DE112010002232B4 - Semantische Szenensegmentierung mittels Random multinominalem Logit (RML) - Google Patents

Semantische Szenensegmentierung mittels Random multinominalem Logit (RML) Download PDF

Info

Publication number
DE112010002232B4
DE112010002232B4 DE112010002232.1T DE112010002232T DE112010002232B4 DE 112010002232 B4 DE112010002232 B4 DE 112010002232B4 DE 112010002232 T DE112010002232 T DE 112010002232T DE 112010002232 B4 DE112010002232 B4 DE 112010002232B4
Authority
DE
Germany
Prior art keywords
image
rml
texton
classifier
training set
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Expired - Fee Related
Application number
DE112010002232.1T
Other languages
German (de)
English (en)
Other versions
DE112010002232T5 (de
Inventor
Ananth Ranganathan
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Honda Motor Co Ltd
Original Assignee
Honda Motor Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Honda Motor Co Ltd filed Critical Honda Motor Co Ltd
Publication of DE112010002232T5 publication Critical patent/DE112010002232T5/de
Application granted granted Critical
Publication of DE112010002232B4 publication Critical patent/DE112010002232B4/de
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
    • G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
    • G06V10/464—Salient features, e.g. scale invariant feature transforms [SIFT] using a plurality of salient features, e.g. bag-of-words [BoW] representations
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/211—Selection of the most significant subset of features
    • G06F18/2115—Selection of the most significant subset of features by evaluating different subsets according to an optimisation criterion, e.g. class separability, forward selection or backward elimination
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/771—Feature selection, e.g. selecting representative features from a multi-dimensional feature space

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Multimedia (AREA)
  • Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Computing Systems (AREA)
  • Medical Informatics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Probability & Statistics with Applications (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)
DE112010002232.1T 2009-06-04 2010-05-28 Semantische Szenensegmentierung mittels Random multinominalem Logit (RML) Expired - Fee Related DE112010002232B4 (de)

Applications Claiming Priority (5)

Application Number Priority Date Filing Date Title
US21793009P 2009-06-04 2009-06-04
US61/217,930 2009-06-04
US12/789,292 US8442309B2 (en) 2009-06-04 2010-05-27 Semantic scene segmentation using random multinomial logit (RML)
US12/789,292 2010-05-27
PCT/US2010/036656 WO2010141369A1 (en) 2009-06-04 2010-05-28 Semantic scene segmentation using random multinomial logit (rml)

Publications (2)

Publication Number Publication Date
DE112010002232T5 DE112010002232T5 (de) 2012-07-05
DE112010002232B4 true DE112010002232B4 (de) 2021-12-23

Family

ID=43298064

Family Applications (1)

Application Number Title Priority Date Filing Date
DE112010002232.1T Expired - Fee Related DE112010002232B4 (de) 2009-06-04 2010-05-28 Semantische Szenensegmentierung mittels Random multinominalem Logit (RML)

Country Status (4)

Country Link
US (1) US8442309B2 (enExample)
JP (1) JP5357331B2 (enExample)
DE (1) DE112010002232B4 (enExample)
WO (1) WO2010141369A1 (enExample)

Families Citing this family (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8891869B2 (en) * 2011-03-31 2014-11-18 Sony Corporation System and method for effectively performing an integrated segmentation procedure
WO2012166840A2 (en) * 2011-06-01 2012-12-06 The Board Of Trustees Of The Leland Stanford Junior University Learning of image processing pipeline for digital imaging devices
CN102663418B (zh) * 2012-03-21 2014-04-23 清华大学 一种基于回归模型的图像集合建模与匹配方法
FR2996939B1 (fr) * 2012-10-12 2014-12-19 Commissariat Energie Atomique Procede de classification d'un objet multimodal
CN103268635B (zh) * 2013-05-15 2016-08-10 北京交通大学 一种几何网格场景模型的分割及语义标注方法
US9488483B2 (en) * 2013-05-17 2016-11-08 Honda Motor Co., Ltd. Localization using road markings
KR20170036657A (ko) * 2014-03-19 2017-04-03 뉴럴라 인코포레이티드 자율 로봇 제어를 위한 방법들 및 장치
CN105389583A (zh) * 2014-09-05 2016-03-09 华为技术有限公司 图像分类器的生成方法、图像分类方法和装置
CN106327469B (zh) * 2015-06-29 2019-06-18 北京航空航天大学 一种语义标签引导的视频对象分割方法
US20170200041A1 (en) * 2016-01-13 2017-07-13 Regents Of The University Of Minnesota Multi-modal data and class confusion: application in water monitoring
CN106021376B (zh) * 2016-05-11 2019-05-10 上海点融信息科技有限责任公司 用于处理用户信息的方法和设备
JP6737906B2 (ja) * 2016-06-07 2020-08-12 トヨタ モーター ヨーロッパ 視覚的且つ動的な運転シーンの知覚的負荷を決定する制御装置、システム及び方法
US11205103B2 (en) 2016-12-09 2021-12-21 The Research Foundation for the State University Semisupervised autoencoder for sentiment analysis
US10635927B2 (en) 2017-03-06 2020-04-28 Honda Motor Co., Ltd. Systems for performing semantic segmentation and methods thereof
CN106971150B (zh) * 2017-03-15 2020-09-08 国网山东省电力公司威海供电公司 基于逻辑回归的排队异常检测方法及装置
WO2018171875A1 (en) * 2017-03-21 2018-09-27 Toyota Motor Europe Nv/Sa Control device, system and method for determining the perceptual load of a visual and dynamic driving scene
CN110120085B (zh) * 2018-02-07 2023-03-31 深圳市腾讯计算机系统有限公司 一种动态纹理视频生成方法、装置、服务器及存储介质
KR102718664B1 (ko) 2018-05-25 2024-10-18 삼성전자주식회사 영상 처리를 위한 네트워크 조정 방법 및 장치
WO2020243333A1 (en) 2019-05-30 2020-12-03 The Research Foundation For The State University Of New York System, method, and computer-accessible medium for generating multi-class models from single-class datasets
JP7242882B2 (ja) * 2019-09-27 2023-03-20 富士フイルム株式会社 情報処理装置、情報処理装置の作動方法、情報処理装置の作動プログラム
US20230028042A1 (en) * 2021-07-21 2023-01-26 Canoo Technologies Inc. Augmented pseudo-labeling for object detection learning with unlabeled images
CN114373027A (zh) * 2021-12-17 2022-04-19 杭州电子科技大学上虞科学与工程研究院有限公司 基于灰度共生矩阵的瓷砖图像数据集生成方法
CN114821210B (zh) * 2022-03-17 2025-06-03 西北工业大学 一种基于多分类逻辑回归的特征选择方法

