WO2024201704A1 - 検知装置、検知方法、及び非一時的なコンピュータ可読媒体 - Google Patents
検知装置、検知方法、及び非一時的なコンピュータ可読媒体 Download PDFInfo
- Publication number
- WO2024201704A1 WO2024201704A1 PCT/JP2023/012479 JP2023012479W WO2024201704A1 WO 2024201704 A1 WO2024201704 A1 WO 2024201704A1 JP 2023012479 W JP2023012479 W JP 2023012479W WO 2024201704 A1 WO2024201704 A1 WO 2024201704A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image area
- shelf
- image
- item
- shelf level
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
Definitions
- the present disclosure relates to a detection device, a detection method, and a non-transitory computer-readable medium.
- a technology has been proposed that uses a single trained discrimination model to detect areas in an image of a group of items, such as merchandise, where the group of items is present in a continuous manner (for example, Patent Document 1).
- a single classification model may not provide sufficient accuracy in detecting an image region.
- a classification model usually has objects that it is good at detecting and objects that it is not good at detecting. For this reason, the inventor has found that it is possible to improve the accuracy in detecting an image region by applying a first model and a second model with different characteristics to an image of a group of items.
- One of the objectives of the present disclosure is to provide a detection device, a detection method, and a non-transitory computer-readable medium that can improve the detection accuracy of an image region. It should be noted that this objective is only one of multiple objectives that the multiple embodiments disclosed in this specification aim to achieve. Other objectives or problems and novel features will become apparent from the description of this specification or the accompanying drawings.
- the sensing device comprises: a first detection unit that detects a second image area in a captured image of an item shelf by using a first model that identifies a first image area based on an item main occupied space that is mainly occupied by an item group in the target image, and a second model that identifies a second image area corresponding to an image of an item group arranged in the front side in the target image; an identification unit that identifies a plurality of shelf level image areas in the captured image, each of which corresponds to a plurality of shelf levels of the item shelf; an average value calculation unit that calculates an average value of the heights of the second image areas corresponding to a height direction of the item shelf in each shelf level image area; a determination unit that determines a processing target image area from among the plurality of shelf level image areas based on the average value in each shelf level image area and the height of each shelf level image area; a second detection unit that detects the first image area in the processing target image area by applying the first model to the processing target image
- the method of detection comprises: Detecting the second image area in the captured image of the item shelf using a first model that identifies a first image area based on an item main occupied space that is mainly occupied by an item group in the target image, and a second model that identifies a second image area corresponding to an image of an item group arranged in the front side in the target image; Identifying a plurality of shelf level image areas in the captured image, each of which corresponds to a plurality of shelf levels of the item shelf; Calculating an average value of the height of the second image area corresponding to the height direction of the item shelf in each shelf level image area; determining a processing target image area from among the plurality of shelf level image areas based on the average value in each shelf level image area and the height of each shelf level image area; detecting the first image region in the target image region by applying the first model to the target image region; Includes.
- a non-transitory computer readable medium comprises: Detecting the second image area in the captured image of the item shelf using a first model that identifies a first image area based on an item main occupied space that is mainly occupied by an item group in the target image, and a second model that identifies a second image area corresponding to an image of an item group arranged in the front side in the target image; Identifying a plurality of shelf level image areas in the captured image, each of which corresponds to a plurality of shelf levels of the item shelf; Calculating an average value of the height of the second image area corresponding to the height direction of the item shelf in each shelf level image area; determining a processing target image area from among the plurality of shelf level image areas based on the average value in each shelf level image area and the height of each shelf level image area; detecting the first image region in the target image region by applying the first model to the target image region; The program for causing the detection device to execute the process including the steps described above is stored.
- the present disclosure provides a detection device, a detection method, and a non-transitory computer-readable medium that can improve the accuracy of detecting an image area.
- FIG. 2 is a block diagram showing an example of a detection device according to the first embodiment.
- 4 is a flowchart showing an example of a processing operation of the detection device in the first embodiment.
- FIG. 11 is a block diagram showing an example of a detection device according to a second embodiment.
- FIG. 13 is a diagram showing an example of an item shelf image.
- FIG. 11 is a diagram illustrating an example of a second image area.
