WO2017169226A1 - 車種識別装置、車種識別システムおよび車種識別方法 - Google Patents
車種識別装置、車種識別システムおよび車種識別方法 Download PDFInfo
- Publication number
- WO2017169226A1 WO2017169226A1 PCT/JP2017/005488 JP2017005488W WO2017169226A1 WO 2017169226 A1 WO2017169226 A1 WO 2017169226A1 JP 2017005488 W JP2017005488 W JP 2017005488W WO 2017169226 A1 WO2017169226 A1 WO 2017169226A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- vehicle
- image
- vehicle type
- type identification
- rule
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/53—Querying
- G06F16/532—Query formulation, e.g. graphical querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
Definitions
- a vehicle recognition device that processes a captured image of a vehicle imaged by an imaging device such as a camera and discriminates the vehicle name of the vehicle is known (see Patent Document 1).
- Patent Document 1 includes a feature amount extraction unit that extracts a feature amount of a front grille of a vehicle from a captured image, and a feature amount storage unit that stores a feature amount of a front grill corresponding to each vehicle type of the vehicle.
- the vehicle name of the vehicle in which the feature value of the extraction means and the feature quantity of the feature value storage means are collated and the similarity is maximum and exceeds a predetermined threshold is captured in the captured image.
- a vehicle recognizing device for discriminating the above is disclosed.
- Patent Document 1 describes that the license plate of the vehicle, the left and right headlamps, the left and right fog lamps, the front spoiler, and the emblem relative positional relationship, and the feature amount of the front grille including these outer shapes are described. Yes.
- searching for the target vehicle type because it is determined by the characteristics of the front grill in general, if only the front grille is captured, the other parts are similar to the target vehicle type, but other parts include images that are not similar to the target vehicle type. There is a problem that the candidate images are extracted and the work becomes difficult.
- This disclosure is intended to provide a vehicle type identification device, a vehicle type identification system, and a vehicle type identification method capable of extracting a target vehicle with high accuracy by narrowing down to a specific partial area.
- a vehicle type identification device of the present disclosure is a vehicle type identification device that identifies a vehicle type of the vehicle based on a vehicle image of a vehicle imaged by an imaging device, and the vehicle type identification device includes a processor and a storage device.
- the vehicle image and a score indicating the certainty that the vehicle in the vehicle image is a specific vehicle type are recorded, and the processor specifies the vehicle type.
- the first vehicle image list that satisfies the search condition is extracted using the first rule based on the search condition and the score, and the first vehicle image list is displayed.
- the vehicle type identification system includes a display that displays the vehicle type identification device, the imaging device for imaging a vehicle, the vehicle image, the first vehicle image list, and the second vehicle image list.
- An apparatus that displays the vehicle type identification device, the imaging device for imaging a vehicle, the vehicle image, the first vehicle image list, and the second vehicle image list.
- the vehicle type identification method of the present disclosure is a vehicle type identification method for identifying a vehicle type of the vehicle based on a vehicle image of the vehicle imaged by an imaging device, the vehicle image being an image of the vehicle, and the vehicle image
- a step of recording a score indicating the certainty that the vehicle in the vehicle is a specific vehicle type a step of acquiring a search condition that is information for specifying the vehicle type, and the search condition and the score , Extracting a first vehicle image list that satisfies the search condition using a first rule, displaying the first vehicle image list on a display device, and specifying at least a part of the vehicle image Based on the step of obtaining the part specifying information, the step of generating a second rule based on the part specifying information, the search condition and the score, A extracting a second vehicle image list that applies to the search condition using a second rule that serial generated, a.
- FIG. 1 is a block diagram of a vehicle type identification system according to an embodiment of the present disclosure.
- FIG. 2 is a diagram illustrating a list table illustrating an example of a vehicle image DB according to the vehicle type identification system of the present disclosure.
- FIG. 3 is a diagram illustrating a list table illustrating an example of a score DB according to the vehicle type identification system of the present disclosure.
- FIG. 4 is a flowchart illustrating an example of a procedure for creating a vehicle image DB according to the vehicle type identification system of the present disclosure.
