检索结果-内蒙古大学图书馆

Temporal stabilization of video object segmentation for 3D-TV applications

SIGNAL PROCESSING-IMAGE COMMUNICATION 2005年第2期20卷 151-167页

作者： Erdem, CE Ernst, F Redert, A Hendriks, E TEKSEB MAM TUBITAK Momentum Digital Media TechnolRes Dept Gebze Kocaeli Turkey Philips Res Labs NL-5656 AA Eindhoven Netherlands Delft Univ Technol Dept Elect Engn Math & Comp Sci Informat & Commun Theory Grp NL-2628 CD Delft Netherlands

Our aim is to insert depth information into an existing 2D video sequence to provide content for 3D-TV applications, which we try to achieve through segmentation of the objects in the given 2D video sequence. To this effect, we present a method for temporal stabilization of video object segmentation algorithms for 3D-TV applications. First, two quantitative measures to evaluate temporal stability without ground-truth are discussed. Then, a pseudo-3D curve evolution method, which spatio-temporally stabilizes the estimated segmentation of a video object is introduced. Temporal stability is achieved by re-distributing existing object segmentation errors such that they will be less disturbing when the scene is rendered and viewed in 3D. Our starting point is the hypothesis that if making segmentation errors is inevitable, these errors should be made in a temporally consistent way for 3D-TV applications. This hypothesis is supported by the experiments, which show that there is significant improvement in segmentation quality both in terms of the objective quantitative measures and in terms of the viewing comfort in subjective perceptual tests. Therefore, it is possible to increase the perceptual object segmentation quality without increasing the actual segmentation accuracy. (C) 2004 Elsevier B.V. All rights reserved.

关键词： object segmentation object tracking temporal stabilization 3D TV curve evolution snakes

来源：评论

学校读者我要写书评

暂无评论

Temporo-Spatial Parallel Sparse Memory Networks for Efficient Video object segmentation

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2024年第11期25卷 17291-17304页

作者： Dang, Jisheng Zheng, Huicheng Wang, Bimei 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 Key Lab Informat Secur Technol Guangzhou 510006 Peoples R China Jinan Univ Coll Informat Sci & Technol Guangzhou 510006 Peoples R China Aviat Univ Air Force Coll Elect Sci & Technol Changchun 130022 Peoples R China Sun Yat Sen Univ Sch Elect & Commun Engn Shenzhen 518107 Peoples R China

Memory-based networks have achieved tremendous success in video object segmentation. However, these methods still suffer from unfaithful segmentation and inferior efficiency under complicated video scenarios. The reasons are mainly threefold: 1) Weak perception of fast-moving targets due to individual frame memory patterns without capturing inter-frame motion;2) Lack of discrimination to visually similar appearances due to the limited receptive field;3) Redundant computation caused by matching with all memorized frames. To address these issues, we propose a Temporo-Spatial Parallel Sparse Memory network (TSPSM) for efficient video object segmentation. Our TSPSM constructs a temporal memory bank and a spatial memory bank in parallel to memorize complementary discriminative object cues. The temporal bank exploits discriminative temporal motion cues, while the spatial bank mines spatial context cues between adjacent frames with large receptive fields, thereby alleviating the ambiguity caused by similar instances and fast movements. To reduce redundant computation without sacrificing performance during the matching step, we further design a parallel sparse memory reader based on the constructed informative memory banks, which efficiently retrieves relevant temporal and spatial information in a parallel way. Experiments demonstrate that our TSPSM achieves state-of-the-art performance with real-time speed on DAVIS, and YouTube-VOS benchmarks. Furthermore, extensive experiments show that the proposed TSPMC module can be applied to existing methods as a generic plugin to significantly improve performance.