- FIG. 4 is a diagram illustrating an example of a first image area.
- FIG. 13 is a block diagram showing an example of a detection device according to a third embodiment.
- FIG. 13 is a diagram illustrating an example of an integrated image.
- FIG. 2 illustrates an example of a hardware configuration of a detection device.
- the detection device 10 in the first embodiment detects an image area corresponding to an image of a group of items in a "captured image” by using, for example, a "first model” and a “second model” that have different detection characteristics from each other.
- the "captured image” is, for example, an image of an item shelf (hereinafter, may be referred to as an "item shelf image").
- second model is a model that identifies an image area (hereinafter sometimes referred to as the “second image area” or “second item group image area”) that corresponds to the image of the item group placed in the foreground in the target image.
- image of the item group may be referred to as the “item group image.”
- the second model may be a trained model trained using training data that includes the following images: - An image showing one side of the entire item. An item shelf image in which an image area corresponding to an item group image of an item group arranged in the front row of each shelf in the item shelf image is designated as an "item group image area.”
- a large portion of one side of the item (e.g., more than half of one side) is usually shown in the item shelf image.
- the second model can accurately detect image areas corresponding to products located at the front of each shelf level, but may not be able to accurately detect image areas corresponding to products located behind the products at the front and with most of one side hidden.
- first model is a model that identifies an image area (hereinafter, sometimes referred to as the “first image area” or “first item group image area”) based on the space that is primarily occupied by the item group in the target image (hereinafter, sometimes referred to as the "item main occupied space”).
- the first model may be a trained model trained using training data that includes the following images: - An image showing one side of the entire item.
- An item shelf image in which an image area corresponding to an item group image of an item group arranged in the front row of each shelf in the item shelf image is designated as an "item group image area.”
- An item shelf image in which an image area corresponding to an "image equivalent to the true background (hereinafter sometimes referred to as a "true background image”)" in the item shelf image is designated as a "true background image area.”
- the "true background image area” includes the image area corresponding to the image of the back panel, side panel, or shelf of the item shelf that is shown in the item shelf image without being hidden by the shadow of the item.
- the first model has the characteristic of being able to accurately detect image areas that are likely to be background images (for example, image areas corresponding to large empty spaces where no items are placed) and image areas corresponding to the above-mentioned space mainly occupied by items.
- the first model learns the contradictory information of "item group image areas” and "true background image areas,” for areas that cannot be designated as either, there is a possibility that the model will detect areas close to "item group image areas” as “item group image areas” and areas close to "true background image areas” as “true background image areas.” As a result, there is a possibility that the model will detect an image area that corresponds to a narrow empty space sandwiched between two "item group image areas" as part of the item group image area. This is because it is thought that in many cases, sufficient information cannot be obtained from an image that corresponds to a narrow empty space to detect that it is a background image.
- the detection device 10 detects an image area corresponding to an image of a group of items in a captured image using a "first model” and a “second model” that have different detection characteristics. This makes it possible to improve the detection accuracy of the image area.
- Fig. 1 is a block diagram showing an example of a detection device in the first embodiment.
- the detection device 10 has a detection unit (first detection unit) 11, an identification unit 12, an average value calculation unit 13, a detection unit (second detection unit) 14, and a determination unit 15.
- the detection device 10 acquires a captured image.
- This captured image is, for example, an item shelf image of an item shelf. The following description will be given on the assumption that the captured image is an item shelf image.
- This item shelf has a plurality of shelf levels.
- the detection unit 11 detects the second image area in the captured image by applying the second model to the captured image.
- the identification unit 12 identifies a number of "shelf level image areas" in the captured image, each of which corresponds to a number of shelf levels.
- a shelf level image area corresponding to one shelf level is, for example, an image area corresponding to the space between the shelf board of that shelf level and the shelf board of the shelf level immediately above that shelf level.
- the average value calculation unit 13 calculates the average value of the height of the second image area in each shelf level image area.
- the height of the second image area is the length of the second image area corresponding to the height direction of the item shelf.
- the determination unit 15 determines an image area to be processed by the detection unit 14 from among the multiple shelf level image areas based on the average value of the height of the second image area in each shelf level image area and the height of each shelf level image area.
