WO2019132589A1 - Dispositif de traitement d'images et procédé de détection d'objets multiples - Google Patents

Dispositif de traitement d'images et procédé de détection d'objets multiples Download PDF

Info

Publication number
WO2019132589A1
WO2019132589A1 PCT/KR2018/016862 KR2018016862W WO2019132589A1 WO 2019132589 A1 WO2019132589 A1 WO 2019132589A1 KR 2018016862 W KR2018016862 W KR 2018016862W WO 2019132589 A1 WO2019132589 A1 WO 2019132589A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
position information
generating
deep learning
learning model
Prior art date
Application number
PCT/KR2018/016862
Other languages
English (en)
Korean (ko)
Inventor
김원태
강신욱
이명재
김동민
김신곤
김필수
김기동
노병필
문태준
Original Assignee
(주)제이엘케이인스펙션
대한민국(관세청장)
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 (주)제이엘케이인스펙션, 대한민국(관세청장) filed Critical (주)제이엘케이인스펙션
Publication of WO2019132589A1 publication Critical patent/WO2019132589A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20212—Image combination
    • G06T2207/20221—Image fusion; Image merging
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2210/00—Indexing scheme for image generation or computer graphics
    • G06T2210/12—Bounding box

Definitions

  • the present disclosure relates to an image processing apparatus and method for multi-object detection. More particularly, the present disclosure relates to an apparatus and method for learning a deep learning model for multi-object detection using a plurality of images including a single object, and a computer readable recording medium storing a program for executing the image processing method of the present disclosure And a recording medium.
  • Object recognition is processing for recognizing an area recognized as an object in an arbitrary image as one of a predetermined plurality of classes, and an object can mean a specific object in the image.
  • Deep learning learns a very large amount of data, and when new data is input, it selects the highest probability with probability based on the learning result, and it can adaptively operate according to the image
  • the artificial intelligence field there is an increasing tendency to utilize it in the field of artificial intelligence because it automatically finds the characteristic factor in the learning process of the model based on the data.
  • the technical object of the present disclosure is to provide an image processing apparatus and method for learning an image.
  • an image processing apparatus and method for generating object position information by distinguishing an object and a background from an image including a single object there is provided an image processing apparatus and method for generating object position information by distinguishing an object and a background from an image including a single object.
  • an image processing method including receiving a first image including a first object and a second image including a second object, and separating the object and the background with respect to each of the first image and the second image, An object region extracting unit; An object position information generating unit for generating position information of the first object and the second object; An image synthesizer for generating a third image including the first object and the second object based on the position information of the first object and the position information of the second object; And an object detection deep learning model learning unit for learning an object detection deep learning model using position information of the first object, position information of the second object, and the third image.
  • an image processing apparatus including an object region extracting unit for receiving an image including an object and distinguishing the object from a background, wherein the object region extracting unit compares a pixel value of the input image with a predetermined threshold value
  • An image processing apparatus may be provided for binarizing the pixel values and grouping the binarized pixel values to distinguish objects included in the input image.
  • an image processing method including an object region extracting step of receiving an image including an object and distinguishing the object and a background, wherein the object region extracting step comprises: And binarizing the pixel values and grouping the binarized pixel values to distinguish objects included in the input image.
  • a computer-readable recording medium having recorded thereon a program for executing the image processing method of the present disclosure can be provided.
  • an image processing apparatus and method for learning a deep learning model so that a multi-object image can be detected more accurately can be provided.
  • an image processing apparatus and method for learning a deep learning model for multiple object detection using a plurality of images including a single object can be provided.
  • an image processing apparatus and method for dividing an object and background from an image including a single object and generating object position information can be provided.
  • FIG. 1 is a block diagram showing the configuration of an image processing apparatus according to one embodiment of the present disclosure.
  • FIG. 2 is a diagram for explaining a process of dividing an object and a background in an image including a single object according to an embodiment of the present disclosure and generating position information of the object.
