WO2017211726A1 - Procédé mis en œuvre par ordinateur pour déterminer la taille réelle d'un objet cible dans une image numérique ou une image vidéo - Google Patents

Procédé mis en œuvre par ordinateur pour déterminer la taille réelle d'un objet cible dans une image numérique ou une image vidéo Download PDF

Info

Publication number
WO2017211726A1
WO2017211726A1 PCT/EP2017/063492 EP2017063492W WO2017211726A1 WO 2017211726 A1 WO2017211726 A1 WO 2017211726A1 EP 2017063492 W EP2017063492 W EP 2017063492W WO 2017211726 A1 WO2017211726 A1 WO 2017211726A1
Authority
WO
WIPO (PCT)
Prior art keywords
target object
digital image
video frame
pixel
horizontal
Prior art date
Application number
PCT/EP2017/063492
Other languages
English (en)
Inventor
Kenneth Gjerulff Obbekjær KRING
Original Assignee
Blue Sky Tec Aps
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 Blue Sky Tec Aps filed Critical Blue Sky Tec Aps
Publication of WO2017211726A1 publication Critical patent/WO2017211726A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes

Definitions

  • the present invention relates to a computer implemented method for determining the actual size of a target object within a digital image or video frame.
  • Building products or elements include products used in constructing/remodeling buildings, including non-residential commercial buildings, governmental buildings, and residential or home (single family and multi-family) buildings.
  • An improvement project may include a replacement of existing building products (e.g., windows, doors, siding, roof, and gutters), an addition to an existing structure, a new structure, a renovation, etc.
  • existing building products e.g., windows, doors, siding, roof, and gutters
  • the building products industry represents a long standing industry directed to manufacturing, delivering, and installing architectural products or elements, e.g., windows, fenestration appurtenances, doors, hardware, etc.
  • a further problem faced by dealers and contractors is providing the home/business owner with a representative visual representation ("visualization") of the final configured product or completed improvement project.
  • a system is needed that allows for easy retrieval of target dimensions (such as a window frame for a window opening in a wall), for visualization of presented product offerings for a specific target, and for firm quotes generated during the sales process.
  • a first aspect relates to a computer implemented method for determining the actual size of a target object within a digital image or video frame comprising the steps of:
  • a second aspect relates to a computer implemented method for determining the actual size of a target object within a digital image or video frame comprising the steps of:
  • v) determining the pixel per arbitrary length unit or the arbitrary length unit per pixel of the actual target object in the horizontal and/or vertical direction of the digital image or video frame; wherein the determination is made from a pre- calibrated curve or look-up table based on a digital image or video frame recorded of a reference object with a known size, and wherein the same pixel resolution and horizontal to vertical aspect ratio is used as the digital image or video frame comprising the target object;
  • step vi) is calculated/determined from a pre- calibrated curve or look-up table based on a digital image or video frame recorded of a reference object with a known size, and wherein the same pixel resolution and horizontal to vertical aspect ratio is used as the digital image or video frame comprising the target object.
  • a “target object” of the present invention refers to an object in the digital image or video frame having a constraint dimension that is measured by one or more methods of the present invention.
  • constraint dimension refers to a measured portion or a multiple of a measured portion of a target object to which a designed part is to conform and a “constraint pixel dimension” refers to the length of a constraint dimension measured in pixels.
  • a target object may contain a "symmetry element" which in the present invention refers to an aspect of the target object that in standard practice resides at a position within the target object such that the symmetry element divides a constraint dimension in an integer number of equal parts.
  • one or more aspects or embodiments of the present invention may be embodied as a system, method, computer program product or any combination thereof. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, micro-code, etc.) or an embodiment combining software and hardware aspects that may all generally be referred to herein as a "circuit,” "module” or “system.” Furthermore, the present invention may take the form of a computer program product embodied in any tangible medium of expression having computer usable program code embodied in the medium.
  • program modules include routines, programs, objects, components, data structures, etc., that perform particular tasks or implement particular abstract data types.
  • the invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network.
  • program modules may be located in both local and remote computer storage media including memory storage devices.
  • the computer-usable or computer-readable medium may be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory
  • the computer-usable or computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted, or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
  • a computer-usable or computer-readable medium may be any medium that can contain or store the program for use by or in connection with the instruction execution system, apparatus, or device.
  • Computer program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, Swift, C++, C# or the like and conventional procedural programming languages, such as the C programming language or similar programming languages.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
  • the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network
  • LAN local area network
  • wide area network LAN
  • WAN wide area network
  • Internet Service Provider any suitable Internet Service Provider
  • image-processing algorithms are used to identify a target object within the digital image or video frame.
  • Image processing algorithms are used to decipher certain attributes of the captured image frame.