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080075361A1 (en) 2006-09-21 2008-03-27 Microsoft Corporation Object Recognition Using Textons and Shape Filters

Family Cites Families (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4945478A (en) 1987-11-06 1990-07-31 Center For Innovative Technology Noninvasive medical imaging system and method for the identification and 3-D display of atherosclerosis and the like
DE19623033C1 (de) 1996-06-08 1997-10-16 Aeg Electrocom Gmbh Verfahren und Anordnung zur Mustererkennung auf statistischer Basis
US6711278B1 (en) 1998-09-10 2004-03-23 Microsoft Corporation Tracking semantic objects in vector image sequences
US7274810B2 (en) 2000-04-11 2007-09-25 Cornell Research Foundation, Inc. System and method for three-dimensional image rendering and analysis
FR2832832A1 (fr) * 2001-11-23 2003-05-30 Ge Med Sys Global Tech Co Llc Procede de detection et de caracterisation automatique de nodules dans une image tomographique et systeme d'imagerie medicale par tomodensimetrie correspondant
US7313268B2 (en) * 2002-10-31 2007-12-25 Eastman Kodak Company Method for using effective spatio-temporal image recomposition to improve scene classification
US7827183B2 (en) 2003-03-19 2010-11-02 Customiser Limited Recognition of patterns in data
US7110000B2 (en) * 2003-10-31 2006-09-19 Microsoft Corporation Synthesis of progressively-variant textures and application to arbitrary surfaces
US20050221266A1 (en) * 2004-04-02 2005-10-06 Mislevy Robert J System and method for assessment design
JP4260060B2 (ja) * 2004-05-12 2009-04-30 ジーイー・メディカル・システムズ・グローバル・テクノロジー・カンパニー・エルエルシー Ｘ線ｃｔ装置および画像再構成装置
CN101356546B (zh) * 2006-05-29 2011-10-12 松下电器产业株式会社 图像高分辨率化装置、方法及系统
US20080027917A1 (en) 2006-07-31 2008-01-31 Siemens Corporate Research, Inc. Scalable Semantic Image Search
US20090083790A1 (en) 2007-09-26 2009-03-26 Tao Wang Video scene segmentation and categorization
US8213725B2 (en) * 2009-03-20 2012-07-03 Eastman Kodak Company Semantic event detection using cross-domain knowledge

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080075361A1 (en) 2006-09-21 2008-03-27 Microsoft Corporation Object Recognition Using Textons and Shape Filters

Non-Patent Citations (7)

