检索结果-内蒙古大学图书馆

Assessment of crowdsourcing and gamification loss in user-assisted object segmentation

MULTIMEDIA TOOLS AND APPLICATIONS 2016年第23期75卷 15901-15928页

作者： Carlier, Axel Salvador, Amaia Cabezas, Ferran Giro-i-Nieto, Xavier Charvillat, Vincent Marques, Oge Univ Toulouse IRIT ENSEEIHT Toulouse France Univ Politecn Cataluna Barcelona Catalonia Spain Florida Atlantic Univ Boca Raton FL 33431 USA

There has been a growing interest in applying human computation - particularly crowdsourcing techniques - to assist in the solution of multimedia, image processing, and computer vision problems which are still too difficult to solve using fully automatic algorithms, and yet relatively easy for humans. In this paper we focus on a specific problem - object segmentation within color images - and compare different solutions which combine color image segmentation algorithms with human efforts, either in the form of an explicit interactive segmentation task or through an implicit collection of valuable human traces with a game. We use Click'n'Cut, a friendly, web-based, interactive segmentation tool that allows segmentation tasks to be assigned to many users, and Ask'nSeek, a game with a purpose designed for object detection and segmentation. The two main contributions of this paper are: (i) We use the results of Click'n'Cut campaigns with different groups of users to examine and quantify the crowdsourcing loss incurred when an interactive segmentation task is assigned to paid crowd-workers, comparing their results to the ones obtained when computer vision experts are asked to perform the same tasks. (ii) Since interactive segmentation tasks are inherently tedious and prone to fatigue, we compare the quality of the results obtained with Click'n'Cut with the ones obtained using a (fun, interactive, and potentially less tedious) game designed for the same purpose. We call this contribution the assessment of the gamification loss, since it refers to how much quality of segmentation results may be lost when we switch to a game-based approach to the same task. We demonstrate that the crowdsourcing loss is significant when using all the data points from workers, but decreases substantially (and becomes comparable to the quality of expert users performing similar tasks) after performing a modest amount of data analysis and filtering out of users whose data are clearly not useful

关键词： GWAP Crowdsourcing Serious games object detection object segmentation

来源：评论

学校读者我要写书评

暂无评论

An Unified Recurrent Video object segmentation Framework for Various Surveillance Environments

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2021年 30卷 7889-7902页

作者： Patil, Prashant W. Dudhane, Akshay Kulkarni, Ashutosh Murala, Subrahmanyam Gonde, Anil Balaji Gupta, Sunil Deakin Univ Appl Artificial Intelligence Inst A2I2 Geelong Campus Geelong Vic 3216 Australia MBZUAI Comp Vis Dept Abu Dhabi U Arab Emirates IIT Ropar Dept Elect Engn Comp Vis & Pattern Recognit Lab Rupnagar 140001 Punjab India SGGSIET Dept Elect & Telecommunicat Engn Nanded 431606 India

Moving object segmentation (MOS) in videos received considerable attention because of its broad security-based applications like robotics, outdoor video surveillance, self-driving cars, etc. The current prevailing algorithms highly depend on additional trained modules for other applications or complicated training procedures or neglect the inter-frame spatio-temporal structural dependencies. To address these issues, a simple, robust, and effective unified recurrent edge aggregation approach is proposed for MOS, in which additional trained modules or fine-tuning on a test video frame(s) are not required. Here, a recurrent edge aggregation module (REAM) is proposed to extract effective foreground relevant features capturing spatio-temporal structural dependencies with encoder and respective decoder features connected recurrently from previous frame. These REAM features are then connected to a decoder through skip connections for comprehensive learning named as temporal information propagation. Further, the motion refinement block with multi-scale dense residual is proposed to combine the features from the optical flow encoder stream and the last REAM module for holistic feature learning. Finally, these holistic features and REAM features are given to the decoder block for segmentation. To guide the decoder block, previous frame output with respective scales is utilized. The different configurations of training-testing techniques are examined to evaluate the performance of the proposed method. Specifically, outdoor videos often suffer from constrained visibility due to different environmental conditions and other small particles in the air that scatter the light in the atmosphere. Thus, comprehensive result analysis is conducted on six benchmark video datasets with different surveillance environments. We demonstrate that the proposed method outperforms the state-of-the-art methods for MOS without any pre-trained module, fine-tuning on the test video frame(s) or complic

关键词： Decoding Feature extraction object segmentation Training Task analysis Optical imaging Dynamics Spatio-temporal dependencies adversarial learning recurrent feature sharing various surveillance environments

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 1-12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

CVABS: moving object segmentation with common vector approach for videos

引用

IET COMPUTER VISION 2019年第8期13卷 719-729页

作者： Isik, Sahin Ozkan, Kemal Gerek, Omer Nezih Eskisehir Osmangazi Univ Comp Engn Dept TR-26480 Eskisehir Turkey Eskisehir Tech Univ Elect & Elect Dept TR-26555 Eskisehir Turkey