  • FIG. 3 is a diagram illustrating a process of generating a multi-object image using two images including a single object according to an embodiment of the present disclosure.
  • FIG. 4 is a diagram for explaining an embodiment of a composite neural network for generating a multi-channel feature map.
  • FIG. 5 is a diagram illustrating a process of learning a composite-object neural network using a multi-object image according to an embodiment of the present disclosure.
  • FIG. 6 is a diagram for explaining a process of analyzing an actual image using an image processing apparatus according to an embodiment of the present disclosure.
  • FIG. 7 is a diagram for explaining an image processing method according to an embodiment of the present disclosure.
  • first, second, etc. are used only for the purpose of distinguishing one element from another, and do not limit the order or importance of elements, etc. unless specifically stated otherwise.
  • a first component in one embodiment may be referred to as a second component in another embodiment, and similarly a second component in one embodiment may be referred to as a first component .
  • the components that are distinguished from each other are intended to clearly illustrate each feature and do not necessarily mean that components are separate. That is, a plurality of components may be integrated into one hardware or software unit, or a single component may be distributed into a plurality of hardware or software units. Thus, unless otherwise noted, such integrated or distributed embodiments are also included within the scope of this disclosure.
  • the components described in the various embodiments are not necessarily essential components, and some may be optional components. Thus, embodiments consisting of a subset of the components described in one embodiment are also included within the scope of the present disclosure. Also, embodiments that include other elements in addition to the elements described in the various embodiments are also included in the scope of the present disclosure.
  • FIG. 1 is a block diagram showing the configuration of an image processing apparatus according to one embodiment of the present disclosure.
  • the image processing apparatus 100 includes an object region extraction unit 110, an object position information generation unit 120, an image synthesis unit 130, and / or an object detection deep learning model learning unit 140 .
  • this shows only some components necessary for explaining the present embodiment, and the components included in the image processing apparatus 100 are not limited to the above-described examples.
  • two or more constituent units may be implemented in one constituent unit, and an operation performed in one constituent unit may be divided and executed in two or more constituent units.
  • some of the constituent parts may be omitted or additional constituent parts may be added.
  • the image processing apparatus 100 receives a first image including a first object and a second image including a second object, and acquires an object and a background for each of the first image and the second image, And generates a third image including the first object and the second object based on the position information of the first object and the position information of the second object,
  • the object detection deep learning model can be learned using the position information of the first object, the position information of the second object, and the third image.
  • the input image 150 may include an image including a single object.
  • the input image 150 may be an image related to a cargo including one object.
  • the input image 150 may be an X-ray image of the cargo taken by the X-ray reading device.
  • the image may be a raw image taken by an X-ray imaging device or an image in any form (format) for storing or transmitting the image.
  • the image may be obtained by capturing image data captured by an X-ray reading device and transmitting the image data to an output device such as a monitor and then data.
  • the object region extracting unit 110 may receive the image 150 including a single object and may divide the received image into an object and a background.
  • the object refers to a specific object in the image, and the background can refer to a part excluding an object from the image.
  • the object region extracting unit 110 according to an embodiment compares a pixel value of the input image 150 with a predetermined threshold value to binarize the pixel value and groups the binarized pixel values, You can distinguish objects. A specific process of extracting an object will be described later with reference to FIG.
  • the object position information generation unit 120 can determine the position of the object extracted from the object region extraction unit 110. For example, the object position information generation unit 120 specifies a bounding box surrounding the object region, and generates position information of the separated object in the object region extraction unit 110 based on the specified rectangular box can do. The specific process of generating the location information of the object will be described in more detail with reference to FIG.
  • the object region extraction unit 200 and the object position information generation unit 260 of FIG. 2 may be an embodiment of the object region extraction unit 110 and the object position information generation unit 120 of FIG. 1, respectively.