- the height of the shelf level image area is the length of the shelf level image area corresponding to the height direction of the item shelf.
- Fig. 2 is a flowchart showing an example of the processing operation of the detection device in the first embodiment.
- the detection unit 11 detects a second image area in the captured image by applying the second model to the captured image (step S101).
- the identification unit 12 identifies a number of shelf level image areas in the captured image that respectively correspond to a number of shelf levels (step S102).
- the average value calculation unit 13 calculates the average value of the height of the second image area in each shelf image area (step S103).
- the determination unit 15 determines an image area to be processed by the detection unit 14 from among the multiple shelf level image areas based on the average value of the height of the second image area in each shelf level image area and the height of each shelf level image area (step S104).
- the detection unit 14 detects the first image area in the processing target image area determined by the determination unit 15 by applying the first model to the processing target image area (step S105).
- the detection device 10 detects an item group image area in a captured image using a "first model” and a “second model” that have different detection characteristics. This allows one model to compensate for the weaknesses of the other model in detecting objects, thereby improving the detection accuracy of the item group image area.
- the detection unit 11 of the detection device 10 detects a second image area in the captured image by applying a second model to the captured image.
- the determination unit 15 determines an image area to be processed by the detection unit 14 from among the multiple shelf level image areas based on the average value of the heights of the second image areas in each shelf level image area and the height of each shelf level image area.
- the detection unit 14 detects a first image area in the image area to be processed by applying a first model to the image area to be processed determined by the determination unit 15.
- the second model is a model that identifies a second image area that corresponds to an image of a group of items arranged at the front in the target image.
- the first model is a model that identifies a first image area in the target image based on the main occupied space of the items.
- the configuration of the detection device 10 can improve the detection accuracy of the item group image area. That is, for example, if the average value of the height of the second image area in the shelf image area is sufficiently small compared to the height of the shelf image area, it is highly likely that even items located at the back are captured in the shelf image area.
- the second model is applied to such a shelf image area, it is possible that the image area corresponding to the items located at the back cannot be detected with high accuracy.
- the first model is applied to such a shelf image area, it is highly likely that the image area corresponding to the items located at the back can be detected with high accuracy.
- the average value of the height of the second image area in the shelf image area is sufficiently large compared to the height of the shelf image area, it is highly likely that almost no items located at the back are captured in the shelf image area.
- the second model is applied to such a shelf image area, it is highly likely that the image area corresponding to the product group located at the front can be detected with high accuracy. Therefore, one model can compensate for the poor detection of the detection target of the other model, so that the detection accuracy of the item group image area can be improved.
- the second embodiment relates to an embodiment that embodies the contents of the first embodiment more specifically.
- FIG. 3 is a block diagram showing an example of a detection device in the second embodiment.
- the detection device 20 has a detection unit (first detection unit) 21, an identification unit 22, an average value calculation unit 23, a detection unit (second detection unit) 24, and a determination unit 25.
- the detection device 20 acquires a captured image in the same manner as the detection device 10 in the first embodiment.
- This captured image is, for example, an item shelf image in which an item shelf is captured. The following description will be given on the assumption that the captured image is an item shelf image.
- This item shelf has multiple shelf levels.
- the detection unit 21 detects a second image area in the captured image (i.e., the item shelf image) by applying a second model to the captured image.
- FIG. 4A is a diagram showing an example of an item shelf image.
- FIG. 4B is a diagram showing an example of a second image area.
- Figure 4A shows an item shelf image of a shelf where PET bottled drinks are displayed.
- the item shelf shown in the item shelf image in Figure 4A has four shelf levels.
- PET bottles are arranged in an upright position as items.
- PET bottles are arranged lying on their sides and stacked.
- the space above the PET bottles is narrow, while on the bottom shelf level, the space above the PET bottles is wide. For this reason, in the image of the top three shelf levels, most of the PET bottles at the back are hidden by the PET bottles in front, while in the image of the bottom shelf level, even the PET bottles at the back are visible.
- FIG. 4B The result of applying the second model to the item shelf image in FIG. 4A is shown in FIG. 4B.
- the shaded area corresponds to the second image area.
- the second model is able to accurately detect the item group image area corresponding to the plastic bottles in the images of the top three shelves.
