Low power DMA labeling

• US 9,710,878 B2
• Filed: 12/17/2014
• Issued: 07/18/2017
• Est. Priority Date: 12/17/2014
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Haraden, Ryan Scott, Tubbs, Matthew Ray, Muff, Adam James, Shearer, Robert Allen
• Primary Examiner(s): Wu, Jingge
• Application Number:
  US14/574,093
• Publication Number:
  US 20160180493A1
• Time in Patent Office: 944 Days
• CPC Class Codes: G06T 1/20 Processor architectures; Processor configuration, e.g. pipelining
• CPC Class Codes: G06T 1/60 Memory management
• CPC Class Codes: G06T 2200/28 involving image processing hardware
• CPC Class Codes: H04N 13/139 Format conversion, e.g. of frame-rate or size

Abstract

Methods for preprocessing pixel data using a Direct Memory Access (DMA) engine during a data transfer of the pixel data from a first memory (e.g., a DRAM) to a second memory (e.g., a local cache) are described. The pixel data may derive from an image capturing device (e.g., a color camera or a depth camera) in which individual pixel values are not a multiple of eight bits. In some embodiments, the DMA engine may perform a variety of image processing operations on the pixel data prior to the pixel data being written into the second memory. In one example, the DMA engine may be configured to identify and label one or more pixels as being within a particular range of pixel values and/or the DMA engine may be configured to label pixels as belonging to one or more pixel groups based on their pixel values.

Claims

1. A method for processing an image using a direct memory access engine, comprising:

acquiring configuration settings for the direct memory access engine, the configuration settings include a maximum pixel value threshold and a minimum pixel value threshold;

initiating a data transfer of the image from a first memory to a second memory using the direct memory access engine;

acquiring a first set of pixels associated with a first portion of the image, the first set of pixels includes a first pixel and a second pixel;

generating a metadata label using a first set of pixel values corresponding with the first set of pixels;

updating the first pixel to embed the metadata label within unused bits of the first pixel while the image is transferred from the first memory to the second memory using the direct memory access engine such that the first pixel includes both the metadata label and a first pixel value corresponding with the first pixel in response to detecting that the first set of pixels includes a pixel value between the maximum pixel value threshold and the minimum pixel value threshold; and

writing the first pixel to the second memory subsequent to embedding the metadata label within the unused bits of the first pixel.

2. The method of claim 1, wherein:

the first pixel corresponds with a first row of the image and the second pixel corresponds with a second row of the image different from the first row; and

the first pixel value corresponding with the first pixel is not updated while the image is transferred from the first memory to the second memory.

3. The method of claim 1, wherein:

the first pixel value is not a multiple of eight bits.

4. The method of claim 1, wherein:

the image comprises a depth image.

5. The method of claim 1, wherein:

the image comprises a depth image, the configuration settings include a maximum pixel value threshold for depth pixels and a minimum pixel value threshold for depth pixels.

6. The method of claim 5, wherein:

the maximum pixel value threshold for depth pixels corresponds with a first distance from a capture device used for generating the depth image and the minimum pixel value threshold for depth pixels corresponds with a second distance from the capture device that is less than the first distance.

7. The method of claim 1, wherein:

the image comprises a color image.

8. The method of claim 1, wherein:

the first memory comprises a DRAM and the second memory comprises an SRAM.

9. The method of claim 1, wherein:

unused bits of the second pixel are not updated while the image is transferred from the first memory to the second memory using the direct memory access engine.

10. The method of claim 1, wherein:

the configuration settings include a maximum number of pixel groupings.

11. The method of claim 1, wherein:

the first set of pixels corresponds with a plurality of pixels that are concurrently transferred over a memory bus connecting the first memory to the second memory.

12. The method of claim 1, wherein:

the first set of pixels corresponds with a maximum number of pixels that may be concurrently buffered within a memory buffer of the direct memory access engine.

13. The method of claim 1, further comprising:

determining a minimum number of new pixel groupings based on the first set of pixel values corresponding with the first set of pixels; and

generating one or more pixel groupings based on the minimum number of new pixel groupings.

14. A direct memory access engine, comprising:

a memory configured to store configuration settings for the direct memory access engine, the configuration settings include a maximum pixel value threshold and a minimum pixel value threshold; and

one or more processors in communication with the memory, the one or more processors configured to initiate a data transfer of an image from a first memory to a second memory and acquire a first set of pixels associated with a first portion of the image, the first set of pixels includes a first pixel and a second pixel, the one or more processors configured to update the first pixel to embed a metadata label within unused bits of the first pixel while the image is transferred from the first memory to the second memory such that the first pixel includes both the metadata label and a first pixel value corresponding with the first pixel in response to detecting that the first set of pixels includes a pixel value between the maximum pixel value threshold and the minimum pixel value threshold.

15. The direct memory access engine of claim 14, wherein:

the first pixel corresponds with a first row of the image and the second pixel corresponds with a second row of the image different from the first row; and

the first pixel value corresponding with the first pixel is not updated while the image is transferred from the first memory to the second memory.

16. The direct memory access engine of claim 14, wherein:

the image comprises a depth image.

17. The direct memory access engine of claim 14, wherein:

the first memory comprises a DRAM and the second memory comprises an SRAM.

18. The direct memory access engine of claim 14, wherein:

unused bits of the second pixel are not updated while the image is transferred from the first memory to the second memory.

19. One or more storage devices containing processor readable code for programming one or more processors to perform a method for processing an image using a direct memory access engine comprising:

acquiring configuration settings for the direct memory access engine, the configuration settings include a maximum pixel value threshold and a minimum pixel value threshold;

initiating a data transfer of the image from a first memory to a second memory using the direct memory access engine;

acquiring a first set of pixels associated with a first portion of the image, the first set of pixels includes a first pixel and a second pixel;

embedding a metadata label within unused bits of the first pixel while the image is transferred from the first memory to the second memory using the direct memory access engine such that the first pixel includes both the metadata label and a first pixel value corresponding with the first pixel in response to detecting that the first set of pixels includes a pixel value between the maximum pixel value threshold and the minimum pixel value threshold; and

writing the first pixel to the second memory subsequent to embedding the metadata label within the unused bits of the first pixel.

20. The one or more storage devices of claim 19, wherein:

the first pixel corresponds with a first row of the image and the second pixel corresponds with a second row of the image different from the first row; and

the first pixel value corresponding with the first pixel is not updated while the image is transferred from the first memory to the second memory.