  • the input image 210 may be the input image 150 described with reference to FIG. 1 and may be, for example, an image relating to the cargo including the bag 212 as a single object.
  • the object region extracting unit 200 roughly cuts the surrounding region based on the bag 212 by performing a cropping operation on the input image 210 including one bag 212
  • the cropped image 220 can be acquired.
  • the object region extracting unit 200 may obtain the binarized image 230 by thresholding the pixel value of the cropped image 220 and a predetermined threshold value to binarize the pixel value.
  • the object region extracting unit 200 can obtain the grouped image 240 by grouping adjacent pixels to select a portion of the object from the binarized image 230. Then, the object region extracting unit 200 performs labeling and hole filling operations on the grouped image 240 to generate a pixel group formed in the largest shape as a region 252 for the object And determining the remainder as the area 254 for the background.
  • the object position information generation unit 260 can determine the position of the object in the input image 210 using the information about the object region image extracted by the object region extraction unit 200.
  • the object position information generation unit 260 specifies a bounding box surrounding the object region, and generates position information of the object classified by the object region extraction unit 200 based on the specified rectangular box can do.
  • the object position information generating unit 260 specifies a rectangular box 262 surrounding the bag 212 and acquires position information of the bag 212 based on the specified rectangular box have.
  • the position information of the bag 212 may be position information of four vertices forming the rectangular box 262, but is not limited thereto.
  • the position information may be represented by the coordinates (x, y) of one vertex of the rectangular box 262 and the width and height of the rectangular box.
  • the coordinates (x, y) of the one vertex may be the coordinates of the upper left vertex of the square box 262.
  • the coordinates (x, y) of the vertex can be specified based on the coordinates (0, 0) of the upper left vertex of the input image 210.
  • position information of an object included in an image can be automatically generated, it is possible to avoid the hassle of a readout source for directly inputting the positional information of an object for each image for artificial intelligence learning .
  • the image synthesis unit 130 generates a multi-object image using a plurality of single object images obtained by acquiring the position information of the object through the object region extraction unit 110 and the object position information generation unit 120 Can be generated.
  • the first image including the first object and the second image including the second object may be transmitted through the object region extracting unit 110 and the object position information generating unit 120, respectively.
  • the position information of the second object is obtained and the image combining unit 130 generates a third image including the first object and the second object based on the obtained position information of the first object and the position information of the second object can do.
  • a detailed process of generating a multi-object image will be described in detail with reference to FIG.
  • the image combining unit 300 of FIG. 3 is an embodiment of the image combining unit 130 of FIG. 3, the image combining unit 300 includes a first single object image 310, a second single object image 320, and a first single object image 320 obtained through an object region extracting unit and an object position information generating unit 310 and the second single object image 320 are included in the multi object image 340 and the multi object image 340 in which the first single object image 310 and the second single object image are combined And obtain location information 350 for the objects.
  • the image combining unit 300 may also use the image 330 for the background separated from the object when the first single object image 310 and the second single object image 320 are combined.
  • the object detection deep learning model learning unit 140 may learn an object detection deep learning model using position information of a first object, position information of a second object, and a third image.
  • the object detection deep learning model learning unit 140 can learn the artificial neural network model.
  • the position information of the first object, the position information of the second object, and the third image may be used for learning of the compound neural network model.
  • the combined-product neural network model will be described in more detail with reference to FIGS. 4 and 5.
  • FIG. 4 is a diagram for explaining an embodiment of a composite neural network for generating a multi-channel feature map.
  • the composite neural network of the present disclosure may be used to extract " features " such as borders, line colors, etc. from input data (images) and may include multiple layers. Each layer can receive input data and process the input data of the layer to generate output data.
  • the composite neural network can output the feature map generated by convoluting the input image or the input feature map with filter kernels as output data.
