System and method of counting livestock
A system configured to receive video and/or images from an image capture device over a livestock path, generate feature maps from an image of the video by applying at least a first convolutional neural network, slide a window across the feature maps to obtain a plurality of anchor shapes, determine if each anchor shape contains an object to generate a plurality of regions of interest, each of the plurality of regions of interest being a non-rectangular, polygonal shape, extract feature maps from each region of interest, classify objects in each region of interest, in parallel with classification, predict segmentation masks on at least a subset of the regions of interest in a pixel-to-pixel manner, identify individual animals within the objects based on classifications and the segmentation masks, and count individual animals based on identification, and provide the count to a digital device for display, processing, and/or reporting.
1. A system comprising:
at least one processor; and
memory, the memory containing instructions to control any number of the at least one processor to:
receive one or more images from an image capture device, the image capture device being positioned over a path, the one or more images capturing animals or portions of animals in motion along the path, the image capture device including at least one camera;
identify individual animals or portions of animals based on one or more images using instance segmentation;
determine, using the instance segmentation, when at least one of the individual animals or portions of animals passes a first zone and incrementing a count, the first zone being located at a position within the path and being within a field of view of the image capture device;
determine, using the instance segmentation, when at least one of the individual animals or portions of animals returns to the path from the first zone and decrementing the count, wherein decrementing the count includes the instance segmentation recognizing a particular animal or portion of a particular animal as having previously passed the first zone; and
provide the count to a digital device for display.
2. The system of claim 1 , wherein the animals are one of sheep, goats, chickens, or turkeys.
3. The system of claim 1 , wherein the image capture device comprises a LiDAR device.
4. The system of claim 1 , wherein counting occurs in real time as the animals or portions of animals moves along the path.
5. The system of claim 1 , wherein the determine when at least one of the individual animals or portions of animals passes the first zone and incrementing the count when the animal enters the first zone.
6. A system comprising:
at least one processor; and
memory, the memory containing instructions to control any number of the at least one processor to:
receive one or more images from an image capture device, the image capture device being positioned over a path, the one or more images capturing animals or portions of animals in motion along the path, the image capture device including at least one camera;
identify individual animals or portions of animals based on one or more images using instance segmentation;
determine, using the instance segmentation, when at least one of the individual animals or portions of animals passes a first zone and incrementing a count, the first zone being located at a position within the path and being within a field of view of the image capture device;
determine, using the instance segmentation, when at least one of the individual animals or portions of animals returns to the path from the first zone and decrementing the count, wherein determine when at least one of the individual animals or portions of animals returns to the path from the first zone further includes not decrementing the count until the instance segmentation recognizes a particular animal as having previously passed through the first zone; and
provide the count to a digital device for display.
7. A non-transitory computer readable medium comprising instructions to a control at least one processor to perform a method, the method comprising:
receiving one or more images from an image capture device, the image capture device being positioned over a path, the one or more images capturing animals or portions of animals in motion along the path, the image capture device including at least one camera;
identifying individual animals or portions of animals based on one or more images using instance segmentation;
determining, using the instance segmentation, when at least one of the individual animals or portions of animals passes a first zone and incrementing a count, the first zone being located at a position within the path and being within a field of view of the image capture device;
determining, using the instance segmentation, when at least one of the individual animals or portions of animals returns to the path from the first zone and decrementing the count, wherein decrementing the count includes the instance segmentation recognizing a particular animal or portion of a particular animal as having previously passed the first zone; and
providing the count to a digital device for display.
8. The non-transitory computer readable medium of claim 7 , wherein the animals are one of sheep, goats, chickens, or turkeys.
9. The non-transitory computer readable medium of claim 7 , wherein the image capture device comprises a LiDAR device.
10. The non-transitory computer readable medium of claim 7 , wherein counting occurs in real time as the animals or portions of animals moves along the path.
11. The non-transitory computer readable medium of claim 7 , wherein the determining when at least one of the individual animals or portions of animals passes the first zone and incrementing the count when the animal enters the first zone.
12. A non-transitory computer readable medium comprising instructions to a control at least one processor to perform a method, the method comprising:
receiving one or more images from an image capture device, the image capture device being positioned over a path, the one or more images capturing animals or portions of animals in motion along the path, the image capture device including at least one camera;
identifying individual animals or portions of animals based on one or more images using instance segmentation;
determining, using the instance segmentation, when at least one of the individual animals or portions of animals passes a first zone and incrementing a count, the first zone being located at a position within the path and being within a field of view of the image capture device;
determining, using the instance segmentation, when at least one of the individual animals or portions of animals returns to the path from the first zone and decrementing the count, wherein determine when at least one of the individual animals or portions of animals returns to the path from the first zone further includes not decrementing the count until the instance segmentation recognizes a particular animal as having previously passed through the first zone; and
providing the count to a digital device for display.
13. A method comprising:
receiving one or more images from an image capture device, the image capture device being positioned over a path, the one or more images capturing animals or portions of animals in motion along the path, the image capture device including at least one camera;
identifying individual animals or portions of animals based on one or more images using instance segmentation;
determining, using the instance segmentation, when at least one of the individual animals or portions of animals passes a first zone and incrementing a count, the first zone being located at a position within the path and being within a field of view of the image capture device;
determining, using the instance segmentation, when at least one of the individual animals or portions of animals returns to the path from the first zone and decrementing the count, wherein decrementinq the count includes the instance segmentation recognizing a particular animal or portion of a particular animal as having previously passed the first zone; and
providing the count to a digital device for display.