- FIG. 5A is a conceptual diagram illustrating an example of a partial region assigned in the vehicle type identification system of the present disclosure.
- FIG. 5B is a conceptual diagram illustrating an example of a partial region assigned in the vehicle type identification system of the present disclosure.
- FIG. 6 is a flowchart illustrating an example of a search procedure according to the vehicle type identification system of the present disclosure.
- FIG. 7 is a conceptual diagram illustrating an example of a list and a vehicle image displayed according to the first rule of the vehicle type identification system of the present disclosure.
- FIG. 8 is a conceptual diagram illustrating an example of a reference image displayed in the vehicle type identification system according to the present disclosure.
- FIG. 9 is a conceptual diagram illustrating an example of a list and vehicle images displayed according to the second rule of the vehicle type identification system of the present disclosure.
- FIG. 10A is a diagram showing an outline of the narrowing-down procedure, and is a diagram of vehicle images corresponding to the first vehicle image list L1 similar to FIG. FIG.
- this embodiment specifically discloses a vehicle type identification device, a vehicle type identification system, and a vehicle type identification method according to the present disclosure will be described in detail with reference to the drawings as appropriate. However, more detailed description than necessary may be omitted. For example, detailed descriptions of already well-known matters and repeated descriptions for substantially the same configuration may be omitted. This is to avoid the following description from becoming unnecessarily redundant and to facilitate understanding by those skilled in the art.
- the accompanying drawings and the following description are provided to enable those skilled in the art to fully understand the present disclosure, and are not intended to limit the claimed subject matter.
- FIG. 1 is a block diagram showing a hardware configuration for realizing the vehicle type identification system of the present disclosure.
- the hardware configuration for realizing the vehicle type identification system 1 includes an imaging device 2, a display device 3, a vehicle type identification device 4, and a bus 5 that connects them.
- the vehicle type identification device 4 includes an input device 6, a storage device 7, and a processor 8.
- the input device 6 of the vehicle type identification device 4 is an operation unit that operates the vehicle type identification device 4 with an input device such as a keyboard or a mouse.
- the input device 6 is used when a user inputs various commands to the vehicle type identification device 4 and changes or updates information in a database (DB).
- DB database
- the storage device 7 of the vehicle type identification device 4 is, for example, a RAM, a ROM, a hard disk or the like.
- the storage device 7 stores various programs and various data for realizing each function of the vehicle type identification system 1, and a vehicle basic DB, a vehicle image DB, a score DB, and the like, which are used for vehicle type identification processing, which will be described later. .
- a list of the vehicle image DB and the score DB stored in the storage device 7 will be described with reference to FIGS.
- FIG. 2 shows an example of a vehicle image DB stored in the storage device 7.
- vehicle image DB “image time” of the date of the image taken by the image pickup device 2 corresponding to “image name” and “image name”, which are the numbers of vehicle images taken by the image pickup device 2 and used as keys of the database.
- Imaging device ID "which is the number of the imaging device 2 assigned to each imaging device 2 that has captured each vehicle image is registered.
- a “number plate” of a vehicle imaged as vehicle information, “number plate coordinates (X, Y)” for extracting a front image and specifying a partial region R, and the like are also registered.
- FIG. 3 shows an example of the score DB stored in the storage device 7.
- the score DB an “image name” corresponding to the vehicle image DB and a “partial region No” of each partial region R are automatically generated.
- a score for each vehicle type is defined in each partial region R.
- the score is a value indicating the certainty that the partial area is a partial area of a specific vehicle type.
- the score is calculated by applying the feature amount automatically calculated in each partial region R to a score calculation model defined in advance for each partial region R for each vehicle type and registered in the vehicle basic DB.
- the automatically calculated feature quantity for example, HOG (Histograms of Oriented Gradients) feature quantity or dense SIFT (Scale-Invariant Feature Transform) feature quantity may be cited.
- FIG. 4 is a flowchart showing an example of creating a score DB. The procedure for creating the score DB will be described with reference to FIG.