  • the initial layers of the composite product neural network may be operated to extract low level features such as edges or gradients from the input.
  • the next layers of the neural network can extract gradually more complex features such as eyes, nose, and so on.
  • the image processing based on the composite neural network can be applied to various fields. For example, image processing apparatuses for image object recognition, image processing apparatuses for image reconstruction, image processing apparatuses for semantic segmentation, image processing for scene recognition, Device or the like.
  • the input image 410 may be processed through the composite neural network 400 to output a feature map image.
  • the outputted feature map image can be utilized in various fields as described above.
  • the composite neural network 400 may be processed through a plurality of layers 420, 430, and 440, and each layer may output multi-channel feature map images 425 and 435.
  • a plurality of layers 420, 430, and 440 may extract a feature of an image by applying a filter having a predetermined size from a left top end to a right bottom end of input data.
  • the plurality of layers 420, 430, and 440 multiply the weights by the weighted upper left NxM pixels of the input data and map them to a neuron at the upper left of the feature map.
  • the weight to be multiplied will also be NxM.
  • the NxM may be, for example, 3x3, but is not limited thereto.
  • the plurality of layers 420, 430, and 440 scans input data from left to right and from top to bottom by k squares, and maps the weights to neurons of the feature map.
  • the k-th column means a stride for moving the filter when performing the product multiplication, and can be set appropriately to adjust the size of the output data.
  • k may be one.
  • the NxM weight is called a filter or filter kernel. That is, the process of applying the filter in the plurality of layers 420, 430, and 440 is a process of performing a convolution operation with the filter kernel. As a result, the extracted result is called a "feature map" Map image ".
  • the layer on which the convolution operation is performed may be referred to as a convolution layer.
  • the term " multiple-channel feature map " refers to a set of feature maps corresponding to a plurality of channels, and may be, for example, a plurality of image data.
  • the multi-channel feature maps may be inputs at any layer of the composite neural network, and may be output according to feature map computation results such as convolution operations.
  • the multi-channel feature maps 425, 435 are generated by a plurality of layers 420, 430, 440, also referred to as "feature extraction layers" or "convolutional layers” do. Each layer may sequentially receive the multi-channel feature maps generated in the previous layer and generate the next multi-channel feature maps as output.
  • L (L is an integer) th layer 440, multi-channel feature maps generated in the (L-1) th layer (not shown) are received to generate multi-channel feature maps.
  • the feature maps 425 having the channel K1 are outputs according to the feature map operation 420 in the layer 1 for the input image 410 and the feature map operation 430 in the layer 2 ≪ / RTI > Feature maps 435 with channel K2 are also outputs according to feature map operation 430 at layer 2 for input feature maps 425 and feature map operations (not shown) at layer 3, ≪ / RTI >
  • the multi-channel feature maps 425 generated in the first layer 420 include feature maps corresponding to K1 (K1 is an integer) channels.
  • the multi-channel feature maps 435 generated in the second layer 430 include feature maps corresponding to K2 (K2 is an integer) channels.
  • K1 and K2 which represent the number of channels, may correspond to the number of filter kernels used in the first layer 420 and the second layer 430, respectively. That is, the number of multi-channel feature maps generated in the Mth layer (M is an integer equal to or greater than 1 and equal to or smaller than L-1) may be equal to the number of filter kernels used in the Mth layer.
  • the object detection deep learning model learning unit 500 of FIG. 5 is an embodiment of the object detection deep learning model learning unit 140 of FIG. Referring to FIG. 5, a multi-object image 510 synthesized using single object images and location information of objects may be used as data necessary for learning.
  • the object detection deep learning model learning unit 500 can learn the composite neural network 520 by projecting the position information of each of the single objects together with the multi object image 510.
  • a superimposed X-Ray image of a plurality of objects can be obtained.
  • the artificial neural network is learned by using the shape of each object together with the position information of the objects of the object, the more accurate detection result can be obtained even when the overlap between the objects occurs.
  • FIG. 6 is a diagram for explaining a process of analyzing an actual image using an image processing apparatus according to an embodiment of the present disclosure.
  • the image processing apparatus 600 of FIG. 6 is an embodiment of the image processing apparatus 100 of FIG.
  • the object detecting apparatus 620 can detect each object using the artificial neural network model learned in the image processing apparatus 600 for an image 622 including multiple objects in a real environment.