  • the processor uses image processing algorithms to identify one or more discernable objects in the image frame and attempts to identify them.
  • the image processing may use edge detection techniques to identify one or more objects in the captured image.
  • identification algorithms are used to determine the likely identity of the object. Any number of techniques might be used for such a task.
  • the object might be normalized and compared to a database of possible objects using geometric and/or size analysis. If an object is viewed askew or at an angle, a normalization routine might rotate it and compensate for skew to result in a rectangular object.
  • the features of the image object can then be compared to the database of known rectangular objects having similar dimensional relationships, (e.g. ratio of length to width, such as other currency) and the denomination can be determined.
  • Other techniques such as morphological filters, look-up table, trained artificial neural network, some threshold, or an object repository of learned objects may be used as well.
  • the content of the image frame may in some embodiments be deciphered by processing the frame for edge pattern detection.
  • the processed edge pattern is classified by artificial neural networks that have been trained on a list of known objects, in a look up table, or by a threshold. Once the pattern is classified, a descriptive sentence is constructed consisting of the object and its certain attributes.
  • a graphical user interface for interactively selecting a target object is used to identify a target object within the digital image or video frame.
  • the computer comprises a processor and a memory coupled to the processor.
  • the memory is coupled to the processor, and the memory comprises program instructions implementing a graphical user interface for interactively selecting a target object.
  • Program instructions are executable by the processor for:
  • - processing a user input routine that processes selection of a control accepting manual selection by a user of a target object.
  • the manual selection of the target object is made directly on the digital image or video frame at one or more particular points on said digital image or video frame.
  • the computer/computing device may comprise a central processing unit (CPU), a host/PCI/cache bridge, and a main memory.
  • CPU central processing unit
  • main memory main memory
  • the CPU may comprise one or more general purpose CPU cores and optionally one or more special purpose cores (e.g., DSP core, floating point, etc.).
  • the one or more general purpose cores execute general purpose opcodes, while the special purpose cores executes functions specific to their purpose.
  • the CPU is coupled through the CPU local bus to a host/PCI/cache bridge or chipset.
  • a second level (i.e. L2) cache memory may be coupled to a cache controller in the chipset.
  • the external cache may comprise an L1 or first level cache.
  • the bridge or chipset couples to main memory via a memory bus.
  • the main memory comprises dynamic random access memory (DRAM) or extended data out (EDO) memory, or other types of memory such as ROM, static RAM, flash, and non-volatile static random access memory (NVSRAM), bubble memory, etc.
  • DRAM dynamic random access memory
  • EDO extended data out
  • ROM read-only memory
  • static RAM static RAM
  • flash flash
  • NVSRAM non-volatile static random access memory
  • bubble memory bubble memory
  • the computing device may also comprise various system components coupled to the CPU via system bus (e.g., PCI).
  • PCI peripheral component interconnect
  • the host/PCI/cache bridge or chipset interfaces to the system bus, such as peripheral component interconnect (PCI) bus.
  • PCI peripheral component interconnect
  • the system bus may comprise any of several types of well-known bus structures using any of a variety of bus architectures.
  • Example architectures include Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MCA) bus, Enhanced ISA (EISA) bus, Video Electronics Standards Associate (VESA) local bus and Peripheral Component Interconnect (PCI) also known as Mezzanine bus.
  • ISA Industry Standard Architecture
  • MCA Micro Channel Architecture
  • EISA Enhanced ISA
  • VESA Video Electronics Standards Associate
  • PCI Peripheral Component Interconnect
  • Various components connected to the system bus include, but are not limited to, a non-volatile memory (e.g., disk based data storage), a video/graphics adapter connected to a display, a user input interface (l/F) controller connected to one or more input devices such as a mouse, tablet, microphone, keyboard and modem, network interface controller, and/or a peripheral interface controller connected to one or more external peripherals, such as printer and speakers.
  • the network interface controller is coupled to one or more devices, such as data storage, remote computer running one or more remote applications, via a network, which may comprise the Internet cloud, a local area network (LAN), wide area network (WAN), storage area network (SAN), etc.
  • a small computer systems interface (SCSI) adapter may also be coupled to the system bus.
  • the SCSI adapter can couple to various SCSI devices such as a CD-ROM drive, tape drive, etc.
  • the non-volatile memory may include various removable/non-removable, volatile/nonvolatile computer storage media, such as hard disk drives that reads from or writes to non-removable, nonvolatile magnetic media, a magnetic disk drive that reads from or writes to a removable, nonvolatile magnetic disk, an optical disk drive that reads from or writes to a removable, nonvolatile optical disk such as a CD ROM or other optical media.
  • Other removable/non-removable, volatile/nonvolatile computer storage media that can be used in the exemplary operating environment include, but are not limited to, magnetic tape cassettes, flash memory cards, digital versatile disks, digital video tape, solid state RAM, solid state ROM, and the like.
  • a user may enter commands and information into the computer through input devices connected to the user input interface.
  • input devices include a keyboard and pointing device, mouse, trackball or touch pad.
  • Other input devices may include a microphone, joystick, game pad, satellite dish, scanner, etc.
  • the computer may operate in a networked environment via connections to one or more remote computers, such as a remote computer.
