检索结果-内蒙古大学图书馆

Joint Multisource Saliency and Exemplar Mechanism for Weakly Supervised Video object segmentation

IEEE TRANSACTIONS ON IMAGE PROCESSING 2021年 30卷 8155-8169页

作者： En, Qing Duan, Lijuan Zhang, Zhaoxiang Beijing Univ Technol Fac Informat Technol Beijing Key Lab Trusted Comp Beijing 100124 Peoples R China Natl Engn Lab Crit Technol Informat Secur Classif Beijing 100124 Peoples R China Chinese Acad Sci Ctr Res Intelligent Percept & Comp Inst Automat Natl Lab Pattern Recognit Beijing 100190 Peoples R China Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Chinese Acad Sci Ctr Artificial Intelligence & Robot Hong Kong Inst Sci & Innovat Hong Kong Peoples R China

Weakly supervised video object segmentation (WSVOS) is a vital yet challenging task in which the aim is to segment pixel-level masks with only category labels. Existing methods still have certain limitations, e.g., difficulty in comprehending appropriate spatiotemporal knowledge and an inability to explore common semantic information with category labels. To overcome these challenges, we formulate a novel framework by integrating multisource saliency and incorporating an exemplar mechanism for WSVOS. Specifically, we propose a multisource saliency module to comprehend spatiotemporal knowledge by integrating spatial and temporal saliency as bottom-up cues, which can effectively eliminate disruptions due to confusing regions and identify attractive regions. Moreover, to our knowledge, we make the first attempt to incorporate an exemplar mechanism into WSVOS by proposing an adaptive exemplar module to process top-down cues, which can provide reliable guidance for co-occurring objects in intraclass videos and identify attentive regions. Our framework, which comprises the two aforementioned modules, offers a new perspective on directly constructing the correspondence between bottom-up cues and top-down cues when ground-truth information for the reference frames is lacking. Comprehensive experiments demonstrate that the proposed framework achieves state-of-the-art performance.

关键词： Spatiotemporal phenomena Feature extraction Motion segmentation Annotations Training Task analysis object segmentation Weakly supervised learning video object segmentation exemplar mechanism spatiotemporal saliency

来源：评论

学校读者我要写书评

暂无评论

Guided Co-segmentation Network for Fast Video object segmentation

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2021年第4期31卷 1607-1617页

作者： Liu, Weide Lin, Guosheng Zhang, Tianyi Liu, Zichuan Nanyang Technol Univ NTU Sch Comp Sci & Engn Singapore 639798 Singapore ASTAR Inst Infocomm Res I2R Singapore 138632 Singapore Nanyang Technol Univ NTU Sch Elect & Elect Engn Singapore 639798 Singapore

Semi-supervised video object segmentation is a task of propagating instance masks given in the first frame to the entire video. It is a challenging task since it usually suffers from heavy occlusions, large deformation, and large variations of objects. To alleviate these problems, many existing works apply time-consuming techniques such as fine-tuning, post-processing, or extracting optical flow, which makes them intractable for online segmentation. In our work, we focus on online semi-supervised video object segmentation. We propose a GCSeg (Guided Co-segmentation) Network which is mainly composed of a Reference Module and a Co-segmentation Module, to simultaneously incorporate the short-term, middle-term, and long-term temporal inter-frame relationships. Moreover, we propose an Adaptive Search Strategy to reduce the risk of propagating inaccurate segmentation results in subsequent frames. Our GCSeg network achieves state-of-the-art performance on online semi-supervised video object segmentation on Davis 2016 and Davis 2017 datasets.

关键词： Feature extraction object segmentation Task analysis Motion segmentation Pipelines Decoding Search problems Video segmentation co-segmentation semi-supervised

来源：评论

学校读者我要写书评

暂无评论

Video object segmentation with shape cue based on spatiotemporal superpixel neighbourhood

引用

IET COMPUTER VISION 2014年第1期8卷 16-25页

作者： Tian, Zhiqiang Zheng, Nanning Xue, Jianru Lan, Xuguang Li, Ce Zhou, Gang Xi An Jiao Tong Univ Inst Artificial Intelligence & Robot Xian 710049 Peoples R China

In this study, the authors present a method to extract moving objects in image sequences. The proposed approach is based on a graph cuts algorithm defined on a spatiotemporal superpixel neighbourhood. Presegmented superpixels are partitioned into foreground and background while preserving temporal and spatial coherence. It achieves this goal by three steps. First, instead of operating at pixel level, the superpixels are advocated as basic units of the authors segmentation scheme. Second, within the graph cuts framework, two superpixel-based data terms and two superpixel-based smoothness terms are proposed to solve segmentation problem. Finally, the proposed method yields the segmentation of all the superpixels within video volume by the graph cuts algorithm. To illustrate the advantages of this approach, the quantitative and qualitative results are compared with other state-of-the-art methods. The experimental results show that the proposed method gives better performance of segmentation with respect to these methods.