Background modelling is a fundamental step for several real-time computer vision applications that requires security systems and monitoring. An accurate background model helps to detect the activity of moving objects in the video. In this work, the authors have developed a new subspace-based background-modelling algorithm using the concept of common vector approach (CVA) with Gram-Schmidt orthogonalisation. Once the background model that involves the common characteristic of different views corresponding to the same scene is acquired, a smart foreground detection and background updating procedure is applied based on dynamic control parameters. A variety of experiments is conducted on different problem types related to dynamic backgrounds. Several types of metrics are utilised as objective measures and the obtained visual results are judged subjectively. It was observed that the proposed method stands successfully for all problem types reported on CDNet2014 dataset by updating the background frames with a self-learning feedback mechanism.

关键词： computer vision object detection video signal processing image motion analysis image segmentation smart foreground detection background updating procedure dynamic control parameters dynamic backgrounds objective measures background frames object segmentation common vector approach real-time computer vision applications security systems subspace-based background-modelling algorithm CDNet2014 dataset Gram-Schmidt orthogonalisation self-learning feedback mechanism

来源：评论

学校读者我要写书评

暂无评论

Adversarial Attacks on Video object segmentation With Hard Region Discovery

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2024年第6期34卷 5049-5062页

作者： Li, Ping Zhang, Yu Yuan, Li Zhao, Jian Xu, Xianghua Zhang, Xiaoqin Hangzhou Dianzi Univ Sch Comp Sci & Technol Hangzhou 310018 Peoples R China Guangdong Lab Artificial Intelligence & Digital Ec Shenzhen 518132 Peoples R China Peking Univ Sch Elect & Comp Engn Beijing 100871 Peoples R China Peng Cheng Lab Shenzhen 518055 Peoples R China Inst North Elect Equipment Beijing 100044 Peoples R China Intelligent Game & Decis Lab Beijing 100085 Peoples R China Wenzhou Univ Coll Comp Sci & Artificial Intelligence Wenzhou 325035 Peoples R China

Video object segmentation has been applied to various computer vision tasks, such as video editing, autonomous driving, and human-robot interaction. However, the methods based on deep neural networks are vulnerable to adversarial examples, which are the inputs attacked by almost human-imperceptible perturbations, and the adversary (i.e., attacker) will fool the segmentation model to make incorrect pixel-level predictions. This will rise the security issues in highly-demanding tasks because small perturbations to the input video will result in potential attack risks. Though adversarial examples have been extensively used for classification, it is rarely studied in video object segmentation. Existing related methods in computer vision either require prior knowledge of categories or cannot be directly applied due to the special design for certain tasks, failing to consider the pixel-wise region attack. Hence, this work develops an object-agnostic adversary that has adversarial impacts on VOS by first-frame attacking via hard region discovery. Particularly, the gradients from the segmentation model are exploited to discover the easily confused region, in which it is difficult to identify the pixel-wise objects from the background in a frame. This provides a hardness map that helps to generate perturbations with a stronger adversarial power for attacking the first frame. Empirical studies on three benchmarks indicate that our attacker significantly degrades the performance of several state-of-the-art video object segmentation models.

关键词： Perturbation methods object segmentation Task analysis Computational modeling Predictive models object tracking Computer vision Video object segmentation adversarial attack perturbation hard region discovery

来源：评论

学校读者我要写书评

暂无评论

Online Meta Adaptation for Fast Video object segmentation

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2020年第5期42卷 1205-1217页

作者： Xiao, Huaxin Kang, Bingyi Liu, Yu Zhang, Maojun Feng, Jiashi Natl Univ Def Technol Coll Syst Engn Changsha 410073 Hunan Peoples R China Natl Univ Singapore Dept Elect & Comp Engn Singapore 119077 Singapore

Conventional deep neural networks based video object segmentation (VOS) methods are dominated by heavily fine-tuning a segmentation model on the first frame of a given video, which is time-consuming and inefficient. In this paper, we propose a novel method which rapidly adapts a base segmentation model to new video sequences with only a couple of model-update iterations, without sacrificing performance. Such attractive efficiency benefits from the meta-learning paradigm which leads to a meta-segmentation model and a novel continuous learning approach which enables online adaptation of the segmentation model. Concretely, we train a meta-learner on multiple VOS tasks such that the meta model can capture their common knowledge and gains the ability to fast adapt the segmentation model to new video sequences. Furthermore, to deal with unique challenges of VOS tasks from temporal variations in the video, e.g., object motion and appearance changes, we propose a principled online adaptation approach that continuously adapts the segmentation model across video frames by exploiting temporal context effectively, providing robustness to annoying temporal variations. Integrating the meta-learner with the online adaptation approach, the proposed VOS model achieves competitive performance against the state-of-the-arts and moreover provides faster per-frame processing speed.