  • the remote computer may comprise a personal computer (PC), server, router, network PC, peer device or other common network node, and typically includes many or all of the elements described supra.
  • Such networking environments are commonplace in offices, enterprise-wide computer networks, intranets and the Internet.
  • the computer When used in a LAN networking environment, the computer is connected to the LAN via a network interface.
  • the computer When used in a WAN networking environment, the computer includes a modem or other means for establishing communications over the WAN, such as the Internet.
  • the modem which may be internal or external, is connected to the system bus via a user input interface, or other appropriate
  • the software adapted to implement the system and methods of the present invention can also reside in the cloud.
  • Cloud computing provides computation, software, data access and storage services that do not require end- user knowledge of the physical location and configuration of the system that delivers the services.
  • Cloud computing encompasses any subscription-based or pay-per-use service and typically involves provisioning of dynamically scalable and often virtualized resources.
  • Cloud computing providers deliver applications via the internet, which can be accessed from a web browser, while the business software and data are stored on servers at a remote location.
  • Computer readable media can be any available media that can be accessed by the computer and capable of storing for later reading by a computer a computer program implementing the method of this invention.
  • Computer readable media includes both volatile and nonvolatile media, removable and non-removable media.
  • Computer readable media may comprise computer storage media and communication media.
  • Computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data
  • Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer.
  • Communication media typically embodies computer readable instructions, data structures, program modules or other data such as a magnetic disk within a disk drive unit.
  • the software adapted to implement the system and methods of the present invention may also reside, in whole or in part, in the static or dynamic main memories or in firmware within the processor of the computer system (i.e. within microcontroller, microprocessor or microcomputer internal memory).
  • the computer implemented method further comprises the step of iv.b) correlating and/or correcting the object boundaries with a figure shape from a database; and wherein step vi) is based on the correlated and/or corrected figure shape. This is to refine the calculation by removing possible pixel errors or indirectly removing objects covering parts of the target object.
  • the computer implemented method further comprises the steps of v.b) adjusting the size of the target object in the digital image or video frame to contain as many pixels as possible within the pixel resolution limits of the original digital image or video frame, while retaining its original horizontal to vertical aspect ratio; and v.c) adjusting the in step v.a) calculated/determined pixel per arbitrary length unit or arbitrary length unit per pixel of the actual target object in the horizontal and/or vertical direction of the digital image or video frame to the resized target object.
  • This adjustment makes it easier to calculate/determine the actual size of the target object, since the minimum distance (L m in) thereby will be removed from the equation.
  • step v.a) is calculated/determined by using machine learning algorithms.
  • the inventor has found that deep neural network algorithms are particularly useful.
  • a third aspect relates to an apparatus for determining the actual size of a target object within a digital image or video frame comprising:
  • a fourth aspect relates to a computer program product for determining the actual size of a target object within a digital image or video frame, the computer program product comprising a readable memory device having computer readable program code stored thereon, including program code which, when executed, causes one or more processors to perform the steps of:
  • Figure 1 shows a digital image containing a target object that has already been identified, and its boundaries determined
  • Figure 2 shows that the minimum distance (L m in) from which a target object can be photographed depends on its size;
  • Figure 3 shows exemplary part of a look-up table
  • Figure 4 shows the target object in Figure 1 , adjusted to contain as many pixels as possible within the pixel resolution limits of the original digital image or video frame.
  • Figure 1 shows a digital image containing a target object that has already been identified, and its boundaries determined.
  • the minimum distance (L m in) from which a target object can be photographed depends on its size.
  • the number of pixels used to define the objects is the same. This observation is crucial for the present invention, as different sizes of objects will be defined by a different number of pixels per object arbitrary length unit (e.g. per mm) of the actual object. Hence, fewer pixels are available per area object for showing details in a larger object than in a smaller object. The lack or presence of details may be used to determine the number of pixels per object arbitrary length unit (e.g. per mm) of the actual object by using machine learning methods.
  • the number of pixels per object arbitrary length unit (e.g. per mm) of the actual object is used to calculate/determine the actual size of the target object.
  • the calculation/determination is made from a pre-calibrated curve or look-up table based on a digital image or video frame recorded of a reference object with a known size, and wherein the same pixel resolution and horizontal to vertical aspect ratio is used as the digital image or video frame comprising the target object.
  • An exemplary part of a look-up table is shown in Figure 3.
  • the size of the target object is adjusted to contain as many pixels as possible within the pixel resolution limits of the original digital image or video frame ( Figure 4), while retaining its original horizontal to vertical aspect ratio.
  • the calculated/determined number of pixels per object arbitrary length unit (e.g. per mm) of the actual object will be corrected