- the second model can accurately detect even image areas corresponding to narrow empty spaces such as those sandwiched between two item group image areas.
- the identification unit 22 like the identification unit 12 of the first embodiment, identifies a number of "shelf level image areas" in the captured image that respectively correspond to a number of shelf levels.
- the lower line that defines the second image area in the image of each shelf appears as a straight line that is approximately parallel to the shelf. In other words, by identifying this straight line, it is possible to identify the line that corresponds to the surface of the plastic bottle that is in contact with the shelf.
- the identification unit 22 may identify the lower line that defines the second image area in the image of each shelf level, and identify the image area sandwiched between two adjacent lines as the "shelf level image area.”
- the identification unit 22 may directly identify the front image of the shelf by pattern matching or the like. This front image of the shelf can also be identified as a line corresponding to the surface of the plastic bottle in contact with the shelf. The identification unit 22 may then identify the image area sandwiched between two adjacent lines as a "shelf level image area.” Note that image areas SA11, SA12, SA13, and SA14, each surrounded by a frame in FIG. 4B, are each an example of a shelf level image area.
- the average value calculation unit 23 like the average value calculation unit 13 in the first embodiment, calculates the average value of the heights of the second image areas in each shelf level image area.
- the height of the second image area is the length of the second image area corresponding to the height direction of the item shelf.
- the determination unit 25 determines an image area to be processed by the detection unit 24 from among the multiple shelf level image areas based on the average value of the height of the second image area in each shelf level image area and the height of each shelf level image area.
- the determination unit 25 has a specific processing unit 25A and a determination processing unit 25B.
- the identification processing unit 25A identifies the length of each shelf level image area corresponding to the height direction of the item shelf as the height ( ⁇ ) of each shelf level image area.
- the determination processing unit 25B calculates a "reference value" for each identified shelf level image area by multiplying the height ( ⁇ ) of each identified shelf level image area by a predetermined ratio (e.g., 0.6). The determination processing unit 25B then determines the image area to be processed by comparing the calculated "reference value" for each shelf level image area with the average value of the height of the second image area corresponding to each shelf level image area. For example, the determination processing unit 25B determines the shelf level image area corresponding to the second image area having an average value smaller than the "reference value" as the image area to be processed by the detection unit 24. In the example of FIG. 4B, the determination processing unit 25B determines the shelf level image area SA14 as the image area to be processed by the detection unit 24.
- the detection unit 24 detects the first image area in the processing target image area by applying the first model to the processing target image area determined by the determination unit 25.
- FIG. 4C is a diagram showing an example of the first image area.
- the shaded area in shelf level image area SA14 corresponds to the first image area.
- model 1 can accurately detect not only the item group image area corresponding to the PET bottle group located at the front in shelf level image area SA14 (i.e., the image of the bottom shelf), but also the item group image area corresponding to the PET bottle group located at the back.
- FIG. 4C also shows the results of applying model 1 to shelf level image areas SA11, SA12, and SA13.
- model 1 may detect an image area corresponding to a narrow empty space SP1, such as that sandwiched between two item group image areas, as part of the item group image area.
- the third embodiment relates to identifying free space.
- FIG. 5 is a block diagram showing an example of a detection device in the third embodiment.
- the detection device 30 has a detection unit (first detection unit) 11, an identification unit 12, an average value calculation unit 13, a detection unit (second detection unit) 14, a determination unit 15, an integration unit 31, and a space identification unit 32.
- the integration unit 31 integrates a first image area in the processing target image area detected by the detection unit 14 with a second image area in each shelf level image area other than the processing target image area detected by the detection unit 11 to obtain an "integrated image.”
- the second image area in the shelf level image areas SA11, SA12, and SA13 detected by the second model and the first image area in the shelf level image area SA14 detected by the first model are integrated to form an "integrated image.”
- Figure 6 is a diagram showing an example of an integrated image.
- the space identifying unit 32 identifies free space on each shelf level where no items are placed, based on the integrated image. For example, the space identifying unit 32 may identify free space by subtracting the integrated image from the shelf level image area. In FIG. 6, for example, the areas surrounded by rectangular frames (spaces SP1, SP2, SP3, and SP4) correspond to free space.