关键词： Adaptation models Task analysis object segmentation Optical imaging Motion segmentation Image segmentation Runtime Meta learning video object segmentation convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

DOST: a distributed object segmentation tool

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2018年第16期77卷 20839-20862页

作者： Farid, Muhammad Shahid Lucenteforte, Maurizio Grangetto, Marco Univ Punjab Punjab Univ Coll Informat Technol Lahore Pakistan Univ Turin Dipartimento Informat Turin Italy

This paper presents a novel distributed object segmentation framework that allows one to extract potentially large coherent objects from digital images. The proposed approach requires minimum user supervision and permits to segment the objects accurately. It works in three steps starting with the user input in form of few mouse clicks on the target object. First, based on user input, the statistical characteristics of the target distributed object are modeled with Gaussian mixture model. This model serves as the primary segmentation of the object. In the second step, the segmentation result is refined by performing connected component analysis to reduce false positives. In the final step the resulting segmentation map is dilated to select the neighboring pixels that are potentially incorrectly classified;this allows us to recast the segmentation as a graph partitioning problem that can be solved using the well-known graph cut technique. Extensive experiments have been carried out on heterogeneous images to test the accuracy of the proposed method for the segmentation of various types of distributed objects. Examples of application of proposed technique in remote sensing to segment roads and rivers from aerial images are also presented. The visual and objective evaluation and comparison with the existing techniques show that the proposed tool can deliver optimal performance when applied to tough object segmentation tasks.

关键词： object segmentation Graph cuts Gaussian mixture model Connected component analysis

来源：评论

学校读者我要写书评

暂无评论

Flow-Edge Guided Unsupervised Video object segmentation

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2022年第12期32卷 8116-8127页

作者： Zhou, Yifeng Xu, Xing Shen, Fumin Zhu, Xiaofeng Shen, Heng Tao Univ Elect Sci & Technol China Ctr Future Multimedia Chengdu 611731 Peoples R China Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 611731 Peoples R China

Recently, deep learning techniques have achieved significant improvements in unsupervised video object segmentation (UVOS). However, many of existing approach cannot accurately identify the foreground objects and the background as they commonly use the coarse temporal features (e.g., optical flow and multi-frames attention). In this paper, we present a novel model termed Flow Edge-based Motion-Attentive Network (FEM-Net), to address the unsupervised video object segmentation problem. Firstly, a motion-attentive encoder is used to jointly learn the spatial and temporal features. Then, a Flow Edge Connect (FEC) module is designed to hallucinate edges of the ambiguous or missing region in the optical flow. During the segmentation stage, the complementary temporal feature composed by the motion-attentive feature and flow edge is fed into a decoder to infer the salient foreground objects. Experimental results on two challenging public benchmarks (i.e. DAVIS-16 and FBMS) demonstrate that the proposed FEM-Net compares favorably against the state-of-the-art methods.

关键词： Motion segmentation Feature extraction object segmentation Image edge detection Task analysis Image segmentation Computer vision Video segmentation optical flow attention mechanisms Index Terms deep learning

来源：评论

学校读者我要写书评

暂无评论

MirrorNet: Bio-Inspired Camouflaged object segmentation

引用

IEEE ACCESS 2021年 9卷 43290-43300页

作者： Yan, Jinnan Trung-Nghia Le Khanh-Duy Nguyen Minh-Triet Tran Thanh-Toan Do Nguyen, Tam, V Univ Dayton Dept Comp Sci Dayton OH 45469 USA Natl Inst Informat Tokyo 1018430 Japan Vietnam Natl Univ Univ Informat Technol Multimedia Commun Lab Ho Chi Minh City 7000060 Vietnam Vietnam Natl Univ Univ Sci Fac Informat Technol Ho Chi Minh City 7000060 Vietnam Monash Univ Fac Informat Technol Dept Data Sci & AI Clayton Vic 3800 Australia

Camouflaged objects are generally difficult to be detected in their natural environment even for human beings. In this paper, we propose a novel bio-inspired network, named the MirrorNet, that leverages both instance segmentation and bio-inspired attack stream for the camouflaged object segmentation. Differently from existing networks for segmentation, our proposed network possesses two segmentation streams: the main stream and the bio-inspired attack stream corresponding with the original image and its flipped image, respectively. The output from the bio-inspired attack stream is then fused into the main stream's result for the final camouflage map to boost up the segmentation accuracy. Extensive experiments conducted on the public CAMO dataset demonstrate the effectiveness of our proposed network. Our proposed method achieves 89% in accuracy, outperforming the state-of-the-arts.

关键词： Streaming media object segmentation Image segmentation Image color analysis Biomedical imaging Training object recognition Camouflaged object segmentation bio-inspired network

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：