Abstract

La présente invention concerne un procédé mis en œuvre par ordinateur pour déterminer la taille réelle d'un objet cible dans une une image numérique ou une image vidéo. Le procédé comprend les étapes consistant à : i) obtenir une image numérique ou une image vidéo contenant un objet cible ; ii) obtenir des données concernant l'image numérique ou l'image vidéo contenant un objet cible, les données comprenant des informations concernant la résolution de pixel, et un rapport d'aspect horizontal à vertical ; iii) identifier un objet cible dans l'image numérique ou l'image vidéo ; iva) déterminer des limites de l'objet cible à partir de données de pixel dans l'image numérique ou l'image vidéo ; v) déterminer le pixel par unité de longueur arbitraire ou l'unité de longueur arbitraire par pixel de l'objet cible réel dans la direction horizontale et/ou verticale de l'image numérique ou de l'image vidéo ; la détermination étant effectuée à partir d'une courbe pré-étalonnée ou d'une table de consultation sur la base d'une image numérique ou d'une image vidéo enregistrée d'un objet de référence ayant une taille connue, et la même résolution de pixel et le même rapport d'aspect horizontal à vertical étant utilisés comme image numérique ou image vidéo comprenant l'objet cible ; et vi) calculer la taille réelle d'un objet cible à partir du nombre de pixels par unité de longueur arbitraire ou de l'unité de longueur arbitraire par pixel de l'objet cible réel dans la direction horizontale et/ou verticale de l'image numérique ou de l'image vidéo.
PCT/EP2017/063492 2016-06-08 2017-06-02 Procédé mis en œuvre par ordinateur pour déterminer la taille réelle d'un objet cible dans une image numérique ou une image vidéo WO2017211726A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DKPA201600335A DK179255B1 (en) 2016-06-08 2016-06-08 A computer implemented method for determining the actual size of a target object within a digital image/video frame
DKPA201600335 2016-06-08

Publications (1)

Publication Number Publication Date
WO2017211726A1 true WO2017211726A1 (fr) 2017-12-14