- the detection device 30 in the third embodiment identifies free space based on an integrated image obtained by applying the first model and the second model to the shelf image areas, which are the detection targets that the model is good at, and integrating the image areas obtained, so that free space can be identified with high accuracy.
- the description here is based on the assumption that the integration unit 31 and the space identification unit 32 are applied to the detection device 10 of the first embodiment, the present disclosure is not limited to this.
- the integration unit 31 and the space identification unit 32 may also be applied to the detection device 20 of the second embodiment.
- Fig. 7 is a diagram showing an example of a hardware configuration of a detection device.
- the detection device 100 has a processor 101 and a memory 102.
- the processor 101 may be, for example, a microprocessor, a micro processing unit (MPU), or a central processing unit (CPU).
- the processor 101 may include a plurality of processors.
- the memory 102 is configured by a combination of a volatile memory and a non-volatile memory.
- the memory 102 may include a storage located away from the processor 101. In this case, the processor 101 may access the memory 102 via an I/O interface not shown.
- the detection devices 10, 20, and 30 of the first to third embodiments may each have the hardware configuration shown in FIG. 7.
- the detection units 11 and 21, the identification units 12 and 22, the average value calculation units 13 and 23, the detection units 14 and 24, the determination units 15 and 25, the integration unit 31, and the space identification unit 32 of the detection devices 10, 20, and 30 of the first to third embodiments may be realized by the processor 101 reading and executing a program stored in the memory 102.
- the program can be stored using various types of non-transitory computer readable medium and supplied to the detection devices 10, 20, and 30.
- Examples of non-transitory computer readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives) and magneto-optical recording media (e.g., magneto-optical disks).
- Detection device 11 Detection unit (first detection unit) 12 Identification unit 13 Average value calculation unit 14 Detection unit (second detection unit) 15 Determination unit 20 Detection device 21 Detection unit (first detection unit) 22 Identification unit 23 Average value calculation unit 24 Detection unit (second detection unit) 25 Determination unit 25A Identification processing unit 25B Determination processing unit 30 Detection device 31 Integration unit 32 Space identification unit
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
Description
