Recovering occluded image data using machine learning
US-2021133936-A1 · May 6, 2021 · US
US12537918B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-12537918-B2 |
| Application number | US-202118257717-A |
| Country | US |
| Kind code | B2 |
| Filing date | Dec 9, 2021 |
| Priority date | Dec 23, 2020 |
| Publication date | Jan 27, 2026 |
| Grant date | Jan 27, 2026 |
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.
There is provided an artificial satellite and a ground system enabling to efficiently hold data in the artificial satellite. The artificial satellite includes an image processing unit that executes feature amount generation processing of generating a feature amount of a captured satellite image, a storage unit that holds feature amount data obtained as a result of the feature amount generation processing, and a communication unit that transmits the feature amount data to a ground station when communication with the ground station becomes possible. The ground system includes an image processing unit configured to generate complemented data by using complementing data and feature amount data that indicates a feature amount of a satellite image acquired from an artificial satellite and obtained by capturing an image of a ground by the artificial satellite.
Opening claim text (preview).
The invention claimed is: 1 . An artificial satellite, comprising: a memory; an antenna; an image capturing device configured to capture a first satellite image; and a central processing unit (CPU) is configured to: execute, on the captured first satellite image, a feature amount generation process to generate feature amount data of the captured first satellite image, wherein the generated feature amount data includes an arithmetic value associated with the executed feature amount generation process; determine that the generated feature amount data is less than a specific value associated with a recognition process; control, based on the determination that the generated feature amount data is less than the specific value associated with the recognition process, the image capturing device to re-capture a second satellite image; execute, on the re-captured second satellite image, the feature amount generation process to update the generated feature amount data; control the memory to store the updated feature amount data; determine that communication with a ground station is possible; and control, based on the determination that the communication with the ground station is possible, the antenna to transmit the updated feature amount data to the ground station. 2 . The artificial satellite according to claim 1 , wherein the CPU is further configured to execute a specific compression process as the feature amount generation process. 3 . The artificial satellite according to claim 1 , wherein the CPU is further configured to execute, as the feature amount generation process, a feature amount conversion process to convert at least one of the captured first satellite image or the re-captured second satellite image to a specific feature amount. 4 . The artificial satellite according to claim 1 , wherein the CPU is further configured to: execute, as the feature amount generation process, a feature amount conversion process to convert at least one of the captured first satellite image or the re-captured second satellite image to a specific feature amount; and execute the recognition process on the specific feature amount. 5 . The artificial satellite according to claim 1 , wherein the CPU is further configured to erase the captured first satellite image and the re-captured second satellite image. 6 . The artificial satellite according to claim 1 , wherein each of the captured first satellite image and the re-captured second satellite image is an optical captured image. 7 . The artificial satellite according to claim 1 , wherein the updated feature amount data further includes information regarding a recognition target in at least one of the captured first satellite image or the re-captured second satellite image. 8 . The artificial satellite according to claim 7 , wherein the recognition target is related to one of a specific target subject or a specific change amount of the specific target subject. 9 . The artificial satellite according to claim 1 , wherein the updated feature amount data further includes information regarding a specific feature state in at least one of the captured first satellite image or the re-captured second satellite image. 10 . The artificial satellite according to claim 1 , wherein the CPU is further configured to obtain, based on at least one of the captured first satellite image or the re-captured second satellite image, information regarding a movement of the artificial satellite, and the updated feature amount data further includes the obtained information regarding the movement of the artificial satellite. 11 . The artificial satellite according to claim 1 , wherein the updated feature amount data further includes information for an alignment of the captured first satellite image or the re-captured second satellite image. 12 . The artificial satellite according to claim 1 , wherein the CPU is further configured to: control the image capturing device to capture a plurality of images in a plurality of bands, wherein the captured plurality of images includes the captured first image and the re-captured second image; and integrate the captured plurality of images to generate an integrated image, and the updated feature amount data further includes information associated with the integrated image. 13 . A ground system, comprising: an antenna configured to receive feature amount data from an artificial satellite, wherein the artificial satellite captures a satellite image of a ground, the artificial satellite further executes, on the satellite image, a feature amount generation process to generate the feature amount data of the captured satellite image, the generated feature amount data is different from the captured satellite image, and the received feature amount data includes an arithmetic value associated with the executed feature amount generation process; and a central processing unit (CPU) configured to generate complemented data based on complementing data and the received feature amount data. 14 . The ground system according to claim 13 , further comprising a memory configured to store the complementing data prior to the reception of the feature amount data. 15 . The ground system according to claim 13 , further comprising a memory configured to store the complementing data prior to the capture of the satellite image, wherein the stored complementing data is information regarding an image-capturing area of the satellite image. 16 . The ground system according to claim 13 , wherein the CPU is further configured to execute a data analysis process based on the generated complemented data.
Target detection · CPC title
Satellite images · CPC title
Communications satellites · CPC title
for receiving images from a single remote source · CPC title
Artificial satellites; Systems of such satellites; Interplanetary vehicles (space shuttles B64G1/14) · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.