关键词： Memory management object segmentation Task analysis Motion segmentation Accuracy Visualization Decoding Video object segmentation temporo-spatial parallel sparse memory network temporo-spatial parallel memory construction parallel sparse memory reader

来源：评论

学校读者我要写书评

暂无评论

AMSASeg: An Attention-Based Multi-Scale Atrous Convolutional Neural Network for Real-Time object segmentation From 3D Point Cloud

引用

IEEE ACCESS 2021年 9卷 70789-70796页

作者： Kim, Moogab Ilyas, Naveed Kim, Kiseon Gwangju Inst Sci & Technol GIST Sch Elect Engn & Comp Sci Gwangju 61005 South Korea

Extracting meaningful information on objects varying scale and shape is a challenging task while obtaining distinctive features on small to large size objects to enhance overall object segmentation accuracy from 3D point cloud. To handle this challenge, we propose an attention-based multi-scale atrous convolutional neural network (AMSASeg) for object segmentation from 3D point cloud. Specifically, a backbone network consists of three modules: distinctive atrous spatial pyramid pooling (DASPP), FireModule, and FireDeconv. The DASPP utilizes average pooling operations and atrous convolutions with different sizes to aggregate distinctive information on objects at multiple scales. The FireModule and FireDeconv are responsible to efficiently extract general features. Meanwhile, a spatial attention module (SAM) and channel attention module (CAM) aggregate spatial and semantic information on smaller objects from low-level and high-level layers, respectively. Our network enables to encode multi-scale information and extract distinct feature on overall objects to enhance segmentation performance. We evaluate our method on KITTI dataset. Experimental results demonstrate that the proposed network is effective to improve segmentation performance on small to large objects at real-time speed.

关键词： Three-dimensional displays Feature extraction Image segmentation Real-time systems object segmentation Computational efficiency Task analysis Deep learning convolutional neural network object segmentation 3D point cloud autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Learning of perceptual grouping for object segmentation on RGB-D data

引用

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION 2014年第1期25卷 64-73页

作者： Richtsfeld, Andreas Moerwald, Thomas Prankl, Johann Zillich, Michael Vincze, Markus Vienna Univ Technol Automat & Control Inst ACIN A-1040 Vienna Austria

object segmentation of unknown objects with arbitrary shape in cluttered scenes is an ambitious goal in computer vision and became a great impulse with the introduction of cheap and powerful RGB-D sensors. We introduce a framework for segmenting RGB-D images where data is processed in a hierarchical fashion. After pre-clustering on pixel level parametric surface patches are estimated. Different relations between patch-pairs are calculated, which we derive from perceptual grouping principles, and support vector machine classification is employed to learn Perceptual Grouping. Finally, we show that object hypotheses generation with Graph-Cut finds a globally optimal solution and prevents wrong grouping. Our framework is able to segment objects, even if they are stacked or jumbled in cluttered scenes. We also tackle the problem of segmenting objects when they are partially occluded. The work is evaluated on publicly available object segmentation databases and also compared with state-of-the-art work of object segmentation. (C) 2013 The Authors. Published by Elsevier Inc. All rights reserved.

关键词： Computer vision object segmentation Perceptual organization RGB-D images B-spline fitting object reconstruction SVM learning Graph-based segmentation

来源：评论

学校读者我要写书评

暂无评论

From Pixels to Semantics: Self-Supervised Video object segmentation With Multiperspective Feature Mining

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2022年 31卷 5801-5812页

作者： Li, Ruoqi Wang, Yifan Wang, Lijun Lu, Huchuan Wei, Xiaopeng Zhang, Qiang Dalian Univ Technol Sch Informat & Commun Engn Dalian 116024 Peoples R China Dalian Univ Technol Sch Innovat & Entrepreneurship Dalian 116024 Peoples R China Dalian Univ Technol Ningbo Inst Ningbo 315012 Peoples R China Dalian Univ Technol Sch Artificial Intelligence Dalian 116024 Peoples R China Dalian Univ Technol Sch Comp Sci & Technol Dalian 116024 Peoples R China

Existing self-supervised methods pose one-shot video object segmentation (O-VOS) as pixel-level matching to enable segmentation mask propagation across frames. However, the two tasks are not fully equivalent since O-VOS is more reliant on semantic correspondence rather than accurate pixel matching. To remedy this issue, we explore a new self-supervised framework that integrates pixel-level correspondence learning with semantic-level adaptation. The pixel-level correspondence learning is performed through photometric reconstruction of adjacent RGB frames during offline training, while semantic-level adaption operates at test-time by enforcing a bi-directional agreement of the predicted segmentation masks. In addition, we further propose a new network architecture with multi-perspective feature mining mechanism which can not only enhance reliable features but also suppress noisy ones to facilitate more robust image matching. By training the network using the proposed self-supervised framework, we achieve state-of-the-art performance on widely adopted datasets, further closing up the gap between self-supervised learning methods and their fully supervised counterparts.

