Object detection metadata
AssigneeApple Inc.
InventorsDavid William Singer, Courtney Ann Kennedy
Life of this patent
Estimating the term…
Abstract
A perimeter around a detected object in a frame of image data can be generated in a first coordinate system. The perimeter can be converted from the first coordinate system into a second coordinate system having the same aspect ratio as the first coordinate system. A first metadata entry can include dimensions of image data in the second coordinate system. A second metadata entry can provide a location and dimensions of the converted perimeter in the second coordinate space. Additional metadata can indicate matching objects between frames, position of an object relative to other objects in a frame, a probability that an object is correctly detected, and a total number of objects detected across multiple frames of image data.
Claims14
A method comprising:
- receiving object detection metadata in a metadata track corresponding to video data;
- determining pixel dimensions of the video data;
- extracting metadata from the object detection metadata to obtain extracted metadata, the extracted metadata comprising dimensions of the video data in pixel-independent space;
- extracting a detected-object entry from the metadata track, the detected-object entry comprising information that provides a location of an object detection perimeter and dimensions of the perimeter;
- scaling, by a data processing system, the information that provides the location and the dimensions of the perimeter using the pixel dimensions of the video data and dimensions of the pixel-independent space, wherein the detected-object entry includes a detected-object index value corresponding to a particular object and wherein another detected-object entry corresponding to a different frame of the video data includes the same index value, indicating that the particular object occurs in both frames.
A non-transitory machine readable storage medium storing instructions which when executed by a processing system cause the system to perform a method comprising:
- receiving object detection metadata in a metadata track corresponding to video data;
- determining pixel dimensions of the video data;
- extracting metadata from the object detection metadata to obtain extracted metadata, the extracted metadata comprising dimensions of the video data in pixel-independent space;
- extracting a detected-object entry from the metadata track, the detected-object entry comprising information that provides a location of an object detection perimeter and dimensions of the perimeter;
- scaling, by a data processing system, the information that provides the location and the dimensions of the perimeter using the pixel dimensions of the video data and dimensions of the pixel-independent space, wherein the detected-object entry includes a detected-object index value corresponding to a particular object and wherein another detected-object entry corresponding to a different frame of the video data includes the same index value, indicating that the particular object occurs in both frames.
Dependencies are inferred from the claim text.