対象画像において物品群が主に占有する物品主占有空間に基づく第1画像領域を識別する第1モデルと、対象画像において前側に配置された物品群の画像に対応する第2画像領域を識別する第2モデルとのうちの、前記第2モデルを用いて、物品棚が撮影された撮影画像における前記第2画像領域を検知する第1検知部と、
前記撮影画像において前記物品棚の複数の棚段にそれぞれ対応する複数の棚段画像領域を特定する特定部と、
各棚段画像領域における、前記物品棚の高さ方向に対応する前記第2画像領域の高さの平均値を算出する平均値算出部と、
各棚段画像領域における前記平均値と、各棚段画像領域の高さとに基づいて、前記複数の棚段画像領域の中から、処理対象画像領域を決定する決定部と、
前記処理対象画像領域に対して前記第1モデルを適用することによって前記処理対象画像領域における前記第1画像領域を検知する第2検知部と、
を具備する。
対象画像において物品群が主に占有する物品主占有空間に基づく第1画像領域を識別する第1モデルと、対象画像において前側に配置された物品群の画像に対応する第2画像領域を識別する第2モデルとのうちの、前記第2モデルを用いて、物品棚が撮影された撮影画像における前記第2画像領域を検知することと、
前記撮影画像において前記物品棚の複数の棚段にそれぞれ対応する複数の棚段画像領域を特定することと、
各棚段画像領域における、前記物品棚の高さ方向に対応する前記第2画像領域の高さの平均値を算出することと、
各棚段画像領域における前記平均値と、各棚段画像領域の高さとに基づいて、前記複数の棚段画像領域の中から、処理対象画像領域を決定することと、
前記処理対象画像領域に対して前記第1モデルを適用することによって前記処理対象画像領域における前記第1画像領域を検知することと、
を含む。
対象画像において物品群が主に占有する物品主占有空間に基づく第1画像領域を識別する第1モデルと、対象画像において前側に配置された物品群の画像に対応する第2画像領域を識別する第2モデルとのうちの、前記第2モデルを用いて、物品棚が撮影された撮影画像における前記第2画像領域を検知することと、
前記撮影画像において前記物品棚の複数の棚段にそれぞれ対応する複数の棚段画像領域を特定することと、
各棚段画像領域における、前記物品棚の高さ方向に対応する前記第2画像領域の高さの平均値を算出することと、
各棚段画像領域における前記平均値と、各棚段画像領域の高さとに基づいて、前記複数の棚段画像領域の中から、処理対象画像領域を決定することと、
前記処理対象画像領域に対して前記第1モデルを適用することによって前記処理対象画像領域における前記第1画像領域を検知することと、
を含む処理を、検知装置に実行させるプログラムを格納している。
<検知装置の概要>
第1実施形態における検知装置10は、例えば、互いに検知特性の異なる「第1モデル」及び「第2モデル」を用いて、「撮影画像」における物品群の画像に対応する画像領域を検知する。「撮影画像」は、例えば、物品棚が撮影された画像(以下では、「物品棚画像」と呼ぶことがある)である。
- 物品単体の一側面の全体が撮影された画像。
- 物品棚画像において各棚段の最前列に並べられた物品群の物品群画像に対応する画像領域を「物品群画像領域」として指定した、物品棚画像。
- 物品単体の一側面の全体が撮影された画像。
- 物品棚画像において各棚段の最前列に並べられた物品群の物品群画像に対応する画像領域を「物品群画像領域」として指定した、物品棚画像。
- 物品棚画像において「真の背景に相当する画像(以下では、「真背景画像」と呼ぶことがある)」に対応する画像領域を「真背景画像領域」として指定した、物品棚画像。
図1は、第1実施形態における検知装置の一例を示すブロック図である。図1において検知装置10は、検知部(第1検知部)11と、特定部12と、平均値算出部13と、検知部(第2検知部)14と、決定部15とを有している。検知装置10は、撮影画像を取得する。この撮影画像は、例えば、物品棚が撮影された物品棚画像である。以下では、撮影画像が物品棚画像であることを前提に説明する。この物品棚は、複数の棚段を有している。
以上の構成を有する検知装置10の処理動作の一例について説明する。図2は、第1実施形態における検知装置の処理動作の一例を示すフローチャートである。
第2実施形態は、第1実施形態の内容をより具体化する実施形態に関する。
第3実施形態は、空きスペースの特定に関する。
図7は、検知装置のハードウェア構成例を示す図である。図7において検知装置100は、プロセッサ101と、メモリ102とを有している。プロセッサ101は、例えば、マイクロプロセッサ、MPU(Micro Processing Unit)、又はCPU(Central Processing Unit)であってもよい。プロセッサ101は、複数のプロセッサを含んでもよい。メモリ102は、揮発性メモリ及び不揮発性メモリの組み合わせによって構成される。メモリ102は、プロセッサ101から離れて配置されたストレージを含んでもよい。この場合、プロセッサ101は、図示されていないI/Oインタフェースを介してメモリ102にアクセスしてもよい。
11 検知部(第1検知部)
12 特定部
13 平均値算出部
14 検知部(第2検知部)
15 決定部
20 検知装置
21 検知部(第1検知部)
22 特定部
23 平均値算出部
24 検知部(第2検知部)
25 決定部
25A 特定処理部
25B 決定処理部
30 検知装置
31 統合部
32 スペース特定部
Claims (10)
- 対象画像において物品群が主に占有する物品主占有空間に基づく第1画像領域を識別する第1モデルと、対象画像において前側に配置された物品群の画像に対応する第2画像領域を識別する第2モデルとのうちの、前記第2モデルを用いて、物品棚が撮影された撮影画像における前記第2画像領域を検知する第1検知部と、
前記撮影画像において前記物品棚の複数の棚段にそれぞれ対応する複数の棚段画像領域を特定する特定部と、
各棚段画像領域における、前記物品棚の高さ方向に対応する前記第2画像領域の高さの平均値を算出する平均値算出部と、
各棚段画像領域における前記平均値と、各棚段画像領域の高さとに基づいて、前記複数の棚段画像領域の中から、処理対象画像領域を決定する決定部と、