关键词： object segmentation Video object cuts Spatial coherence

来源：评论

学校读者我要写书评

暂无评论

Weakly-Supervised RGBD Video object segmentation

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2024年 33卷 2158-2170页

作者： Yang, Jinyu Gao, Mingqi Zheng, Feng Zhen, Xiantong Ji, Rongrong Shao, Ling Leonardis, Ales Southern Univ Sci & Technol Dept Comp Sci & Engn Shenzhen 518055 Peoples R China Univ Birmingham Birmingham B15 2TT England Univ Warwick Coventry CV4 7AL England Southern Univ Sci & Technol Shenzhen 518055 Peoples R China Guangdong Univ Petrochem Technol Coll Comp Sci Maoming 525011 Peoples R China Xiamen Univ Sch Informat Dept Artificial Intelligence Media Analyt & Comp Lab Xiamen 361005 Peoples R China Univ Chinese Acad Sci UCAS Terminus AI Lab Beijing 101408 Peoples R China Univ Birmingham Sch Comp Sci Birmingham B15 2TT England

Depth information opens up new opportunities for video object segmentation (VOS) to be more accurate and robust in complex scenes. However, the RGBD VOS task is largely unexplored due to the expensive collection of RGBD data and time-consuming annotation of segmentation. In this work, we first introduce a new benchmark for RGBD VOS, named DepthVOS, which contains 350 videos (over 55k frames in total) annotated with masks and bounding boxes. We futher propose a novel, strong baseline model - Fused Color-Depth Network (FusedCDNet), which can be trained solely under the supervision of bounding boxes, while being used to generate masks with a bounding box guideline only in the first frame. Thereby, the model possesses three major advantages: a weakly-supervised training strategy to overcome the high-cost annotation, a cross-modal fusion module to handle complex scenes, and weakly-supervised inference to promote ease of use. Extensive experiments demonstrate that our proposed method performs on par with top fully-supervised algorithms. We will open-source our project on https://***/yjybuaa/depthvos/ to facilitate the development of RGBD VOS.

关键词： Annotations object segmentation Training Target tracking Task analysis object tracking Benchmark testing RGBD data video object segmentation visual tracking

来源：评论

学校读者我要写书评

暂无评论

A neural model of selective attention and object segmentation in the visual scene: An approach based on partial synchronization and star-like architecture of connections

引用

NEURAL NETWORKS 2009年第5-6期22卷 707-719页

作者： Borisyuk, Roman Kazanovich, Yakov Chik, David Tikhanoff, Vadim Cangelosi, Angelo Univ Plymouth Sch Comp & Math Plymouth PL4 8AA Devon England Russian Acad Sci Inst Math Problems Biol Pushchino 142290 Moscow Region Russia State Univ Pushchino Pushchino 142290 Moscow Region Russia

A brain-inspired computational system is presented that allows sequential selection and processing of objects from a visual scene. The system is comprised of three modules. The selective attention module is designed as a network of spiking neurons of the Hodgkin-Huxley type with star-like connections between the central unit and peripheral elements. The attention focus is represented by those peripheral neurons that generate spikes synchronously with the central neuron while the activity of other peripheral neurons is suppressed. Such dynamics corresponds to the partial synchronization mode. It is shown that peripheral neurons with higher firing rates are preferentially drawn into partial synchronization. We show that local excitatory connections facilitate synchronization, while local inhibitory connections help distinguishing between two groups of peripheral neurons with similar intrinsic frequencies. The module automatically scans a Visual scene and sequentially selects regions of interest for detailed processing and object segmentation. The contour extraction module implements standard image processing algorithms for contour extraction. The module computes raw contours of objects accompanied by noise and some spurious inclusions. At the next stage, the object segmentation module designed as a network of phase oscillators is used for precise determination of object boundaries and noise suppression. This module has a star-like architecture of connections. The segmented object is represented by a group of peripheral oscillators working in the regime of partial synchronization with the central oscillator. The functioning of each module is illustrated by an example of processing of the visual scene taken from a visual stream of a robot camera. (C) 2009 Elsevier Ltd. All rights reserved.

