Vision system with tail detection

Patent metadata

Field	Value
Publication number	US-10354388-B2
Application number	US-201815953218-A
Country	US
Kind code	B2
Filing date	Apr 13, 2018
Priority date	Aug 17, 2016
Publication date	Jul 16, 2019
Grant date	Jul 16, 2019

Abstract

A system that includes a three-dimensional (3D) camera configured to capture a 3D image of a rearview of a dairy livestock in a stall and a processor. The processor is configured to obtain the 3D image, identify one or more regions within the 3D image comprising depth values greater than a depth value threshold, and s to identify a thigh gap region from the one or more regions. The processor is further configured to demarcate an access region within the thigh gap region and demarcate a tail detection region. The processor is further configured to identify one or more tail candidates within the tail detection region, to identify a tail candidate that corresponds with a tail model as the tail, and to determine position information for the tail.

First claim

The invention claimed is:

1. A vision system comprising:
a three-dimensional (3D) camera configured to capture a 3D image of a rearview of a dairy livestock in a stall, wherein each pixel of the 3D image is associated with a depth value; and
a processor operably coupled to the 3D camera, and configured to:
obtain the 3D image;
identify one or more regions within the 3D image comprising depth values greater than a depth value threshold;
identify a thigh gap region among the one or more regions, wherein the thigh gap region comprises an area between hind legs of the dairy livestock;
demarcate an access region within the thigh gap region, wherein the access region is defined by:
a first vertical edge,
a second vertical edge,
a first upper edge spanning between the first vertical edge and the second vertical edge, and
a first lower edge spanning between the first vertical edge and the second vertical edge;

demarcate a tail detection region, wherein the tail detection region is defined by:
a third vertical edge extending vertically from the first vertical edge of the access region,
a fourth vertical edge extending vertically from the second vertical edge of the access region,
a second upper edge spanning between the third vertical edge and the fourth vertical edge, and
a second lower edge spanning between the third vertical edge and the fourth vertical edge, wherein the second lower edge is adjacent to the first upper edge of the access region;

identify one or more tail candidates within the tail detection region;
compare the one or more tail candidates to a tail model;
identify a tail candidate from among the one or more tail candidates as a tail of the dairy livestock when the tail candidate corresponds with the tail model; and
determine position information for the tail of the dairy livestock in response to identifying the tail of the dairy livestock.

2. The system of claim 1 , wherein:
the tail model indicates a tail shape; and
the tail of the dairy livestock corresponds with the tail shape in at least two of a plurality of depth planes.

3. The system of claim 1 , wherein:
the system further comprises a memory configured to store a thigh gap detection rule set that identifies a marker positioned between the hind legs of the dairy livestock at a lower edge of the 3D image; and
identifying the thigh gap region comprises applying the thigh gap detection rule set to the one or more regions to identify the thigh gap region, wherein applying the thigh gap detection rule set comprises identifying a region from among the one or more regions that comprises the marker as the thigh gap region.

4. The system of claim 1 , wherein:
the system further comprises a memory configured to store a thigh gap detection rule set that indicates a minimum area value to be considered the thigh gap region; and
identifying the thigh gap region comprises applying the thigh gap detection rule set to the one or more regions to identify the thigh gap region, wherein applying the thigh gap detection rule set comprises:
comparing the area of each of the one or more regions to the minimum area value to be considered the thigh gap region; and
identifying a region from among the one or more regions as the thigh gap region when the region has an area greater than or equal to the minimum area value to be considered the thigh gap region.

5. The system of claim 1 , wherein:
the system further comprises a memory configured to store a thigh gap detection rule set that indicates a maximum height value to be considered the thigh gap region; and
identifying the thigh gap region comprises applying the thigh gap detection rule set to the one or more regions to identify the thigh gap region, wherein applying the thigh gap detection rule set comprises:
comparing the height of each of the one or more regions to the maximum height value to be considered the thigh gap region; and
identifying a region from among the one or more regions as the thigh gap region when the region has a height less than or equal to the maximum height value to be considered the thigh gap region.

6. The system of claim 1 , wherein:
the system further comprises a memory configured to store a thigh gap detection rule set that indicates a minimum width value to be considered the thigh gap region; and
identifying the thigh gap region comprises applying the thigh gap detection rule set to the one or more regions to identify the thigh gap region, wherein applying the thigh gap detection rule set comprises:
comparing the width of each of the one or more regions to the minimum width value to be considered the thigh gap region; and
identifying a region from among the one or more regions as the thigh gap region when the region has a width greater than or equal to the minimum width value to be considered the thigh gap region.

7. An apparatus comprising:
a memory operable to store three-dimensional (3D) images, wherein each pixel of the 3D image is associated with a depth value; and
a processor operably coupled to the memory, and configured to:
obtain a 3D image of a rearview of a dairy livestock in a stall;
identify one or more regions within the 3D image comprising depth values greater than a depth value threshold;
identify a thigh gap region among the one or more regions, wherein the thigh gap region comprises an area between hind legs of the dairy livestock;
demarcate an access region within the thigh gap region, wherein the access region is defined by:
a first vertical edge,
a second vertical edge,
a first upper edge spanning between the first vertical edge and the second vertical edge, and
a first lower edge spanning between the first vertical edge and the second vertical edge;

demarcate a tail detection region, wherein the tail detection region is defined by:
a third vertical edge extending vertically from the first vertical edge of the access region,
a fourth vertical edge extending vertically from the second vertical edge of the access region,
a second upper edge spanning between the third vertical edge and the fourth vertical edge, and
a second lower edge spanning between the third vertical edge and the fourth vertical edge, wherein the second lower edge is adjacent to the first upper edge of the access region;

identify one or more tail candidates within the tail detection region;
compare the one or more tail candidates to a tail model; and
identify a tail candidate from among the one or more tail candidates as a tail of the dairy livestock when the tail candidate corresponds with the tail model; and
determine position information for the tail of the dairy livestock in response to identifying the tail of the dairy livestock.

8. The apparatus of claim 7 , wherein:
the tail model indicates a tail shape; and
the tails of the dairy livestock corresponds with the tail shape in at least two of a plurality of depth planes.

9. The apparatus of claim 7 , wherein:
the memory is operable to store a thigh gap detection rule set that identifies a marker positioned between the hind legs of the dairy livestock at a lower edge of the 3D image; and
identifying the thigh gap region comprises applying the thigh gap detection rule set to the one or more regions to identify the thigh gap region, wherein applying the thigh gap detection rule set comprises identifying a region from among the one or more regions that comprises the marker as the thigh gap region.

10. The apparatus of claim 7 , wherein:
the memory is operable to store a thigh gap detection rule set that indicates a minimum area value to be considered the thigh gap region; and
identifying the thigh gap region comprises applying the thigh gap detection rule

Assignees

• Technologies Holdings Corp

Inventors

• Foresman Mark A
• Prevost Bradley J

Classifications

• G06T2207/10012

  Stereo images · CPC title

• G06T7/12

  Edge-based segmentation · CPC title

• G06T7/33

  using feature-based methods · CPC title

• G06T7/75

  involving models · CPC title

• G06T2207/10028

  Range image; Depth image; 3D point clouds · CPC title