- the processor 8 calculates a score by applying the calculated feature amount for each partial region R to a score calculation model that is defined in advance for each partial region R for each vehicle type and registered in the vehicle basic DB. (ST104).
- the processor 8 registers the calculated score (for example, 0.86) as the score of the vehicle type A of the partial region R0 of the image img00001, and sequentially calculates the score value calculated for each image and each partial region as the vehicle type score. It is registered in the score DB stored in the storage device 7 (ST105).
- the processor 8 of the vehicle type identification device 4 is a CPU or the like, reads various programs from the storage device 7, acquires search conditions, extracts a vehicle image list, calculates feature values in the partial region R of the vehicle, and performs data processing. To control the entire vehicle type identification system 1.
- FIG. 6 is a flowchart showing an example of searching for a vehicle type.
- the user inputs search conditions to the input device 6.
- the search conditions are, for example, a vehicle type, an imaging device ID, a shooting time range, and the like.
- the search condition can be said to be information for specifying a target vehicle image. For example, if the user wants to search for a vehicle image “an image obtained by imaging the vehicle type AAA and taken by an imaging device near the A intersection at around ** month, day, day,” enter search conditions. It is sufficient to express such a condition by using.
- the search condition includes at least a vehicle type. A part of the search condition may be a wild card.
- the processor 8 acquires the search condition (ST201).
- the processor 8 sets a score calculation rule, which is a rule composed of the partial area R and the weight of each partial area (R0, R1,...) (ST203).
- the calculation rule set in ST203 is a rule (first rule) used for primary narrowing based on the vehicle type in the search condition.
- the first rule is preferably a universal rule.
- the processor 8 reads the score of the vehicle image in the search target image list from the score DB (ST204).
- the processor 8 calculates a discrimination score according to the score of the vehicle image read in ST204 and the calculation rule (ST205).
- the discrimination score is a score calculated by applying the score of the vehicle image to the calculation rule.
- ST205 a discrimination score is calculated for each vehicle image for all vehicle types that can be search conditions.
- the first rule is a rule that weights the entire partial region R equally. Therefore, the discrimination score for the vehicle type “A” of img00001 is (0.86 + 0.01 + 0.77 + 0.45 + 0.23 + 0. 65) divided by 6.
- the processor 8 performs vehicle type discrimination for discriminating which vehicle type the vehicle image is based on the discrimination score (ST206).
- Various rules can be considered for causing the processor 8 to discriminate which vehicle type the vehicle image is based on the discrimination score. For example, you may make the processor 8 discriminate
- the processor 8 updates the display target image list based on the vehicle type discrimination result (ST207). If the vehicle type determined for the vehicle image is the search target vehicle type, the processor 8 adds the vehicle image to the display target image list.
- the display target image list is a list including information including information existing in the vehicle image DB such as the date and time when the vehicle image was captured and the imaging device ID that captured the vehicle image.
- the processor 8 displays a display target image list and a plurality of vehicle images corresponding to the display target image list on the display device 3 (ST208) (see FIG. 7).
- the first vehicle image list L1 is displayed on the display device 3 as an example of the display target image list.
- a plurality of vehicle images corresponding to the first vehicle image list L1 are displayed on the display device 3 as an example of a plurality of vehicle images corresponding to the display target image list.
- the processor 8 displays a reference image (for example, catalog image: see FIG. 8) of the search target vehicle type (ST209).
- a reference image for example, catalog image: see FIG. 8 of the search target vehicle type (ST209).
- the user compares the reference image with a plurality of vehicle images corresponding to the first vehicle image list L1
- the user can clearly select a vehicle image that feels different from the reference image among the vehicle images displayed in ST208. It ’s different from the target model. ”
- the user can determine that the vehicle image that feels close to the reference image is “it seems to be the target vehicle type”.
- the reference image functions as a guideline for selecting a target vehicle type.
- Search can be performed automatically. If the user's skill is high, the target vehicle type can be determined without referring to the reference image, so that the reference image may not be displayed on the display device 3.
