Apparatus and method for low-power object-detection in images using image integration hardware

• US 9,582,725 B2
• Filed: 12/30/2015
• Issued: 02/28/2017
• Est. Priority Date: 09/30/2014
• Status: Active Grant

• Current Assignee: Qualcomm, Inc.
• Original Assignee: Qualcomm, Inc.
• Inventors: Govil, Alok, Gousev, Evgeni Petrovich, Rangan, Venkat, Rasquinha, Nelson
• Primary Examiner(s): ANSARI, TAHMINA N
• Application Number:
  US14/985,158
• Publication Number:
  US 20160117564A1
• Time in Patent Office: 426 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06V 10/20 Image preprocessing
• CPC Class Codes: G06V 10/24 Aligning, centring, orientation detection or correction of the image
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]
• CPC Class Codes: G06V 10/467 Encoded features or binary features, e.g. local binary patterns [LBP]
• CPC Class Codes: G06V 10/94 Hardware or software architectures specially adapted for image or video understanding
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions
• CPC Class Codes: G06V 40/172 Classification, e.g. identification
• CPC Class Codes: H04N 13/254 in combination with electromagnetic radiation sources for illuminating objects
• CPC Class Codes: H04N 23/611 where the recognised objects include parts of the human body
• CPC Class Codes: H04N 25/443 by reading pixels from selected 2D regions of the array, e.g. for windowing or digital zooming
• CPC Class Codes: H04N 25/46 by combining or binning pixels
• CPC Class Codes: H04N 25/75 Circuitry for providing, modifying or processing image signals from the pixel array

Abstract

An apparatus includes a hardware sensor array including a plurality of pixels arranged along at least a first dimension and a second dimension of the array, each of the pixels capable of generating a sensor reading. A hardware scanning window array includes a plurality of storage elements arranged along at least a first dimension and a second dimension of the hardware scanning window array, each of the storage elements capable of storing a pixel value based on one or more sensor readings. Peripheral circuitry for systematically transfers pixel values, based on sensor readings, into the hardware scanning window array, to cause different windows of pixel values to be stored in the hardware scanning window array at different times. Control logic coupled to the hardware sensor array, the hardware scanning window array, and the peripheral circuitry, provides control signals to the peripheral circuitry to control the transfer of pixel values.

Claims

1. A low-power vision sensor, comprising:

an image sensor array capable of capturing an image, the image sensor array having a plurality of rows and a plurality of columns;

one or more line buffers for transferring image data from one or more rows of the plurality of rows of the image sensor array;

two-dimensional integration hardware capable of computing a two-dimensional integral image based on the image data transferred by the one or more line buffers, the two-dimensional integral image to be used in a computer vision computation; and

computer vision feature computation hardware configured to compute a computer vision feature based on two-dimensional blocks within the two-dimensional integral image computed by the two-dimensional integration hardware.

2. The low-power vision sensor of claim 1, further comprising a hardware scanning window array for storing a two-dimensional integral image sample window, the hardware scanning window array having a number of columns fewer than a number of columns of the one or more line buffers.

3. The low-power vision sensor of claim 2, further comprising:

an image frame buffer for storing the image data prior to access by the two-dimensional integration hardware.

4. The low-power vision sensor of claim 2 further comprising:

an integral image frame buffer for storing the two-dimensional integral image prior to access by the hardware scanning window array.

5. The low-power vision sensor of claim 1, further comprising an analog-to-digital converter (ADC) coupled to the one or more line buffers and the two-dimensional integration hardware.

6. The low-power vision sensor of claim 1, wherein the computer vision feature is a multi-block local binary pattern (LBP) feature.

7. The low-power vision sensor of claim 2, further comprising a hardware classifier configured to detect the presence of a reference object within the two-dimensional integral image sample window stored in the hardware scanning window array based on computer vision features computed by the computer vision feature computation hardware.

8. The low-power vision sensor of claim 1, wherein no image signal processing circuitry is disposed between the image sensor array and the two-dimensional integration hardware.

9. A method for detecting an object in a low-power vision sensor, comprising:

capturing, via an image sensor array, an image, the image sensor array having a plurality of rows and a plurality of columns;

transferring, via one or more line buffers, image data from one or more rows of the plurality of rows of the image sensor array;

computing, via two-dimensional integration hardware, a two-dimensional integral image based on the image data transferred by the one or more line buffers, the two-dimensional integral image to be used in a computer vision operation; and

computing, via computer vision feature computation hardware, a computer vision feature based on values computed using two-dimensional blocks within the integral image computed by the two-dimensional integration hardware.