* Cited by examiner, † Cited by third party
Title
J. Malik, S. Belongie, T. Leung, and J. Shi: Contour and texture analysis for image segmentation. In: Int’l. Journal of Computer Vision, 43, June 2001, 1, 7-27.
MATTHEW ALASTAIR JOHNSON „Semantic Segmentation and Image Search", University of Cambridge, April 2008; J. Malik, S. Belongie, T. Leung and J. Shi. „Contour and texture analysis for image segmentation" Int'l Journal of Computer Vision, 43(1 ):7-27, June 2001 und Xiaofeng Ren and Jitendra Malik „Learning a Classification Model for Segmentation" Proceedings of the Ninth IEE International Conference on Computer Vision (ICCV'03), 2003
MATTHEW ALASTAIR JOHNSON: Semantic Segmentation and Image Search. In: Dissertation University of Cambridge, April 2008, 1-171.
Prinzie Anita, Dirk Van den Poel „Random Forests for Multiclass classification: Random Multinomial Logit" WORKING PAPER, 2007/435, D/2006/7012/3X, Ghent University, Ghent, Belgium, Januar 2007
Prinzie Anita, Dirk Van den Poel: Random Forests for Multiclass classification: Random Multinomial Logit. In: WORKING PAPER, 2007/435, D/2006/7012/3X, Januar 2007, 1-31.
Song-Chun Zhu, Cheng-en Guo, Yingnian Wu, and Yizhou Wang: What Are Textons?. In: A. Heyden et al. (Eds.): ECCV 2002, 2002, 1-16.
Xiaofeng Ren and Jitendra Malik: Learning a Classification Model for Segmentation. In: Proceedings of the Ninth IEEE International Conference on Computer Vision (ICCV’03), 2003, 1-8.

Also Published As

Publication number Publication date
JP2012529110A (ja) 2012-11-15
US20100310159A1 (en) 2010-12-09
DE112010002232T5 (de) 2012-07-05
US8442309B2 (en) 2013-05-14
JP5357331B2 (ja) 2013-12-04
WO2010141369A1 (en) 2010-12-09

Similar Documents

Publication Publication Date Title
DE112010002232B4 (de) Semantische Szenensegmentierung mittels Random multinominalem Logit (RML)
DE112016005059B4 (de) Unterkategorienbewusste faltende neuronale Netzwerke zur Objekterfassung
EP2368216A1 (de) Verfahren und einrichtung zur analyse von umgebungsobjekten und/oder umgebungsszenen, wie zur objekt- und szenenklassensegmentierung
DE102020200503A1 (de) Verfahren zum Generieren von gelabelten Daten, insbesondere für das Training eines neuronalen Netzes, mittels Verbesserung initialer Label
DE102022202223A1 (de) Erzeugen von Trainingsdaten für maschinelles Lernen
DE102021201124A1 (de) Trainieren von bildklassifizierernetzen
DE102021203020A1 (de) Generative-adversarial-network-modelle zur detektion kleiner strassenobjekte
DE102022209528A1 (de) Visuelle Analysesysteme zur Diagnose und Verbesserung von Deep-Learning-Modellen für bewegbare Objekte beim autonomen Fahren
DE102018113621A1 (de) Verfahren zum Trainieren eines konvolutionellen neuronalen Netzwerks zum Verarbeiten von Bilddaten zur Anwendung in einem Fahrunterstützungssystem
DE102013210771A1 (de) Detektion eines komplexen objekts unter verwendung einer kaskade von klassifizierungseinrichtungen
DE102019213459A1 (de) Verfahren zum Komprimieren eines Neuronalen Netzes
DE102019129029A1 (de) System und verfahren zur objektdetektion
DE102013206920A1 (de) Detektion eines komplexen Objekts unter Verwendung einer Kaskade vonKlassifizierungseinrichtungen
DE102023113925A1 (de) Verfahren zur Detektion von wenigstens einem Hindernis bei einem automatisierten und/oder zumindest teilautonomen Fahrsystem
DE102021131179A1 (de) Formpriorisierte Bildklassifizierung unter Verwendung tiefer Faltungsnetze
DE102022201161A1 (de) Objektklassifizierung mit einem einstufigen metabasierten Objektdetektor unter Verwendung von Klassenprototypen
DE102021212732A1 (de) Überprüfen von test- und/oder trainings-datensätzen für ein computerbasiertes maschinenlernmodul
DE102021206106A1 (de) Vorrichtung und Verfahren zum Trainieren eines Maschinenlernsystems zum Entrauschen eines Eingangssignals
DE102021206190A1 (de) Verfahren zur Erkennung von Objekten gesuchter Typen in Kamerabildern
EP4033452B1 (de) Domänenunabhängiges training von bildklassifikatoren
DE102023130646B4 (de) Verfahren zur Dimensionsreduzierung
DE102023128935A1 (de) Erkennungsvorrichtung und Verfahren zur Objektklassifizierung unter Verwendung eines White-Box-Modells
DE102022208480A1 (de) Verfahren zum Evaluieren eines trainierten tiefen neuronalen Netzes
DE102023201113A1 (de) Computerimplementiertes Verfahren zum Trainieren eines Algorithmus des maschinellen Lernens und/oder zum Generieren mindestens eines Trainingsbildes
DE102019213458A1 (de) Verfahren zum Komprimieren eines Neuronalen Netzes

Legal Events

Date Code Title Description
R012 Request for examination validly filed
R016 Response to examination communication
R016 Response to examination communication
R018 Grant decision by examination section/examining division
R079 Amendment of ipc main class

Free format text: PREVIOUS MAIN CLASS: G06K0009400000

Ipc: G06V0030164000

R020 Patent grant now final
R119 Application deemed withdrawn, or ip right lapsed, due to non-payment of renewal fee