  • the image processing apparatus 600 of the present disclosure when the present disclosure is applied to an electronic clearance system, the image processing apparatus 600 of the present disclosure generates a new multi-object embedded image based on a single object region extraction in an X-ray image .
  • the object detection apparatus 620 can also find an area where there are multiple objects contained in the cargo passing through the X-ray scanner. Therefore, by automatically extracting the position of the object with respect to the X-ray image, it is possible to more easily perform the image inspection operation by the readout source, and further, the information including the extracted object and the quantity information of the object in the cargo And can be used for comparison of computerized information.
  • FIG. 7 is a diagram for explaining an image processing method according to an embodiment of the present disclosure.
  • the first image including the first object and the second image including the second object may be input, and the object and the background may be distinguished for each of the first image and the second image. For example, a pixel value of an input image may be compared with a predetermined threshold value to binarize the pixel value, and binarized pixel values may be grouped to distinguish objects included in the input image.
  • step S710 location information of the first object and the second object may be generated. For example, a rectangular box surrounding the object area may be specified, and position information of the object classified in step S700 may be generated based on the specified rectangular box.
  • a third image including the first object and the second object may be generated based on the position information of the first object and the position information of the second object.
  • the third image including the first object and the second object may be generated based on the position information of the first object and the position information of the second object obtained in step S710.
  • the object detection deep learning model can be learned using the position information of the first object, the position information of the second object, and the third image. For example, it is possible to learn the compound neural network model. In order to learn the neural network model, the position information of the first object generated in step S710, the position information of the second object, and the third image generated in step S720 are used .
  • the present invention is not limited thereto, and the input image may be an image including two or more objects. In this case, it is possible to distinguish two or more objects and backgrounds from the input image, and generate position information for each of the two or more objects.
  • the description with reference to FIG. 2 when a plurality of pixel groups are formed, it can be determined that not only the pixel groups formed in the largest shape but also the other pixel groups are regions for the objects. The process of generating the position information of each determined object is the same as described for the image including one object.
  • the third image is generated based on the two single object images and the position information of the respective objects.
  • the present invention is not limited to this, and a third image may be generated using two or more single object images and position information of each object. That is, the image processing method and apparatus according to the present disclosure can generate a third image based on two or more images each including one or more objects and position information of each object.
  • the deep learning based model of the present disclosure can also be applied to a fully convoluted neural network, a convolutional neural network, a recurrent neural network, but is not limited to, at least one of a neural network, a restricted Boltzmann machine (RBM), and a deep belief neural network (DBN).
  • a machine running method other than deep running may be included.
  • a hybrid model combining deep running and machine running For example, a feature of an image may be extracted by applying a deep learning-based model, and a model based on a machine learning may be applied when an image is classified or recognized based on the extracted feature.
  • the machine learning based model may include, but is not limited to, a support vector machine (SVM), an AdaBoost, and the like.
  • the exemplary methods of this disclosure are represented by a series of acts for clarity of explanation, they are not intended to limit the order in which the steps are performed, and if necessary, each step may be performed simultaneously or in a different order.
  • the illustrative steps may additionally include other steps, include the remaining steps except for some steps, or may include additional steps other than some steps.
  • various embodiments of the present disclosure may be implemented by hardware, firmware, software, or a combination thereof.
  • one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays A general processor, a controller, a microcontroller, a microprocessor, and the like.
  • the present invention can be used to process images containing multiple objects.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Analysis (AREA)

