Insect sensing systems and methods
View Patent ↗One example insect sensing system includes a light emitter configured to emit light; a structured light generator positioned to receive the emitted light and configured to generate structured light from the emitted light; a plurality of light sensors arranged in a line, each of the light sensors oriented to receive at least a portion of the structured light and output a sensor signal indicating an amount of light received by the respective light sensor; a processing device configured to: obtain the sensor signals from each of the light sensors, and determine a presence of an insect based a received sensor signal from at least one light sensor, the sensor signal indicating a reduced amount of received light by the at least one light sensor. Another example insect sensing system includes a camera comprising an image sensor and a lens having an aperture of f/2.8 or wider; and a processor configured to obtain an image from the camera and detect an insect in the image.
1. A sensing system comprising:
a camera comprising an image sensor and a lens, the camera positioned to capture an image including an interior portion of an insect release tube, the camera oriented along a focal axis at an oblique angle to a longitudinal axis of the insect release tube, and a depth of focus of the camera is located within an interior volume of the insect release tube; and
a processor in communication with a non-transitory computer-readable medium and configured to execute processor-executable code stored in the non-transitory computer-readable medium to:
obtain an image from the camera;
identify at least one in-focus moving insect in the image; and
ignore any out-of-focus moving insect in the image.
2. The sensing system of claim 1 , wherein the processor is configured to execute processor-executable code stored in the non-transitory computer-readable medium to detect the in-focus moving insect in the image using an edge detection technique.
3. The sensing system of claim 2 , wherein the processor is configured to execute processor-executable code stored in the non-transitory computer-readable medium to:
generate an edge gradient map of the image, and
detect the at least one in-focus moving insect in the image using the edge gradient map.
4. The sensing system of claim 3 , wherein the processor configured to execute processor-executable code stored in the non-transitory computer-readable medium to:
for each pixel in the image, determine an edge using pixels within a pixel window centered on the respective pixel, and
generate the edge gradient map using the determined edges.
5. The sensing system of claim 1 , wherein the processor is configured to execute processor-executable code stored in the non-transitory computer-readable medium to detect the insect in the image using a machine learning technique.
6. The sensing system of claim 1 , wherein the processor is configured to execute processor-executable code stored in the non-transitory computer-readable medium to:
obtain multiple successive images from the camera and detect moving insects in the successive images at a rate of sufficient to capture multiple in-focus images of one or more moving insects, the rate based on the depth of focus and an average flight speed of a type of insects in an insect population to traverse the release tube.
7. The sensing system of claim 6 , wherein the processor is configured to execute processor-executable code stored in the non-transitory computer-readable medium to:
identify the in-focus moving insect in multiple consecutive images; and
increment an insect count by one for the identified in-focus moving insect in on image of the multiple consecutive images, and
not increment the insect count for the identified in-focus moving insect in the other images of the multiple consecutive images.
8. A method comprising:
obtaining an image from a camera comprising an image sensor and a lens;
identifying at least one in-focus moving insect in the image; and
ignoring any out-of-focus moving insect in the image; wherein:
the camera is positioned to capture images of an interior volume of an insect release tube,
the camera is oriented such that a focal axis of the camera is oriented at an oblique angle to a longitudinal axis of the release tube, and
a depth of focus of the camera is located within the interior volume of the insect release tube.
9. The method of claim 8 , further comprising:
iteratively obtaining images from the camera over a period of time;
detecting in-focus moving insects in the images; and
counting a number of detected in-focus moving insects over the period of time.
10. The method of claim 8 , further comprising:
generating an edge gradient map of the image, and
detecting the in-focus moving insect in the image using the edge gradient map.
11. The method of claim 8 , further comprising:
for each pixel in the image, determining an edge using pixels within a pixel window centered on the respective pixel, and
generating an edge gradient map using the determined edges, and wherein detecting the in-focus moving insect is based on the edge gradient map.
12. The system of claim 1 wherein the processor is configured to execute processor-executable code stored in the non-transitory computer-readable medium to:
obtain multiple images from the camera, the multiple images taken in succession over a period of time; and
identify moving insects within the images;
identify one or more in-focus insects in at least one of the images based on the identified moving insects;
detect at least one moving insect in the image based on the identified in-focus insects; and
ignore one or more out-of-focus insects within the images.