Using object re-identification in video surveillance
US-2018374233-A1 · Dec 27, 2018 · US
US12080057B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-12080057-B2 |
| Application number | US-202018015903-A |
| Country | US |
| Kind code | B2 |
| Filing date | Jul 20, 2020 |
| Priority date | Jul 20, 2020 |
| Publication date | Sep 3, 2024 |
| Grant date | Sep 3, 2024 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
An image analysis apparatus ( 102 ) includes: an icon placement unit ( 107 ) accepting an instruction for placing, on a screen, a plurality of icons including a plurality of input source icons each indicating an input source of image data being a target of analysis, a plurality of image processing icons each indicating an image processing engine for the image data, and at least one output destination icon indicating an output destination of a processing result by an image processing engine, and placing the plurality of icons on the screen in accordance with the instruction; a connection unit ( 110 ) accepting a connection instruction for connecting icons placed on the screen; and a data flow setting unit ( 111 ) setting a flow of data between the icons in accordance with the connection instruction and displaying the flow on the screen.
Opening claim text (preview).
What is claimed is: 1. An image analysis apparatus comprising: at least one memory storing instructions; and at least one processor configured to execute the instructions to: accept an instruction for placing, on a screen, a plurality of icons, and place the plurality of icons on the screen in accordance with the instruction, the plurality of icons including a plurality of input source icons, a plurality of imaging processing icons, and at least one output destination icon, each input source icon indicating an input source of image data that is a target of analysis, each image processing icon indicating an image processing engine for the image data to generate a processing result, and each output destination icon indicating an output destination of the processing result; accept a connection instruction for connecting specified icons that have been placed on the screen; and set a flow of data between the specified icons in accordance with the connection instruction and display the flow on the screen, wherein the connection instruction includes at least an instruction to connect at least one of the plurality of input source icons and the at least one output destination icon such that at least one of the plurality of image processing icons is included between the at least one of the plurality of input source icons and the at least one output destination icon. 2. The image analysis apparatus according to claim 1 , wherein the at least one processor is configured to execute the instructions to: accept, when one of the image processing icons placed on the screen is selected, a set value for a parameter applied to the image processing engine related to the selected image processing icon. 3. The image analysis apparatus according to claim 2 , wherein acceptance of the set value for the parameter includes: finding, when the one of the image processing icons placed on the screen is selected, a candidate of a set value for the parameter applied to the image processing engine related to the selected image processing icon, based on at least part of the image data; displaying the found candidate on the screen; and accepting a setting of the parameter. 4. The image analysis apparatus according to claim 3 , wherein finding the candidate of the set value includes: finding, when the one of the image processing icons placed on the screen is selected and the image processing engine associated with the selected image processing icon includes a function of identifying a person, the candidate of the set value in such a way that all of one or more persons included in a frame image constituting at least part of the image data are analyzed to be different persons via processing by the image processing engine. 5. The image analysis apparatus according to claim 3 , wherein finding the candidate of the set value includes: displaying, on the screen, when the one of the image processing icons placed on the screen is selected, one or a plurality of sample images acquired by executing processing by the image processing engine associated with the selected image processing icon on at least part of the image data; accepting a user evaluation of the one or the plurality of sample images; and finding the candidate of the set value, based on the processing result. 6. The image analysis apparatus according to claim 5 , wherein displaying the one or the plurality of sample images includes displaying a plurality of sample sets constituted of the one or the plurality of sample images, and accepting the user evaluation includes accepting a user evaluation of each of the plurality of sample sets. 7. The image analysis apparatus according to claim 6 , wherein, displaying the one or the plurality of sample images includes, when the one of the image processing icons placed on the screen is selected and the image processing engine associated with the selected image processing icon includes a function of detecting a detection target included in the image data, displaying the one or the plurality of sample images indicating the detected detection target, and accepting the user evaluation includes accepting, as the evaluation, whether the detection target is correctly detected in the one or the plurality of sample images. 8. The image analysis apparatus according to claim 6 , wherein, displaying the one or the plurality of sample images includes displaying the plurality of the sample images that each include a person, when the one of the image processing icons placed on the screen is selected and the image processing engine associated with the selected image processing icon includes a function of identifying a person, and accepting, as the evaluation, whether persons included in the plurality of sample images are identical. 9. The image analysis apparatus according to claim 2 , wherein the at least one processor configured to execute the instructions to: execute, on the image data, analysis processing based on the plurality of icons placed on the screen and a connection relation between the plurality of icons, wherein accepting the set value for the parameter includes accepting a plurality of groups of one or more set values including a set value associated with each of the plurality of icons placed on the screen, and, executing analysis processing includes executing, for each group of the set values, analysis processing on the image data in accordance with the connection relation between the plurality of icons placed on the screen. 10. The image analysis apparatus according to claim 9 , wherein, executing analysis processing includes displaying a result of the analysis processing on the screen for each group of the set values, every time analysis processing on the image data ends in accordance with the connection relation between the plurality of icons placed on the screen. 11. The image analysis apparatus according to claim 9 , wherein executing analysis processing includes: predicting whether an abnormality occurs in a result of the analysis processing; and providing notification for prompting change of the set value when the abnormality is predicted to occur. 12. The image analysis apparatus according to claim 9 , wherein executing analysis processing includes: determining whether an abnormality is included in a result of the analysis processing; and providing notification for prompting change of the set value when the abnormality is determined to be included. 13. The image analysis apparatus according to claim 11 , wherein the abnormality is at least one of: when the image processing engine associated with one of the image processing icons placed on the screen includes a function of identifying a person, a plurality of persons included in a frame image constituting the image data being analyzed are identical; and when the image processing engine associated with the one of the image processing icons placed on the screen includes a function of identifying a person and a target of the analysis is a plurality of pieces of image data acquired by capturing images of different regions in a continuous space, a number of one or more persons that are analyzed as being identical among the plurality of pieces of image data is less than a threshold value. 14. The image analysis apparatus according to claim 1 , wherein the at least one processor configured to execute the instructions to: accept selection of part or all of the plurality of icons placed and connected on the screen and holding as a component, the selected part or all of the plurality of icons and a connection relation between the selected part or all of the plurality of i
Interaction techniques to control parameter settings, e.g. interaction with sliders or dials · CPC title
using icons (graphical or visual programming using iconic symbols G06F8/34) · CPC title
Target detection · CPC title
Validation; Performance evaluation · CPC title
using selection of the recognition techniques, e.g. of a classifier in a multiple classifier system · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.