Family

ID=59014631

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2017/063492 WO2017211726A1 (fr) 2016-06-08 2017-06-02 Procédé mis en œuvre par ordinateur pour déterminer la taille réelle d'un objet cible dans une image numérique ou une image vidéo

Country Status (2)

Country Link
DK (1) DK179255B1 (fr)
WO (1) WO2017211726A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110147465A (zh) * 2019-05-23 2019-08-20 上海闻泰电子科技有限公司 图像处理方法、装置、设备和介质
US11636235B2 (en) 2019-04-15 2023-04-25 Awi Licensing Llc Systems and methods of predicting architectural materials within a space

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120169868A1 (en) * 2010-12-31 2012-07-05 Kt Corporation Method and apparatus for measuring sizes of objects in image
WO2013059599A1 (fr) * 2011-10-19 2013-04-25 The Regents Of The University Of California Outils de mesure fondée sur une image

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9230339B2 (en) * 2013-01-07 2016-01-05 Wexenergy Innovations Llc System and method of measuring distances related to an object
US8885916B1 (en) * 2014-03-28 2014-11-11 State Farm Mutual Automobile Insurance Company System and method for automatically measuring the dimensions of and identifying the type of exterior siding
US9342900B1 (en) * 2014-12-23 2016-05-17 Ricoh Co., Ltd. Distinguishing between stock keeping units using marker based methodology

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120169868A1 (en) * 2010-12-31 2012-07-05 Kt Corporation Method and apparatus for measuring sizes of objects in image
WO2013059599A1 (fr) * 2011-10-19 2013-04-25 The Regents Of The University Of California Outils de mesure fondée sur une image

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11636235B2 (en) 2019-04-15 2023-04-25 Awi Licensing Llc Systems and methods of predicting architectural materials within a space
CN110147465A (zh) * 2019-05-23 2019-08-20 上海闻泰电子科技有限公司 图像处理方法、装置、设备和介质

Also Published As

Publication number Publication date
DK201600335A1 (en) 2017-12-18
DK179255B1 (en) 2018-03-12

Similar Documents

Publication Publication Date Title
Zhang et al. Guided mesh normal filtering
US9607147B2 (en) Method and device for detecting software-tampering
US20180024943A1 (en) Risk identification based on address matching
CN111009002B (zh) 点云配准检测方法、装置以及电子设备、存储介质
US10192058B1 (en) System and method for determining an aggregate threat score
CN102713853B (zh) 使用文件流行程度通知行为试探的攻击性
WO2018103612A1 (fr) Procédé et appareil d'optimisation d'une politique d'autorisation, et support de stockage
CN111798360A (zh) 一种水印检测方法、装置、电子设备及存储介质
US20150278853A1 (en) System And Method For Identifying Hidden Content
US20170147387A1 (en) Identifying kernel data structures
WO2014105921A1 (fr) Atténuation de pixel redondant
WO2017211726A1 (fr) Procédé mis en œuvre par ordinateur pour déterminer la taille réelle d'un objet cible dans une image numérique ou une image vidéo
WO2021036442A1 (fr) Procédé et appareil de filtration lisse préservant les bords cycliques, et dispositif électronique
US20130182969A1 (en) Method and apparatus for correcting corner point of image and image processing device
US10163004B2 (en) Inferring stroke information from an image
US10846619B2 (en) Using machine learning system to dynamically modify device parameters
CN112001300B (zh) 基于按位置交叉熵的楼宇监控方法、装置和电子设备
US11361532B1 (en) System and method for OCR based object registration
CN108520259B (zh) 一种前景目标的提取方法、装置、设备及存储介质
CN114648673A (zh) 对抗样本的生成方法和装置
CN113420688A (zh) 自适应人脸识别处理方法、装置、电子设备及存储介质
CN112153298A (zh) 确定目标对象理想亮度的方法及装置
CN116739608B (zh) 基于人脸识别方式的银行用户身份验证方法及系统
CN114694146B (zh) 文本识别模型的训练方法、文本识别方法、装置及设备
CN109858012B (zh) 弹幕文本相似度计算方法、存储介质、设备及系统

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: 17728177

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: 17728177

Country of ref document: EP

Kind code of ref document: A1