关键词： Selective visual attention object segmentation Oscillatory neural network Synchronization

来源：评论

学校读者我要写书评

暂无评论

Efficient Semisupervised object segmentation for Long-Term Videos Using Adaptive Memory Network

引用

IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS 2024年第5期16卷 1789-1802页

作者： Zhong, Shan Li, Guoqiang Ying, Wenhao Zhao, Fuzhou Xie, Gengsheng Gong, Shengrong Changshu Inst Technol Sch Comp Sci & Engn Changshu 215500 Jiangsu Peoples R China Soochow Univ Sch Comp Sci & Technol Suzhou 215000 Jiangsu Peoples R China Jilin Univ Key Lab Symbol Computat & Knowledge Engn Minist Educ Changchun 130000 Peoples R China Changshu Inst Technol Sch Automot Engn Suzhou 215000 Jiangsu Peoples R China Jiangxi Normal Univ Sch Software Nanchang 330022 Jiangxi Peoples R China

Video object segmentation (VOS) uses the first annotated video mask to achieve consistent and precise segmentation in subsequent frames. Recently, memory-based methods have received significant attention owing to their substantial performance enhancements. However, these approaches rely on a fixed global memory strategy, which poses a challenge to segmentation accuracy and speed in the context of longer videos. To alleviate this limitation, we propose a novel semisupervised VOS model, founded on the principles of the adaptive memory network. Our proposed model adaptively extracts object features by focusing on the object area while effectively filtering out extraneous background noise. An identification mechanism is also thoughtfully applied to discern each object in multiobject scenarios. To further reduce storage consumption without compromising the saliency of object information, the outdated features residing in the memory pool are compressed into salient features through the employment of a self-attention mechanism. Furthermore, we introduce a local matching module, specifically devised to refine object features by fusing the contextual information from historical frames. We demonstrate the efficiency of our approach through experiments, substantially augmenting both the speed and precision of segmentation for long-term videos, while maintaining comparable performance for short videos.

关键词： Feature extraction Videos object recognition Data mining Adaptation models Adaptive systems Video sequences Long-term videos memory network object segmentation semisupervised learning

来源：评论

学校读者我要写书评

暂无评论

SSF-MOS: Semantic Scene Flow Assisted Moving object segmentation for Autonomous Vehicles

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2024年 73卷 1页

作者： Song, Tao Liu, Yunhao Yao, Ziying Wu, Xinkai Beihang Univ Sch Transportat Sci & Engn Beijing 100191 Peoples R China

Detecting moving objects in dynamic environments is precisely essential in autonomous driving. Existing object detection methods using point clouds have difficulties in distinguishing moving and static objects in dynamic environments. Motivated by the optical flow method widely used in image-based dynamic object perception, we propose semantic scene flow-assisted moving object segmentation (SSF-MOS), a unified framework that incorporates semantic information and ego-motion estimation in MOS. SSF-MOS first detects and excludes absolutely static objects, such as poles and roads, by applying the semantic segmentation method. Subsequently, the proposed SSF estimation method computes the motion vectors between consecutive point clouds and predicts the motion state (moving or static) of each point;furthermore, SSF-MOS calibrates the results of moving points by considering the ego-motion of autonomous vehicles. We directly introduce semantic information in the decoupled framework for more accurate results and convenience of upgrades. The extensive experiments show that the proposed SSF-MOS achieves a competitive performance of 0.701 mIOU compared with other state-of-the-art methods on the public dataset SemanticKITTI.

关键词： Semantics Point cloud compression Estimation Three-dimensional displays object segmentation Autonomous vehicles Vehicle dynamics moving object segmentation (MOS) scene flow semantic processing

来源：评论

学校读者我要写书评

暂无评论

Real-time object segmentation and coding for selective-quality video communications

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2004年第6期14卷 813-824页

作者： Challapali, K Brodsky, T Lin, YT Yan, Y Chen, RY Philips Res Briarcliff Manor NY 10510 USA ActivEye Inc Briarcliff Manor NY 10510 USA Polycom Inc Austin TX 78746 USA

The MPEG-4 standard enables the representation of video as a collection of objects. This paper describes an automatic system that exploits such a representation. Our system consists of two parts: real-time content extraction algorithms and a real-time multi-object rate control method. We present two approaches to content extraction: foreground segmentation based on two cameras and face segmentation based on a single camera. The main contributions of this paper are: 1) under a stereo camera setup, we improve a disparity estimation algorithm to obtain crisp and smooth boundaries of foreground objects;2) for a single camera scenario, we propose a novel algorithm for face detection and tracking, combining facial color and structure information;and 3) we develop a constant-quality variable bitrate (CQ-VBR) control algorithm that guarantees the quality specification for each object obtained from the two content extraction methods. Both segmentation algorithms run in real-time on a low-cost media processor, and have been tested extensively in various indoor environments. The CQ-VBR control algorithm is a useful tool for the evaluation of object-based coding. For low-bit-rate applications, we can achieve significant reduction in the overall bitrate, while maintaining the same visual quality of the foreground/face object as compared to conventional frame-based coding. Based on tests conducted on several sequences of different complexity levels, the bit-rate savings can be up to 48%. The satisfactory foreground segmentation (results presented) permits porting a live foreground object into arbitrary scenes to create composite video.