前記処理対象画像領域に対して前記第1モデルを適用することによって前記処理対象画像領域における前記第1画像領域を検知する第2検知部と、
を具備する検知装置。 - 前記決定部は、前記複数の棚段画像領域のうちで、前記棚段画像領域の高さの所定割合未満の前記平均値を有する前記第2画像領域に対応する前記棚段画像領域を、前記処理対象画像領域として決定する、
請求項1記載の検知装置。 - 前記決定部は、
前記物品棚の高さ方向に対応する各棚段画像領域の長さを、各棚段画像領域の高さとして特定する特定処理部と、
前記特定された各棚段画像領域の高さに前記所定割合を乗算して得られる値と、各棚段画像領域に対応する前記第2画像領域の高さの平均値とを比較することによって、前記処理対象画像領域を決定する決定処理部と、
を具備する、
請求項2記載の検知装置。 - 前記特定部は、前記第2画像領域おいて前記物品棚の棚板に接する物品の面に対応する複数のラインを特定し、前記複数のラインによって前記撮影画像を分割することによって、前記複数の棚段画像領域を特定する、
請求項1記載の検知装置。 - 前記処理対象画像領域における前記第1画像領域と、前記処理対象画像領域以外の各棚段画像領域における前記第2画像領域とを統合して統合画像を得る統合部をさらに具備する、請求項1記載の検知装置。
- 前記統合画像に基づいて、各棚段において物品が配置されていない空きスペースを特定するスペース特定部をさらに具備する、
請求項5記載の検知装置。 - 対象画像において物品群が主に占有する物品主占有空間に基づく第1画像領域を識別する第1モデルと、対象画像において前側に配置された物品群の画像に対応する第2画像領域を識別する第2モデルとのうちの、前記第2モデルを用いて、物品棚が撮影された撮影画像における前記第2画像領域を検知することと、
前記撮影画像において前記物品棚の複数の棚段にそれぞれ対応する複数の棚段画像領域を特定することと、
各棚段画像領域における、前記物品棚の高さ方向に対応する前記第2画像領域の高さの平均値を算出することと、
各棚段画像領域における前記平均値と、各棚段画像領域の高さとに基づいて、前記複数の棚段画像領域の中から、処理対象画像領域を決定することと、
前記処理対象画像領域に対して前記第1モデルを適用することによって前記処理対象画像領域における前記第1画像領域を検知することと、
を含む検知方法。 - 前記決定することは、前記複数の棚段画像領域のうちで、前記棚段画像領域の高さの所定割合未満の前記平均値を有する前記第2画像領域に対応する棚段画像領域を、前記処理対象画像領域として決定することを含む、
請求項7記載の検知方法。 - 対象画像において物品群が主に占有する物品主占有空間に基づく第1画像領域を識別する第1モデルと、対象画像において前側に配置された物品群の画像に対応する第2画像領域を識別する第2モデルとのうちの、前記第2モデルを用いて、物品棚が撮影された撮影画像における前記第2画像領域を検知することと、
前記撮影画像において前記物品棚の複数の棚段にそれぞれ対応する複数の棚段画像領域を特定することと、
各棚段画像領域における、前記物品棚の高さ方向に対応する前記第2画像領域の高さの平均値を算出することと、
各棚段画像領域における前記平均値と、各棚段画像領域の高さとに基づいて、前記複数の棚段画像領域の中から、処理対象画像領域を決定することと、
前記処理対象画像領域に対して前記第1モデルを適用することによって前記処理対象画像領域における前記第1画像領域を検知することと、
を含む処理を、検知装置に実行させるプログラムが格納された非一時的なコンピュータ可読媒体。 - 前記決定することは、前記複数の棚段画像領域のうちで、前記棚段画像領域の高さの所定割合未満の前記平均値を有する前記第2画像領域に対応する棚段画像領域を、前記処理対象画像領域として決定することを含む、
請求項9記載の非一時的なコンピュータ可読媒体。
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2025509326A JPWO2024201704A5 (ja) | 2023-03-28 | 検知装置、検知方法、及びプログラム | |
| PCT/JP2023/012479 WO2024201704A1 (ja) | 2023-03-28 | 2023-03-28 | 検知装置、検知方法、及び非一時的なコンピュータ可読媒体 |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/JP2023/012479 WO2024201704A1 (ja) | 2023-03-28 | 2023-03-28 | 検知装置、検知方法、及び非一時的なコンピュータ可読媒体 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2024201704A1 true WO2024201704A1 (ja) | 2024-10-03 |
Family
ID=92903535
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2023/012479 Ceased WO2024201704A1 (ja) | 2023-03-28 | 2023-03-28 | 検知装置、検知方法、及び非一時的なコンピュータ可読媒体 |
Country Status (1)
| Country | Link |
|---|---|
| WO (1) | WO2024201704A1 (ja) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013118218A1 (ja) * | 2012-02-09 | 2013-08-15 | パナソニック株式会社 | 画像認識装置、画像認識方法、プログラムおよび集積回路 |
| JP2020087155A (ja) * | 2018-11-29 | 2020-06-04 | キヤノン株式会社 | 情報処理装置、情報処理方法及びプログラム |
| JP2021117531A (ja) * | 2020-01-22 | 2021-08-10 | 国立研究開発法人産業技術総合研究所 | 物品群の配置状態を認識するための情報処理方法、装置及びプログラム |
