[go: up one dir, main page]

WO2020130999A1 - Procédé de détection de changements inter-vidéo - Google Patents

Procédé de détection de changements inter-vidéo Download PDF

Info

Publication number
WO2020130999A1
WO2020130999A1 PCT/TR2019/051170 TR2019051170W WO2020130999A1 WO 2020130999 A1 WO2020130999 A1 WO 2020130999A1 TR 2019051170 W TR2019051170 W TR 2019051170W WO 2020130999 A1 WO2020130999 A1 WO 2020130999A1
Authority
WO
WIPO (PCT)
Prior art keywords
bir
ile
için
öznitelik
iki
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.)
Ceased
Application number
PCT/TR2019/051170
Other languages
English (en)
Inventor
Murat BAL
Burak BALCI
Alperen ELİHOŞ
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.)
Havelsan Hava Elektronik Sanayi ve Ticaret AS
Original Assignee
Havelsan Hava Elektronik Sanayi ve Ticaret AS
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 Havelsan Hava Elektronik Sanayi ve Ticaret AS filed Critical Havelsan Hava Elektronik Sanayi ve Ticaret AS
Publication of WO2020130999A1 publication Critical patent/WO2020130999A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/254—Analysis of motion involving subtraction of images
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
    • G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
    • G06T7/38—Registration of image sequences
    • 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
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G06V10/757—Matching configurations of points or features
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10032—Satellite or aerial image; Remote sensing
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30181—Earth observation
    • G06T2207/30184—Infrastructure
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30232—Surveillance

Definitions

  • Fakat bu görüntüler hava araçlar ⁇ ndan (özellikle boyut olarak daha küçük olan ⁇ HA, kopter gibi araçlardan) çekilen görüntüler ile karkan ⁇ laformt ⁇ rmak istendi ⁇ inde rota uyumu, titre araç e ⁇ imi ve benzeri gibi sebeplerle görüntülerin çerçeveleri birbiri üzerine oturmamakta, bu yüzden de anl ⁇ k olarak karw ⁇ laformt ⁇ r ⁇ lmalar ⁇ olanakl ⁇ olmamaktad ⁇ r.
  • Dahas ⁇ hava araçlar ⁇ ile al ⁇ nan görüntüler güne invoken ayn ⁇ aç ⁇ da oldu ⁇ u zamanlarda al ⁇ namad ⁇ , hava xartlar ⁇ ndaki de ⁇ i whokliklerden etkilendi ⁇ i ve yanl ⁇ war de ⁇ erlendirmelere aç ⁇ k oldu ⁇ u için, rastlanan çözümler sa ⁇ l ⁇ kl ⁇ bir karw ⁇ laformt ⁇ rmaya olanak sa ⁇ lamamamaktad ⁇ r.
  • Fakat böylesi bir istde nesneleri özniteliklerine göre s ⁇ n ⁇ fland ⁇ rmak ve çerçeveler aras ⁇ ufak aç ⁇ kaymalar ⁇ n ⁇ dahi düzeltmek mümkün olmayaca ⁇ için araçtan yap ⁇ lan çekimlerde sonuç vermesi olanakl ⁇ de ⁇ ildir.
  • Dahas ⁇ , öznitelik hatlar ⁇ üzerinden bir e whotleme ve çerçeve düzeltmesi de öngörmedi ⁇ i için, görüntülerin aç ⁇ sal hatlar olarak ifade edilmesi ve bunlar aras ⁇ nda bir benzetim kurulmas ⁇ yolu ile bir karw ⁇ laformt ⁇ rma yap ⁇ lmas ⁇ n ⁇ öngörmektedir.
  • Bu sorun özellikle uzun çekimlerde (dakika mertebesindeki ve daha uzun olanlarda) ciddi sorunlara yol açmakta, ciddi i souplem güçlerini sa ⁇ layan bilgisayarlar ⁇ n kullan ⁇ lmas ⁇ n ⁇ zorunlu k ⁇ lmaktad ⁇ r.
  • Bu fark sebebiyle bir karw ⁇ laformt ⁇ r may ⁇ yerinde anl ⁇ k olarak yapmak neredeyse imkoptis ⁇ z hale gelmekte ve bir önceki ad ⁇ mdaki sorun ile tekrar karw ⁇ karcan ⁇ ya kal ⁇ nmaktad ⁇ r.
  • Bunun ard ⁇ ndan bulieri konusu yöntem çerçeveleri uzamsal olarak e whotleme i souplemidir.
  • Buna göre, çerçevelerdeki öznitelik noktalar ⁇ tespit edilir, bu noktalara dair öznitelik vektörleri hesaplan ⁇ r, iki çerçeve aras ⁇ nda öznitelik vektörleri yard ⁇ m ⁇ ile bu noktalar e whotlenir ve egrolewilden noktalar kullan ⁇ larak bir perspektif dönüwüm matrisi hesaplan ⁇ r.
  • Bilgi teorisinde iki matris üzerinde bulunan de ⁇ erler aras ⁇ nda mesafeleri hesaplamak için bagroka yollar da mevcuttur ve teknikte uzman bir ki exactly Hamming mesafesi hesaplamak yerine iki matris eleman ⁇ aras ⁇ ndaki mesafeyi bawka yollarla da hesaplayabilir.
  • Teknikte uzman bir ki might herhangi bir karw ⁇ laformt ⁇ rma algoritmas ⁇ kullanarak bu karcan ⁇ laformt ⁇ rmay ⁇ yapabilir.
  • Bu kapsamda gradyan, gri ölçekli bir görüntüdeki piksel de ⁇ erlerinin de ⁇ i provokemindeki büyüklü ⁇ ü ve aç ⁇ sal yönelimini gösteren vektör tan ⁇ mlan ⁇ r.
  • Buna göre, fark vektöründe bir e whokleme operasyonu uygulanarak de ⁇ i whomin oldu ⁇ u bölgeler tespit edilebilmektedir.
  • Uzunlu ⁇ u e whok de ⁇ erin üstünde olan bölgeler de ⁇ i accommodatekli ⁇ in oldu ⁇ u bölgeler olarak i wararetlenmektedir.
  • Bu sayede yola döwwenen may ⁇ nlar, el yap ⁇ m ⁇ patlay ⁇ c ⁇ lar ve benzeri terör faaliyetleri tespit edilememikos olsa dahi sonuçlar ⁇ itibariyle tespit edilip zarar vermeden imha edilebilir.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Computing Systems (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
  • Cosmetics (AREA)