- a user who has visually recognized a plurality of displayed vehicle images includes a vehicle image including a vehicle that is likely to be a target vehicle type, and a vehicle image including a vehicle that is different from the target vehicle type. Recognize that both are included.
- the user performs the following operation in order to increase the ratio of vehicle images including a vehicle that is likely to be the target vehicle type among the plurality of displayed vehicle images.
- the user designates the vicinity of the headlamp as the specific partial region R0 using the input device 6 from among a plurality of partial regions R (see FIG. 5A) divided in advance in a vehicle image including a vehicle that is likely to be the target vehicle type. (Refer to the hatched portion in FIG. 5B).
- the designation is performed by clicking a part of the vehicle image.
- designated should just specify a partial area
- the processor 8 acquires the user's designation as narrowing-down information that identifies at least a partial region R of the vehicle image (YES in ST210).
- the processor 8 updates the search target image list (first vehicle image list L1) to the display target image list (ST211).
- the population to be searched in later processing is narrowed down from the search target image list that is the population extracted in the latest ST202.
- the processor 8 updates the score calculation rule as the second rule based on the narrowing down information (ST212).
- the second rule based on the narrowing down information.
- (1) only the specific partial region R in which the part specified by the refinement information exists can be set as the partial region R used in the second rule (calculation rule). This means that the first rule is changed so that the weight of the specific partial region R is 1 and the other partial regions are 0.
- (2) The weight of the specific partial region R is increased more than other partial regions (for example, the weight of the specific partial region R0 is 0.5, and the weights of the other partial regions R1, R2,. Or the weight of the specific partial region R0 is 1 and the weights of the other partial regions R1, R2,.
- the first rule set in ST203 is a rule for calculating a universally obtained score regardless of the location of the partial area.
- the second rule set in ST212 is a rule for calculating a score by imparting bias to the score of the specific partial region R.
- the processor 8 generates the second rule, calculates the discrimination score of ST205, performs vehicle type discrimination using the discrimination score based on the second rule (ST206), the second vehicle image list L2 and the second vehicle
- the vehicle image corresponding to L2 is displayed on the display device 3 in the image list (ST208) (see FIG. 9). With reference to the display result, the user can identify the vehicle image in which the target vehicle type is captured, and can find the target vehicle type at an early stage.
- FIG. 10A is the same as FIG. 7 and is displayed as a vehicle image corresponding to the first vehicle image list L1 of the user.
- FIG. 10B corresponds to FIG. 5B and shows that a specific partial region (for example, R0) is designated by the user and further refined search is performed.
- FIG. 10C is a display of a refinement search result corresponding to FIG. 9, and the vehicle image is refined. If it is determined that there are many vehicle images searched in the search result, it is possible to specify another specific partial area (for example, R2) and perform the search again.
- another specific partial area for example, R2
- the vehicle type identification device 4 of the present embodiment is the vehicle type identification device 4 that identifies the vehicle type of the vehicle based on the vehicle image of the vehicle imaged by the imaging device 2, and the vehicle type identification device 4 is a processor. 8 and a storage device 7, and the storage device 7 is recorded with a vehicle image that is an image of the vehicle and a score that indicates the certainty that the vehicle is a specific vehicle type.
- the score is defined for each of the plurality of partial regions R in the vehicle image, and the second rule is the score of at least one partial region (for example, R0).
- This is a rule for increasing the weight of the first rule compared to the first rule. Thereby, it can narrow down by the partial area R with the characteristic of a vehicle model, and narrowing down with more accuracy is attained.
- the second rule uses the score of only at least one partial area. As a result, the comparison is easy in the characteristic partial region R of the vehicle type, and an efficient search is possible.
- the first rule is a rule using a score obtained by equally weighting all the partial regions R of the front image in the vehicle image
- the second rule is In this rule, the score weight of at least one partial region R included in the front image is made larger than the score weight of other partial regions R included in the front image.
- the score is calculated based on the feature amount of each partial region R. Thereby, the difference in the score in each partial region R is obtained, and narrowing down of the partial regions R becomes easy.
