SKELETON DETECTION SYSTEM

Information

  • Patent Application
  • 20230298205
  • Publication Number
    20230298205
  • Date Filed
    April 05, 2021
    4 years ago
  • Date Published
    September 21, 2023
    a year ago
Abstract
A skeleton detection system stores a target image for use in skeleton detection, and a plurality of skeleton detection models respectively corresponding to a plurality of skeleton definition models for defining different skeletons. The skeleton detection system determines a predetermined condition for the skeleton detection of the target image, selects a first skeleton detection model from the plurality of skeleton detection models based on a result of the determination, and executes the skeleton detection of the target image by the first skeleton detection model.
Description
Claims
  • 1. A skeleton detection system, comprising: one or more arithmetic devices; andone or more storage devices, wherein the one or more storage devices store a target image for use in skeleton detection, anda plurality of skeleton detection models respectively corresponding to a plurality of skeleton definition models configured to define different skeletons, andthe one or more arithmetic devices determine a predetermined condition for the skeleton detection of the target image,select a first skeleton detection model from the plurality of skeleton detection models based on a result of the determination, andexecute the skeleton detection of the target image by the first skeleton detection model, whereinthe target image is a frame image in a moving image, andthe one or more arithmetic devices select the first skeleton detection model from the plurality of skeleton detection models based on a skeleton detection result in a past frame image in the moving image.
  • 2. The skeleton detection system according to claim 1, wherein the predetermined condition includes at least one of a condition related to a content of the target image, a condition related to an arithmetic resource for the skeleton detection, a condition related to an imaging device configured to capture the target image, a condition related to a content of an image prior to the target image, and a condition designated by a user.
  • 3. (canceled)
  • 4. The skeleton detection system according to claim 1, wherein the one or more arithmetic devices select the first skeleton detection model from the plurality of skeleton detection models based on a detection result of a keypoint in a skeleton detection result in the past frame image.
  • 5. The skeleton detection system according to claim 1, wherein the one or more arithmetic devices select the first skeleton detection model from the plurality of skeleton detection models based on a distance between a person in the target image and an imaging device for the target image.
  • 6. The skeleton detection system according to claim 1, wherein the one or more arithmetic devices select the first skeleton detection model from the plurality of skeleton detection models based on the number of persons in the target image.
  • 7. A skeleton detection system, comprising: one or more arithmetic devices; andone or more storage devices, wherein the one or more storage devices store a target image for use in skeleton detection, anda plurality of skeleton detection models respectively corresponding to a plurality of skeleton definition models configured to define different skeletons, andthe one or more arithmetic devices determine a predetermined condition for the skeleton detection of the target image,select a first skeleton detection model from the plurality of skeleton detection models based on a result of the determination, andexecute the skeleton detection of the target image by the first skeleton detection model, whereinthe one or more arithmetic devices select the first skeleton detection model from the plurality of skeleton detection models based on a purpose of performing skeleton detection designated by a user.
  • 8. A skeleton detection system, comprising: one or more arithmetic devices; andone or more storage devices, wherein the one or more storage devices store a target image for use in skeleton detection, anda plurality of skeleton detection models respectively corresponding to a plurality of skeleton definition models configured to define different skeletons, andthe one or more arithmetic devices determine a predetermined condition for the skeleton detection of the target image,select a first skeleton detection model from the plurality of skeleton detection models based on a result of the determination, andexecute the skeleton detection of the target image by the first skeleton detection model, whereinthe one or more arithmetic devices select the first skeleton detection model from the plurality of skeleton detection models such that an estimated calculation cost of the skeleton detection falls within a usable calculation resource.
  • 9. (canceled)
  • 10. The skeleton detection system according to claim 7, wherein the predetermined condition includes at least one of a condition related to a content of the target image, a condition related to an arithmetic resource for the skeleton detection, a condition related to an imaging device configured to capture the target image, a condition related to a content of an image prior to the target image, and a condition designated by a user.
  • 11. The skeleton detection system according to claim 8, wherein the predetermined condition includes at least one of a condition related to a content of the target image, a condition related to an arithmetic resource for the skeleton detection, a condition related to an imaging device configured to capture the target image, a condition related to a content of an image prior to the target image, and a condition designated by a user.
  • 12. The skeleton detection system according to claim 7, wherein the one or more arithmetic devices select the first skeleton detection model from the plurality of skeleton detection models based on a distance between a person in the target image and an imaging device for the target image.
  • 13. The skeleton detection system according to claim 8, wherein the one or more arithmetic devices select the first skeleton detection model from the plurality of skeleton detection models based on a distance between a person in the target image and an imaging device for the target image.
  • 14. The skeleton detection system according to claim 7, wherein the one or more arithmetic devices select the first skeleton detection model from the plurality of skeleton detection models based on the number of persons in the target image.
  • 15. The skeleton detection system according to claim 8, wherein the one or more arithmetic devices select the first skeleton detection model from the plurality of skeleton detection models based on the number of persons in the target image.
Priority Claims (1)
Number Date Country Kind
2020-147563 Sep 2020 JP national
PCT Information
Filing Document Filing Date Country Kind
PCT/JP2021/014516 4/5/2021 WO