Abstract

L'invention concerne un procédé et un dispositif de traitement d'images permettant d'apprendre un modèle d'apprentissage profond pour détecter de multiples objets à l'aide d'une pluralité d'images contenant chacune un objet unique. Selon l'invention, le procédé de traitement d'images comprend les étapes suivantes : une étape d'extraction de zone d'objet consistant à recevoir une première image contenant un premier objet et une deuxième image contenant un second objet, puis à établir une distinction entre l'objet et l'arrière-plan de chacune des première et deuxième images ; une étape de génération d'informations d'emplacement d'objet consistant à générer les informations d'emplacement des premier et second objets distingués ; une étape de synthèse d'image consistant à générer une troisième image contenant les premier et second objets d'après les informations d'emplacement du premier objet et les informations d'emplacement du second objet ; et une étape d'apprentissage de modèle d'apprentissage profond de détection d'objet consistant à apprendre un modèle d'apprentissage profond de détection d'objet à l'aide des informations d'emplacement du premier objet, des informations d'emplacement du second objet et de la troisième image.
PCT/KR2018/016862 2017-12-29 2018-12-28 Dispositif de traitement d'images et procédé de détection d'objets multiples WO2019132589A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR1020170183858A KR101932009B1 (ko) 2017-12-29 2017-12-29 다중 객체 검출을 위한 영상 처리 장치 및 방법
KR10-2017-0183858 2017-12-29

Publications (1)

Publication Number Publication Date
WO2019132589A1 true WO2019132589A1 (fr) 2019-07-04

Family

ID=65010274

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2018/016862 WO2019132589A1 (fr) 2017-12-29 2018-12-28 Dispositif de traitement d'images et procédé de détection d'objets multiples

Country Status (2)

Country Link
KR (1) KR101932009B1 (fr)
WO (1) WO2019132589A1 (fr)

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220092795A1 (en) * 2019-01-15 2022-03-24 Portland State University Feature pyramid warping for video frame interpolation
US10402978B1 (en) * 2019-01-25 2019-09-03 StradVision, Inc. Method for detecting pseudo-3D bounding box based on CNN capable of converting modes according to poses of objects using instance segmentation and device using the same
KR102145220B1 (ko) * 2019-02-14 2020-08-18 엔에이치엔 주식회사 딥러닝을 활용하여 2차원 이미지를 3차원 이미지로 변환하는 방법 및 장치
KR102315854B1 (ko) * 2019-02-20 2021-10-20 경북대학교 산학협력단 딥러닝 기반 학습 데이터 생성 방법 및 학습 데이터 생성 시스템
KR102193329B1 (ko) * 2019-03-27 2020-12-22 한국원자력 통제기술원 전략물자 식별을 위한 3차원 모델을 활용한 2차원 이미지 유사도 비교 시스템 및 그 방법
KR102247359B1 (ko) * 2019-07-31 2021-05-04 (주)유디피 원격 모니터링을 위한 영상 분석 시스템 및 방법
KR102315311B1 (ko) * 2019-10-31 2021-10-19 재단법인대구경북과학기술원 객체 검출 모델의 학습 방법 및 객체 검출 모델이 실행되는 객체 검출 장치
KR20210068713A (ko) 2019-12-02 2021-06-10 주식회사 피디젠 딥러닝 기반 다중의료데이터를 통한 질병의 진행 예측 분석 시스템
KR102139582B1 (ko) * 2019-12-05 2020-07-29 주식회사 인텔리빅스 다중 roi 및 객체 검출 dcnn 기반의 cctv 영상분석장치 및 그 장치의 구동방법
KR102295202B1 (ko) 2020-01-31 2021-08-27 중앙대학교 산학협력단 다중 객체 검출 방법 및 그 장치
CN111753730A (zh) * 2020-06-24 2020-10-09 国网电子商务有限公司 一种图像审查方法及装置
KR102571457B1 (ko) * 2021-11-29 2023-08-28 (주)테슬라시스템 인공지능 학습용 오클루젼된 이미지 형성 방법

