-Frame Spatio-Temporal Context Memory Networks for Efficient and Robust Video object segmentation

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2024年 33卷 4853-4866页

作者： Dang, Jisheng Zheng, Huicheng Xu, Xiaohao Wang, Longguang Guo, Yulan Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou 510006 Peoples R China Minist Educ Key Lab Machine Intelligence & Adv Comp Guangzhou 510006 Peoples R China Guangdong Prov Key Lab Informat Secur Technol Guangzhou 510006 Peoples R China Univ Michigan Robot Inst Ann Arbor MI 48109 USA Air Force Aviat Univ Sch Elect Sci & Technol Changchun 130022 Peoples R China Sun Yat Sen Univ Sch Elect & Commun Engn Shenzhen Campus Shenzhen 510006 Peoples R China

Current video object segmentation approaches primarily rely on frame-wise appearance information to perform matching. Despite significant progress, reliable matching becomes challenging due to rapid changes of the object's appearance over time. Moreover, previous matching mechanisms suffer from redundant computation and noise interference as the number of accumulated frames increases. In this paper, we introduce a multi-frame spatio-temporal context memory (STCM) network to exploit discriminative spatio-temporal cues in multiple adjacent frames by utilizing a multi-frame context interaction module (MCI) for memory construction. Based on the proposed MCI module, a sparse group memory reader is developed to enable efficient sparse matching during memory reading. Our proposed method is generic and achieves state-of-the-art performance with real-time speed on benchmark datasets such as DAVIS and YouTube-VOS. In addition, our model exhibits robustness to sparse videos with low frame rates.

关键词： Memory management Feature extraction object segmentation Accuracy Task analysis Optical flow Cognition Video object segmentation spatio-temporal memory multi-frame context interaction sparse memory mechanism

来源：评论

学校读者我要写书评

暂无评论

Motion-Appearance Interactive Encoding for object segmentation in Unconstrained Videos

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2020年第6期30卷 1613-1624页

作者： Chen, Zixuan Guo, Chunchao Lai, Jianhuang Xie, Xiaohua Sun Yat Sen Univ Sch Data & Comp Sci Guangzhou 510006 Peoples R China GuangDong Prov Key Lab Informat Secur Technol Guangzhou 510006 Peoples R China

We present a two-stage framework of integrating motion and appearance cues for foreground object segmentation in unconstrained videos. Unlike conventional methods which encode motion and appearance patterns individually, our method puts particular emphasis on their mutual assistance. We propose an interactively constrained encoding (ICE) scheme to incorporate motion and appearance patterns into a graph that leads to a spatiotemporal energy optimization. Specifically, we construct a saliency network to infer the initial foreground maps and use optical flow to capture the initial motion information. After that, we perform ICE in the refinement stage for object segmentation. This scheme allows our method to consistently capture structural patterns about object perceptions throughout the whole framework. Our method can be operated on superpixels instead of raw pixels to reduce the number of graph nodes by two orders of magnitude. Moreover, we propose to tackle the object localization problem with inter-occlusion by weighted bipartite graph matching. The comprehensive experiments on two benchmark datasets (i.e., SegTrack-v2 and DAVIS2016) demonstrate the effectiveness of our approach compared with the state-of-the-art methods.

关键词： Videos Ice object segmentation Encoding Motion segmentation Trajectory Decoding Video object segmentation foreground detection saliency model interactively constrained encoding

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

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：