Abstract

L'invention concerne un procédé mis au point pour comparer une vidéo avec une autre vidéo prise précédemment. Dans la présente invention, il n'est pas obligatoire pour lesdites deux vidéos d'indiquer la zone identique ; des processus de comparaison et de chevauchement sont effectués entre eux au moyen de divers solutions et procédés, les processus pour les équilibrages temporels et spatiaux sont effectués au moyen desdits deux procédés suite à la comparaison entre les images des deux vidéos et, ainsi les changements peuvent être présentés à l'utilisateur instantanément.
PCT/TR2019/051170 2018-12-20 2019-12-20 Procédé de détection de changements inter-vidéo Ceased WO2020130999A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
TR2018/19906 2018-12-20
TR2018/19906A TR201819906A2 (fr) 2018-12-20 2018-12-20

Publications (1)

Publication Number Publication Date
WO2020130999A1 true WO2020130999A1 (fr) 2020-06-25

Family

ID=67980208

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/TR2019/051170 Ceased WO2020130999A1 (fr) 2018-12-20 2019-12-20 Procédé de détection de changements inter-vidéo

Country Status (2)

Country Link
TR (1) TR201819906A2 (fr)
WO (1) WO2020130999A1 (fr)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1622081A1 (fr) * 2003-04-21 2006-02-01 NEC Corporation Dispositif de reconnaissance d'objets video et procede de reconnaissance, dispositif d'attribution d'annotation video, procede d'attribution et programme
US20140334668A1 (en) * 2013-05-10 2014-11-13 Palo Alto Research Center Incorporated System and method for visual motion based object segmentation and tracking
US20170134631A1 (en) * 2015-09-15 2017-05-11 SZ DJI Technology Co., Ltd. System and method for supporting smooth target following

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1622081A1 (fr) * 2003-04-21 2006-02-01 NEC Corporation Dispositif de reconnaissance d'objets video et procede de reconnaissance, dispositif d'attribution d'annotation video, procede d'attribution et programme
US20140334668A1 (en) * 2013-05-10 2014-11-13 Palo Alto Research Center Incorporated System and method for visual motion based object segmentation and tracking
US20170134631A1 (en) * 2015-09-15 2017-05-11 SZ DJI Technology Co., Ltd. System and method for supporting smooth target following

Also Published As

Publication number Publication date
TR201819906A2 (fr) 2019-03-21

Similar Documents

Publication Publication Date Title
Ni et al. Dynamics and patterns of a diffusive Leslie–Gower prey–predator model with strong Allee effect in prey
Mukherjee et al. Modified differential evolution with locality induced genetic operators for dynamic optimization
WO2020130999A1 (fr) Procédé de détection de changements inter-vidéo
Sorbelli et al. Range based algorithms for precise localization of terrestrial objects using a drone
JP2016093240A5 (fr)
BR112018074802A2 (pt) sistema e método de caracterização de materiais.
JP2015029557A5 (fr)
MY187801A (en) Gas-separation membranes having improved flux and selectivity
JP2017076309A5 (fr)
CN105651973B (zh) 服装面料悬垂度检测装置
Al-Saleh et al. First report of Tomato chlorosis virus (ToCV) in tomato crops in Saudi Arabia
Çatalbaş et al. A comparative study of classification methods for fall detection
Jo et al. First Report of Asian prunus virus 2 and Cherry virus A infecting japanese apricot (Prunus mume) in Korea
Sevimli et al. Range-Doppler radar target detection using compressive sensing
Man et al. Face automatic detection based on elliptic skin model and improved AdaBoost algorithm
JP2017080345A5 (fr)
Ran Expect the Unexpected
Collis et al. 1171; The development of influenza virus variants with reduced susceptibility following peramivir treatment: an analysis of clinical and post-marketing experience
Li et al. Compass Detection Algorithm based on Image Corner
MacKenzie et al. Fusarium Keratitis in Germany
Kulkarni et al. Cyclic GMP-AMP Synthase (cGAS), Stimulator Of Interferon Genes (STING) And Interferon Activated Gene 16 (IFI16) Are Essential For Intrinsic Lung Epithelial Responses Against Influenza A Infection, But Not For Therapeutically Induced Antiviral Resistance
Shu et al. Multiple Signal Estimation Using Weighting Music Algorithm
Çekli Position detection with spherical interpolation least squares based on time difference of arrivals using separated acoustic signals by independent component analysis
Imran et al. Systematic Comparison of Linear Feature Extraction Methods for Classification of Hyperspectral Images with Noises
Şahingil et al. The effects of directed infrared countermeasure systems on conical scan reticle seekers

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19901247

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19901247

Country of ref document: EP

Kind code of ref document: A1