- the processor 8 uses the first vehicle image list L1 or the second vehicle image as the reference image obtained by imaging the same type of vehicle as the vehicle image that meets the search condition.
- the information is displayed on the display device 3 together with the vehicle image list L2.
- the vehicle type identification system 1 of the present embodiment includes the vehicle type identification device 4, the imaging device 2 for imaging the vehicle, the vehicle image, the first vehicle image list L1, and the second vehicle image list L2. And a display device 3 for displaying. Thereby, it is possible to construct a system that can narrow down to a specific partial area and extract a target vehicle with high accuracy.
- the vehicle type identification method of the present embodiment is a vehicle type identification method for identifying the vehicle type of the vehicle based on the vehicle image of the vehicle imaged by the imaging device 2, and includes a vehicle image that is an image of the vehicle imaged and A step of recording a score indicating the certainty that the vehicle is a specific vehicle type, a step of acquiring a search condition that is information for specifying the vehicle type, a first condition based on the search condition and the score, A step of extracting a first vehicle image list L1 that satisfies a search condition using a rule; a step of displaying the first vehicle image list L1 on the display device 3; and part specifying information for specifying at least a part of the vehicle image.
- a extracting a second vehicle image list L2 is true search conditions, a.
- the vehicle type identification device, the vehicle type identification system, and the vehicle type identification method of the present disclosure are useful for applications in which a target vehicle can be found early from a large number of vehicle images.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
Description
図1から図5を用いて車種識別システムの一例の構成を説明する。
図6から図10Cに基づいて、本開示の車種識別装置4の具体的な動作について説明する。以下の説明においてはユーザが特定の車両画像を、それまでに撮像した車両画像から検索する流れと併せて車種識別装置4の具体的な動作を説明する。
2 撮像装置
3 表示装置
4 車種識別装置
5 バス
6 入力装置
7 記憶装置
8 プロセッサ
L1 第1の車両画像リスト
L2 第2の車両画像リスト
R 部分領域
Claims (10)
- 撮像装置により撮像された車両の車両画像に基づいて前記車両の車種を識別する車種識別装置であって、
当該車種識別装置は、プロセッサと、記憶装置と、を有し、
前記記憶装置には、前記車両画像と、前記車両画像中の前記車両が特定の車種であることの確からしさを示すスコアと、が記録されており、
前記プロセッサは、
車種を特定するための情報を含む検索条件を取得し、
前記検索条件および前記スコアに基づき、第1のルールを用いて前記検索条件に当てはまる第1の車両画像リストを抽出し、
前記第1の車両画像リストを表示装置に表示し、
前記車両画像の少なくとも一部分を特定する部分特定情報を取得し、
前記部分特定情報に基づいて第2のルールを生成し、
前記検索条件および前記スコアに基づき、前記生成した第2のルールを用いて前記検索条件に当てはまる第2の車両画像リストを抽出する、
車種識別装置。 - 請求項1に記載の車種識別装置であって、
前記スコアが、前記車両画像内の複数の部分領域の各々に定義されており、
前記第2のルールが、少なくとも一つの部分領域のスコアの重みを、前記第1のルールに比べて大きくするルールである、車種識別装置。 - 請求項2に記載の車種識別装置であって、
前記第2のルールが、前記少なくとも一つの部分領域のみのスコアを用いる、車種識別装置。 - 請求項2に記載の車種識別装置であって、