10. The method of claim 9, further comprising storing, via a hardware scanning window array, data based on a two-dimensional integral image sample window generated using the two-dimensional integration hardware, the hardware scanning window array having a number of columns fewer than a number of columns of the one or more line buffers.

11. The method of claim 10, further comprising storing, via an image frame buffer, the image data prior to access by the two-dimensional integration hardware.

12. The method of claim 9, wherein the computer vision feature is a multi-block local binary pattern (LBP) feature.

13. The method of claim 10, further comprising detecting, via a hardware classifier, the presence of a reference object within the two-dimensional integral image sample window stored in the hardware scanning window array based on computer vision features computed by the computer vision feature computation hardware.

27. The method of claim 10, further comprising storing, via an integral image frame buffer, the two-dimensional integral image prior to access by the hardware scanning window array.

14. An apparatus for detecting an object in a low-power vision sensor, comprising:

hardware means for capturing, via an image sensor array, an image, the image sensor array having a plurality of rows and a plurality of columns;

hardware means for transferring, via one or more line buffers, image data from one or more rows of the plurality of rows of the image sensor array;

hardware means for computing, via two-dimensional integration hardware, a two-dimensional integral image based on the image data transferred by the one or more line buffers, the two-dimensional integral image to be used in a computer vision computation; and

hardware means for computing, via computer vision feature computation hardware, a computer vision feature based on values computed using two-dimensional blocks within the two-dimensional integral image computed by the two-dimensional integration hardware.

15. The apparatus of claim 14, further comprising means for storing, via a hardware scanning window array, a two-dimensional integral image sample window generated using the two-dimensional integration hardware the hardware scanning window.

16. The apparatus of claim 15, further comprising means for storing, via an image frame buffer, the image data prior to access by the two-dimensional integration hardware wherein the frame buffer comprises at least one of an image frame buffer or an integral image frame buffer.

17. The apparatus of claim 14, further comprising means for converting analog data to digital data coupled to the one or more line buffers and the two-dimensional integration hardware.

18. The apparatus of claim 14, wherein the computer vision feature is a multi-block local binary pattern (LBP) feature.

19. The apparatus of claim 15, further comprising hardware means for detecting, comprising a hardware classifier, the presence of a reference object within the two-dimensional integral image sample window stored in the hardware scanning window array based on computer vision features computed by the computer vision feature computation hardware.

28. The apparatus of claim 15, further comprising means for storing, via an integral image frame buffer, the two-dimensional integral image prior to access by the hardware scanning window array.

20. One or more non-transitory computer-readable media storing computer-executable instructions detecting an object in a low-power vision sensor that, when executed, cause one or more computing devices to:

capture, via an image sensor array, an image, the image sensor array having a plurality of rows and a plurality of columns;

transfer, via one or more line buffers, image data from one or more rows of the plurality of rows of the image sensor array;

compute, via two-dimensional integration hardware, a two-dimensional integral image based on the image data transferred by the one or more line buffers, the two-dimensional integral image to be used in a computer vision computation; and

compute, via computer vision feature computation hardware, a computer vision feature based on values computed using two-dimensional blocks within the two-dimensional integral image computed by the two-dimensional integration hardware.

21. The non-transitory computer-readable media of claim 20, wherein the computer-executable instructions, when executed, further cause the one or more computing devices to store, via a hardware scanning window array, data based on a two-dimensional integral image sample window generated using the two-dimensional integration hardware, the hardware scanning window array having a number of columns fewer than a number of columns of the one or more line buffers.

22. The non-transitory computer-readable media of claim 21, wherein the computing device further comprises an image frame buffer for storing the image data prior to access by the two-dimensional integration hardware.

23. The non-transitory computer-readable media of claim 21, wherein the computing device further comprises an integral image frame buffer for storing the two-dimensional integral image prior to access by the hardware scanning window array.

24. The non-transitory computer-readable media of claim 20, wherein the computing device further comprises an analog-to-digital converter (ADC) coupled to the one or more line buffers and the two-dimensional integration hardware.

25. The non-transitory computer-readable media of claim 20, wherein the computer vision feature is a multi-block local binary pattern (LBP) feature.

26. The non-transitory computer-readable media of claim 21, wherein the computer-executable instructions, when executed, further cause the one or more computing devices to detect, via a hardware classifier, the presence of a reference object within the two-dimensional integral image sample window stored in the hardware scanning window array based on computer vision features computed by the computer vision feature computation hardware.