-
2023
- 2023-03-28 WO PCT/JP2023/012479 patent/WO2024201704A1/ja not_active Ceased
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013118218A1 (ja) * | 2012-02-09 | 2013-08-15 | パナソニック株式会社 | 画像認識装置、画像認識方法、プログラムおよび集積回路 |
| JP2020087155A (ja) * | 2018-11-29 | 2020-06-04 | キヤノン株式会社 | 情報処理装置、情報処理方法及びプログラム |
| JP2021117531A (ja) * | 2020-01-22 | 2021-08-10 | 国立研究開発法人産業技術総合研究所 | 物品群の配置状態を認識するための情報処理方法、装置及びプログラム |
Also Published As
| Publication number | Publication date |
|---|---|
| JPWO2024201704A1 (ja) | 2024-10-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12536769B2 (en) | System and method for matching products and determining spreads and plugs | |
| US11281876B2 (en) | Retail store with sensor-fusion enhancements | |
| US12437258B2 (en) | System and method for identifying products in a shelf management system | |
| US12118506B2 (en) | System and method for associating products and product labels | |
| CN110472515B (zh) | 货架商品检测方法及系统 | |
| US9600982B2 (en) | Methods and arrangements for identifying objects | |
| US20190188435A1 (en) | Methods and arrangements for identifying objects | |
| CA2888153C (en) | Methods and arrangements for identifying objects | |
| US9224184B2 (en) | Methods and arrangements for identifying objects | |
| US20170249491A1 (en) | Methods and arrangements for identifying objects | |
| CN110472486B (zh) | 一种货架障碍物识别方法、装置、设备及可读存储介质 | |
| US20150310601A1 (en) | Methods and arrangements for identifying objects | |
| US20250045692A1 (en) | System and method for identifying misplaced products in a shelf management system | |
| CN111161346B (zh) | 将商品在货架中进行分层的方法、装置和电子设备 | |
| EP2751748A1 (en) | Methods and arrangements for identifying objects | |
| TWI578272B (zh) | Shelf detection system and method | |
| JP7459947B2 (ja) | 商品検知装置、商品検知システム、商品検知方法および商品検知プログラム | |
| JP2022188754A (ja) | 認識装置、端末装置、認識器構築装置、認識器修正装置、構築方法、及び修正方法 | |
| US20080154736A1 (en) | Method for determining product length for use in regulating transactions in a self-checkout conveyer system | |
| WO2024201704A1 (ja) | 検知装置、検知方法、及び非一時的なコンピュータ可読媒体 | |
| WO2024201705A1 (ja) | 検知装置、検知方法、及び非一時的なコンピュータ可読媒体 | |
| CN113269053A (zh) | 商品的货架层列获取方法、终端、存储装置 | |
| CN104123528B (zh) | 一种识别图片的方法及装置 | |
| WO2024201706A1 (ja) | 検知装置、検知方法、及び非一時的なコンピュータ可読媒体 | |
| JP7476905B2 (ja) | 処理装置、処理方法及びプログラム |
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: 23930344 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2025509326 Country of ref document: JP Kind code of ref document: A |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2025509326 Country of ref document: JP |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 23930344 Country of ref document: EP Kind code of ref document: A1 |