前記第1のルールが、前記車両画像内のフロント画像の全部分領域を均等に重み付けして得られるスコアを用いるルールであり、
前記第2のルールが、前記フロント画像に含まれる少なくとも一つの部分領域のスコアの重みを、前記フロント画像に含まれる他の部分領域のスコアの重みに比べて大きくするルールである、車種識別装置。 - 請求項2に記載の車種識別装置であって、
前記スコアが、各部分領域の特徴量に基づき算出される、車種識別装置。 - 請求項5に記載の車種識別装置であって、
前記特徴量が、dense SIFT(Scale-Invariant Feature Transform)により
算出される数値である、車種識別装置。 - 請求項1に記載の車種識別装置であって、
前記プロセッサが、前記第2のルールを用いて、前記第1の車両画像リストを、より車両画像数の少ない前記第2の車両画像リストに絞り込む、車種識別装置。 - 請求項1に記載の車種識別装置であって、
前記プロセッサが、前記検索条件に当てはまる車両画像の車両と同種の車両を撮像して得られる参照画像を、前記第1の車両画像リストまたは前記第2の車両画像リストとともに前記表示装置に表示する、車種識別装置。 - 請求項1に記載の車種識別装置と、
車両を撮像するための前記撮像装置と、
前記車両画像、前記第1の車両画像リストと、前記第2の車両画像リストとを表示する表示装置と、
を備えた車種識別システム。 - 撮像装置により撮像された車両の車両画像に基づいて前記車両の車種を識別する車種識別方法であって、
車種識別方法は、
車両が撮像された画像である車両画像と、前記車両画像中の前記車両が特定の車種であることの確からしさを示すスコアと、を記録し、
車種を特定するための情報である検索条件を取得し、
前記検索条件および前記スコアに基づき、第1のルールを用いて前記検索条件に当てはまる第1の車両画像リストを抽出し、
前記第1の車両画像リストを表示装置に表示し、
前記車両画像の少なくとも一部分を特定する部分特定情報を取得し、
前記部分特定情報に基づいて第2のルールを生成し、
前記検索条件および前記スコアに基づき、前記生成した第2のルールを用いて前記検索条件に当てはまる第2の車両画像リストを抽出する、
車種識別方法。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP17773774.9A EP3438851A4 (en) | 2016-03-29 | 2017-02-15 | VEHICLE MODEL IDENTIFICATION DEVICE, VEHICLE MODEL IDENTIFICATION SYSTEM, AND VEHICLE MODEL IDENTIFICATION METHOD |
US16/088,546 US20190114494A1 (en) | 2016-03-29 | 2017-02-15 | Vehicle model identification device, vehicle model identification system, and vehicle model identification method |
CN201780020732.9A CN108885636A (zh) | 2016-03-29 | 2017-02-15 | 车型识别装置、车型识别系统以及车型识别方法 |
JP2018508543A JP6906144B2 (ja) | 2016-03-29 | 2017-02-15 | 車種識別装置、車種識別システム、車種識別方法および車種識別プログラム |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2016-065192 | 2016-03-29 | ||
JP2016065192 | 2016-03-29 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2017169226A1 true WO2017169226A1 (ja) | 2017-10-05 |
Family
ID=59963042
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2017/005488 WO2017169226A1 (ja) | 2016-03-29 | 2017-02-15 | 車種識別装置、車種識別システムおよび車種識別方法 |
Country Status (5)
Country | Link |
---|---|
US (1) | US20190114494A1 (ja) |
EP (1) | EP3438851A4 (ja) |
JP (1) | JP6906144B2 (ja) |
CN (1) | CN108885636A (ja) |
WO (1) | WO2017169226A1 (ja) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108446612A (zh) * | 2018-03-07 | 2018-08-24 | 腾讯科技(深圳)有限公司 | 车辆识别方法、装置及存储介质 |
CN111178292A (zh) * | 2019-12-31 | 2020-05-19 | 东软集团(北京)有限公司 | 一种车型识别方法、装置及设备 |
JP2020144722A (ja) * | 2019-03-08 | 2020-09-10 | オムロン株式会社 | 車種判定装置、車種判定方法、および車種判定プログラム |
CN111861680A (zh) * | 2020-08-06 | 2020-10-30 | 南京三百云信息科技有限公司 | 基于配置的车型确定方法、装置以及电子终端 |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10640060B2 (en) * | 2016-03-17 | 2020-05-05 | Innova Electronics Corporation | Vehicle repair shop pre-inspection and post-inspection verification system |
JP6791200B2 (ja) * | 2018-05-11 | 2020-11-25 | トヨタ自動車株式会社 | 捜索支援システム、捜索支援装置、及び、捜索支援方法 |