关键词： MPEG-4 multi-object coding object segmentation rate control real-time content extraction

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal Activity Semantics Understanding Based on Foreground object segmentation: iCounter Scenario

引用

IEEE ACCESS 2022年 10卷 57748-57758页

作者： Yu, Tzu-Wei Sarwar, Muhammad Atif Daraghmi, Yousef-Awwad Cheng, Sheng-Hsien Ik, Tsi-Ui Li, Yih-Lang Natl Yang Ming Chiao Tung Univ Coll Comp Sci Dept Comp Sci Hsinchu 30010 Taiwan Palestine Tech Univ Kadoorie Dept Comp Syst Engn Tulkarem 310 Palestine

Foreground object segmentation that captures the spatial and temporal information of moving objects in video is the most fundamental task for activity understanding in many intelligent applications, such as smart stores. Recently, several methods are proposed for the detection and recognition of activity based on object segmentation. However, these methods are often inaccurate because they do not maintain the temporal associations of object segment consistency across time. In this work, we proposed a hierarchical approach for foreground object segmentation and activity semantics understanding from sequential video to preserve spatial and temporal connectivity in the frames. The proposed system consists of two main modules: (a) the concatenated deep learning network containing PSPNet and convolutional-GRU to segment the foreground of an object of interest;(b) the activity mining framework which incorporates three sub-modules (i) a RetinaNet-based frame classifier to detect and count objects of interest;(ii) a time-domain activity and event detection algorithm;(iii) an image-based item query engine to recognize the shopping items. To evaluate the proposed approach, we designed the smart checkout-box called iCounter to collect the shopping activities dataset named "NOL-41" which is used in extensive experiments. The results show that the accuracy of the foreground object segmentation is 90.6%, the accuracy of the frame classification is 93.4%, the accuracy of activity event detection is 98.4%, and the accuracy of item query is 94.3%. Finally, the overall accuracy of the shopping list is 95.2%.

关键词： object segmentation Semantics Streaming media Image segmentation Deep learning Real-time systems Computer architecture Activity semantics activity recognition self-checkout PSPNet Conv-GRU image query smart store RetinaNet image database foreground object segmentation video foreground segmentation

来源：评论

学校读者我要写书评

暂无评论

Dense optical flow based background subtraction technique for object segmentation in moving camera environment

引用

IET IMAGE PROCESSING 2020年第14期14卷 3393-3404页

作者： Kushwaha, Arati Khare, Ashish Prakash, Om Khare, Manish Univ Allahabad Dept Elect & Commun Allahabad Uttar Pradesh India HNB Garhwal Univ Dept Comp Sci & Engn Srinagar Garhwal India Dhirubhai Ambani Inst Informat & Commun Technol Gandhinagar India

segmentation of moving object in video with moving background is a challenging problem and it becomes more difficult with varying illumination. The authors propose a dense optical flow-based background subtraction technique for object segmentation. The proposed technique is fast and reliable for segmentation of moving objects in realistic unconstrained videos. In the proposed work, they stabilise the camera motion by computing homography matrix, then they perform statistical background modelling using single Gaussian background modelling approach. Moving pixels are identified using dense optical flow in the background modelled scenario. The dense optical flow provides motion information of each pixel between consecutive frames, therefore for moving pixel identification they compute motion flow vector of each pixel between consecutive frames. To distinguish between foreground and background pixels, they labelled each pixel and thresholding the magnitude of motion flow vector identifies the moving pixels. The effectiveness of the proposed algorithm has been evaluated both qualitatively and quantitatively. The proposed algorithm has been evaluated on several realistic videos of different complex conditions. To assess the performance of the proposed work, the authors compared their algorithm with other state-of-art methods and found that the proposed method outperforms the other methods.

关键词： image sequences image segmentation object detection video signal processing image motion analysis Gaussian processes computer vision cameras dense optical flow based background subtraction technique object segmentation camera environment camera motion dense optical flow-based background subtraction technique statistical background single Gaussian background modelling approach moving pixels background modelled scenario motion flow vector

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：