关键词： Semantics Training Feature extraction Image reconstruction Task analysis object segmentation Image segmentation Video object segmentation self-supervised learning pixel-level correspondence semantic-level adaption feature mining

来源：评论

学校读者我要写书评

暂无评论

Efficient LiDAR-Based object segmentation and Mapping for Maritime Environments

引用

IEEE JOURNAL OF OCEANIC ENGINEERING 2019年第2期44卷 352-362页

作者： Thompson, David Coyle, Eric Brown, Jeremy Embry Riddle Aeronaut Univ Dept Mech Engn Daytona Beach FL 32114 USA

This paper proposes a method that utilizes a 3-D occupancy grid to efficiently map a large area while retaining simple representations of objects for path planning and provide spatial characteristics of objects, which may be used for object classification. To enable large-scale mapping of objects, a region around the unmanned surface vehicle (USV) is defined where a high density of LiDAR returns is expected, termed the visibility horizon. The polygon intersection between the visibility horizon and the newly detected objects is computed, as well as the polygon subtraction of the visibility horizon from the mapped list of polygons. The two polygon lists are then combined using a polygon union operation, with the objects retaining class designations. The result is a 2-D map that contains polygon representations of objects, where the object is described with a tunable number of vertices and may have an associated object class. Thus, providing necessary information for path planning and tasking. The resultant polygons are shown here to be accurate to 20 cm using a 10-cm occupancy grid and 16-ft-long unmanned surface vehicles with four multibeam LiDAR sensors.

关键词： LiDAR mapping object segmentation occupancy grid

来源：评论

学校读者我要写书评

暂无评论

Neural network approach to background Modeling for video object segmentation

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 2007年第6期18卷 1614-1627页

作者： Culibrk, Dubravko Marques, Oge Socek, Daniel Kalva, Hari Furht, Borko Florida Atlantic Univ Boca Raton FL 33431 USA

This paper presents a novel background modeling and subtraction approach for video object segmentation. A neural network (NN) architecture is proposed to form an unsupervised Bayesian classifier for this application domain. The constructed classifier efficiently handles the segmentation in natural-scene sequences with complex background motion and changes in illumination. The weights of the proposed NN serve as a model of the background and are temporally updated to reflect the observed statistics of background. The segmentation performance of the proposed NN is qualitatively and quantitatively examined and compared to two extant probabilistic object segmentation algorithms, based on a previously published test pool containing diverse surveillance-related sequences. The proposed algorithm is parallelized. on a subpixel level and designed to enable efficient hardware implementation.

关键词： automated surveillance background subtraction Neural Networks (NNs) object segmentation video processing.

来源：评论

学校读者我要写书评

暂无评论

Online Semantic object segmentation for Vision Robot Collected Video

引用

IEEE ACCESS 2019年 7卷 107602-107615页

作者： Li, Kunqian Tao, Wenbing Liu, Liman Ocean Univ China Coll Engn Qingdao 266100 Shandong Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Natl Key Lab Sci & Technol Multispectral Informat Wuhan 430074 Hubei Peoples R China South Cent Univ Nationalities Sch Biomed Engn Wuhan 430074 Hubei Peoples R China

Video segmentation is the foundation of many senior computer vision applications. For robotic vision applications, video object segmentation is facing more difficulties. Since the videos are usually collected from those complicated scenes and the camera perspective may be static for some time, object saliency and motion clues which are widely used in traditional video segmentation approaches could be unreliable. Besides, its online processing ability is of crucial importance. In this paper, we propose an online video object segmentation method, which is organized as a segmentation-by-detection framework. It first effectively segments out meaningful objects in short video frame batches with the help of object detectors, and then the segmentation of different batches can be associated with each other via bi-directional notebook based connecting strategy. Experiments conducted on public available datasets verify the above-mentioned property and show good performance of the proposed method.