CN111222409A (zh) * | 2019-11-26 | 2020-06-02 | 北京迈格威科技有限公司 | 车辆品牌的标注方法、装置及系统 |
US20210241208A1 (en) * | 2020-01-31 | 2021-08-05 | Capital One Services, Llc | Method and system for identifying and onboarding a vehicle into inventory |
CN115039157A (zh) * | 2020-02-07 | 2022-09-09 | 三菱电机楼宇解决方案株式会社 | 停车车辆搜索系统 |
US11429664B1 (en) * | 2022-03-21 | 2022-08-30 | Verkada Inc. | Hyperzoom attribute analytics on the edge |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH11213284A (ja) * | 1998-01-28 | 1999-08-06 | Mitsubishi Electric Corp | 車種判別装置 |
JP2007299144A (ja) * | 2006-04-28 | 2007-11-15 | Mitsubishi Heavy Ind Ltd | ロゴ判別装置および方法ならびにプログラム |
JP2010102466A (ja) * | 2008-10-23 | 2010-05-06 | Omron Corp | 車両認識装置 |
JP2014002534A (ja) * | 2012-06-18 | 2014-01-09 | Toshiba Corp | 車種判別装置及び車種判別方法 |
Family Cites Families (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7680324B2 (en) * | 2000-11-06 | 2010-03-16 | Evryx Technologies, Inc. | Use of image-derived information as search criteria for internet and other search engines |
US7920716B2 (en) * | 2003-12-25 | 2011-04-05 | Fujitsu Limited | Vehicle search system and vehicle search method |
US20050267657A1 (en) * | 2004-05-04 | 2005-12-01 | Devdhar Prashant P | Method for vehicle classification |
JP4715664B2 (ja) * | 2006-07-27 | 2011-07-06 | 株式会社日立製作所 | 車両検索システム |
US8392432B2 (en) * | 2010-04-12 | 2013-03-05 | Microsoft Corporation | Make and model classifier |
EP2601617A4 (en) * | 2010-08-05 | 2017-12-06 | Hi-Tech Solutions Ltd. | Method and system for collecting information relating to identity parameters of a vehicle |
CN102567380A (zh) * | 2010-12-28 | 2012-07-11 | 沈阳聚德视频技术有限公司 | 在视频图像中检索车辆信息的方法 |
US9466000B2 (en) * | 2011-05-19 | 2016-10-11 | The Regents Of The University Of California | Dynamic Bayesian Networks for vehicle classification in video |
JP5423755B2 (ja) * | 2011-09-28 | 2014-02-19 | 富士通株式会社 | 特定部位抽出プログラム |
JP5974448B2 (ja) * | 2011-10-25 | 2016-08-23 | 富士通株式会社 | 車両情報登録方法、車両情報登録装置、及び車両情報登録プログラム |
CN105320705B (zh) * | 2014-08-05 | 2018-09-14 | 北京大学 | 相似车辆的检索方法及装置 |
-
2017
- 2017-02-15 WO PCT/JP2017/005488 patent/WO2017169226A1/ja active Application Filing
- 2017-02-15 US US16/088,546 patent/US20190114494A1/en not_active Abandoned
- 2017-02-15 JP JP2018508543A patent/JP6906144B2/ja active Active
- 2017-02-15 CN CN201780020732.9A patent/CN108885636A/zh active Pending
- 2017-02-15 EP EP17773774.9A patent/EP3438851A4/en not_active Withdrawn
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH11213284A (ja) * | 1998-01-28 | 1999-08-06 | Mitsubishi Electric Corp | 車種判別装置 |
JP2007299144A (ja) * | 2006-04-28 | 2007-11-15 | Mitsubishi Heavy Ind Ltd | ロゴ判別装置および方法ならびにプログラム |
JP2010102466A (ja) * | 2008-10-23 | 2010-05-06 | Omron Corp | 車両認識装置 |