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20140035660A (ko) * 2012-09-14 2014-03-24 한국전자통신연구원 객체 영역 추출 방법 및 그 장치
KR20140086491A (ko) * 2012-12-28 2014-07-08 삼성전자주식회사 합성 이미지를 촬영하는 촬영 장치 및 그 방법
KR20150043958A (ko) * 2013-10-15 2015-04-23 한국전자통신연구원 객체 인식장치 및 그 방법
KR20160096460A (ko) * 2015-02-05 2016-08-16 삼성전자주식회사 복수의 분류기를 포함하는 딥 러닝 기반 인식 시스템 및 그 제어 방법
KR20160108740A (ko) * 2015-03-06 2016-09-20 중앙대학교 산학협력단 작업 현장 영상 데이터 내의 작업자 인식 방법

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20140035660A (ko) * 2012-09-14 2014-03-24 한국전자통신연구원 객체 영역 추출 방법 및 그 장치
KR20140086491A (ko) * 2012-12-28 2014-07-08 삼성전자주식회사 합성 이미지를 촬영하는 촬영 장치 및 그 방법
KR20150043958A (ko) * 2013-10-15 2015-04-23 한국전자통신연구원 객체 인식장치 및 그 방법
KR20160096460A (ko) * 2015-02-05 2016-08-16 삼성전자주식회사 복수의 분류기를 포함하는 딥 러닝 기반 인식 시스템 및 그 제어 방법
KR20160108740A (ko) * 2015-03-06 2016-09-20 중앙대학교 산학협력단 작업 현장 영상 데이터 내의 작업자 인식 방법

Also Published As

Publication number Publication date
KR101932009B1 (ko) 2018-12-24

Similar Documents

Publication Publication Date Title
WO2019132589A1 (fr) Dispositif de traitement d'images et procédé de détection d'objets multiples
US11681418B2 (en) Multi-sample whole slide image processing in digital pathology via multi-resolution registration and machine learning
WO2019132588A1 (fr) Dispositif et procédé d'analyse d'image basés sur une caractéristique d'image et un contexte
CN103578116B (zh) 用于跟踪对象的设备和方法
US11023715B2 (en) Method and apparatus for expression recognition
WO2019132592A1 (fr) Dispositif et procédé de traitement d'image
WO2019132590A1 (fr) Procédé et dispositif de transformation d'image
KR20160143494A (ko) 현저성 정보 취득 장치 및 현저성 정보 취득 방법
CN107305635A (zh) 对象识别方法、对象识别装置和分类器训练方法
TW202014984A (zh) 一種圖像處理方法、電子設備及存儲介質
WO2015182904A1 (fr) Appareil d'étude de zone d'intérêt et procédé de détection d'objet d'intérêt
CN104135926A (zh) 图像处理设备、图像处理系统、图像处理方法以及程序
CN103093274B (zh) 基于视频的行人计数的方法
WO2019225964A1 (fr) Système et procédé de détection rapide d'objets
CN107766864B (zh) 提取特征的方法和装置、物体识别的方法和装置
JP2011003180A (ja) 画像収集装置に用いる天空検出装置及び方法
Lu et al. Robust 3D organ localization with dual learning architectures and fusion
CN112633297A (zh) 目标对象的识别方法、装置、存储介质以及电子装置
WO2022257314A1 (fr) Procédé de détection d'image, procédé d'apprentissage associé, appareil associé, dispositif et support
KR20190059083A (ko) 영상 분할 기반의 해양 상황 인식 장치 및 그 방법
WO2024077781A1 (fr) Procédé et appareil de reconnaissance d'image sur la base d'un modèle de réseau neuronal convolutif et dispositif terminal
CN113065568A (zh) 目标检测、属性识别与跟踪方法及系统
WO2019132093A1 (fr) Dispositif de détection de code à barres et procédé de détection de code à barres l'utilisant
CN111028263B (zh) 一种基于光流颜色聚类的运动物体分割方法及其系统
CN111368698A (zh) 主体识别方法、装置、电子设备及介质

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: 18893422

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: 18893422

Country of ref document: EP

Kind code of ref document: A1