关键词： Online video segmentation object segmentation object detection object tracklets object proposal shortest path algorithm

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Video object segmentation via Learning object-Aware Global-Local Correspondence

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2022年第12期32卷 8153-8164页

作者： Fan, Jiaqing Liu, Bo Zhang, Kaihua Liu, Qingshan Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Nanjing 211106 Peoples R China JD Finance Amer Corp Mountain View CA 94089 USA Nanjing Univ Informat Sci & Technol Coll Comp & Software Nanjing 210044 Peoples R China Minist Educ Engn Res Ctr Digital Forens Nanjing 210044 Peoples R China

In semi-supervised video object segmentation (VOS) task, temporal coherent object-level cues play a key role yet are hard to accurately model. To this end, this paper presents an object-aware global-local correspondence architecture, which enables to extract the inter-frame temporal coherent object-level features for accurate VOS. Specifically, we first generate a set of object masks by the ground-truth segmentation, and then we squeeze the current frame representation inside the object masks into a set of global object embeddings. Second, we compute the similarity between each embedding and the feature map, producing an object-aware weight for each pixel. The object-aware feature at each pixel is then constructed by summing the object embeddings weighted by their corresponding object-aware weights, which is able to capture rich object category information. Third, to establish the accurate correspondences between the inter-frame temporal coherent cues, we further design a novel global-local correspondence module to refine the temporal feature representations. Finally, we augment the object-aware features with the global-local aligned information to produce a strong spatio-temporal representation, which is essential to a more reliable pixel-wise segmentation prediction. Extensive evaluations are conducted on three popular VOS benchmarks containing Youtube-VOS, Davis2017 and Davis2016, demonstrating that the proposed method achieves favourable performance compared to the state-of-the-arts.

关键词： Task analysis Adaptation models Benchmark testing object segmentation Training Semantics Legged locomotion Semi-supervised video object segmentation object-aware representation global-local correspondence deep learning

来源：评论

学校读者我要写书评

暂无评论

Saliency-guided level set model for automatic object segmentation

引用

PATTERN RECOGNITION 2019年 93卷 147-163页

作者： Cai, Qing Liu, Huiying Qian, Yiming Zhou, Sanping Duan, Xiaojun Yang, Yee-Hong Northwestern Polytech Univ Sch Automat Youyi West Rd 127 Xian 710072 Shanxi Peoples R China Univ Alberta Dept Comp Sci Edmonton AB T6G 2E8 Canada Xi An Jiao Tong Univ Inst Artificial Intelligence & Robot Xianning West Rd 28 Xian 710049 Shanxi Peoples R China Northwestern Polytech Univ Natl Key Lab UVA Technol Youyi West Rd 127 Xian 710072 Shanxi Peoples R China

The level set model is a popular method for object segmentation. However, most existing level set models perform poorly in color images since they only use grayscale intensity information to defined their energy functions. To address this shortcoming, in this paper, we propose a new saliency-guided level set model (SLSM), which can automatically segment objects in color images guided by visual saliency. Specifically, we first define a global saliency-guided energy term to extract the color objects approximately. Then, by integrating information from different color channels, we define a novel local multichannel based energy term to extract the color objects in detail. In addition, unlike using a length regularization term in the conventional level set models, we achieve segmentation smoothness by incorporating our SLSM into a graph cuts formulation. More importantly, the proposed SLSM is automatically initialized by saliency detection. Finally, the evaluation on public benchmark databases and our collected database demonstrates that the new SLSM consistently outperforms many state-of-the-art level set models and saliency detecting methods in accuracy and robustness. (C) 2019 Published by Elsevier Ltd.

关键词： Level set model object segmentation Visual saliency Graph cuts Automatic initialization

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：