JP2014002534A (ja) * | 2012-06-18 | 2014-01-09 | Toshiba Corp | 車種判別装置及び車種判別方法 |
Non-Patent Citations (1)
Title |
---|
See also references of EP3438851A4 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108446612A (zh) * | 2018-03-07 | 2018-08-24 | 腾讯科技(深圳)有限公司 | 车辆识别方法、装置及存储介质 |
JP2020144722A (ja) * | 2019-03-08 | 2020-09-10 | オムロン株式会社 | 車種判定装置、車種判定方法、および車種判定プログラム |
JP7525247B2 (ja) | 2019-03-08 | 2024-07-30 | オムロン株式会社 | 車種判定装置、車種判定方法、および車種判定プログラム |
CN111178292A (zh) * | 2019-12-31 | 2020-05-19 | 东软集团(北京)有限公司 | 一种车型识别方法、装置及设备 |
CN111861680A (zh) * | 2020-08-06 | 2020-10-30 | 南京三百云信息科技有限公司 | 基于配置的车型确定方法、装置以及电子终端 |
CN111861680B (zh) * | 2020-08-06 | 2024-03-29 | 南京三百云信息科技有限公司 | 基于配置的车型确定方法、装置以及电子终端 |
Also Published As
Publication number | Publication date |
---|---|
JPWO2017169226A1 (ja) | 2019-02-07 |
EP3438851A1 (en) | 2019-02-06 |
CN108885636A (zh) | 2018-11-23 |
US20190114494A1 (en) | 2019-04-18 |
JP6906144B2 (ja) | 2021-07-21 |
EP3438851A4 (en) | 2019-02-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2017169226A1 (ja) | 車種識別装置、車種識別システムおよび車種識別方法 | |
CN107358596B (zh) | 一种基于图像的车辆定损方法、装置、电子设备及系统 | |
JP4947185B2 (ja) | 車両検索システムおよび車両検索方法 | |
JP2022093550A (ja) | 情報処理装置、情報処理方法及びプログラム | |
KR101834778B1 (ko) | 교통 표지판 인식장치 및 방법 | |
JP4721830B2 (ja) | 画像検索方法及び装置 | |
US20180268252A1 (en) | Vehicle model identification device, vehicle model identification system comprising same, and vehicle model identification method | |
JP5103955B2 (ja) | 画像検索方法、装置およびプログラム | |
KR102195940B1 (ko) | 적응적 비최대억제 방법을 이용하는 딥러닝기반 영상객체 탐지를 위한 장치 및 방법 | |
CN111222409A (zh) | 车辆品牌的标注方法、装置及系统 | |
JP2013092905A (ja) | 車両情報登録方法、車両情報登録装置、及び車両情報登録プログラム | |
CN110008362A (zh) | 一种案件归类方法及装置 | |
JP2014115961A (ja) | 情報処理装置、車両識別方法、及び車両識別プログラム | |
JP5004082B2 (ja) | 文書画像検索方法、文書画像登録方法、そのプログラムおよび装置 | |
JP2005209177A (ja) | 車両検索システムおよび車両検索方法 | |
JP2898562B2 (ja) | ナンバープレート決定方法 | |
US11651582B2 (en) | Individual identification system | |
JP5327241B2 (ja) | 物体識別装置 | |
CN113657378B (zh) | 车辆跟踪方法、车辆跟踪系统和计算设备 | |
CN114724128A (zh) | 一种车牌识别方法、装置、设备和介质 | |
US20230147924A1 (en) | Image processing system, imaging system, image processing method, and non-transitory computer-readable medium | |
KR102259740B1 (ko) | 제스처 분석에 기반을 둔 차량의 이미지 처리 장치 및 방법 | |
JP6539720B1 (ja) | 画像処理装置 | |
JP2008176625A (ja) | 文字認識結果の管理装置およびその方法並びにコンピュータプログラム | |
JP2015187770A (ja) | 画像認識装置、画像認識方法及びプログラム |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 2018508543 Country of ref document: JP |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2017773774 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref document number: 2017773774 Country of ref document: EP Effective date: 20181029 |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 17773774 Country of ref document: EP Kind code of ref document: A1 |