System and method for space object detection in daytime sky images
In some embodiments, space objects may be detected within shortwave infrared (SWIR) images captured during the daytime. Some embodiments include obtaining a stacked image by stacking shortwave infrared (SWIR) images. A spatial background-difference image may be generated based on the stacked image, and a matched-filter image may be obtained based on the spatial background-difference image. A binary mask may be generated based on the matched-filter image. The binary mask may include a plurality of bits each of which including a first value or a second value based on whether a signal-to-noise ratio (SNR) associated with that bit satisfies a threshold condition. Output data may be generated based on the spatial background-difference image and the binary mask, where the output data provides observations on detected space objects in orbit.
1. A system for detecting space objects, the system comprising:
a computer system comprising one or more processors configured to execute one or more computer program instructions that, when executed by the one or more processors, effectuate operations comprising:
generating a stacked image by stacking a plurality of images that correspond to a plurality of seconds of daytime sky imaged by a ground-based camera system that is responsive at least to infrared light;
generating (i) a first image based on the stacked image and (ii) a second image by performing a convolution of the first image;
generating a background-difference image by determining a difference between the second image and the first image;
generating a matched-filter image based on the background-difference image, wherein the matched-filter image comprises an array of pixels;
selecting one or more pixels from the array of pixels based on a signal intensity of one or more corresponding pixel values of the one or more pixels in the matched-filter image;
generating at least one cluster having one or more pixel locations of each of the one or more pixels;
detecting at least one space object based on the at least one cluster; and
generating, based on detecting the at least one space object, output data indicating that the at least one space object has been detected.
2. The system of claim 1 , wherein:
the camera system comprises:
one or more shortwave infrared (SWIR) sensors; and
one or more thermoelectric coolers (TECs).
3. The system of claim 1 , wherein generating the matched-filter image comprises:
performing a convolution of the background-difference image with a point-source function kernel.
4. The system of claim 1 , wherein the operations further comprise:
determining one or more candidate space objects within the matched-filter image based on a binary mask, wherein the at least one space object is detected from the one or more candidate space objects.
5. The system of claim 1 , wherein generating the output data comprises:
generating an output image corresponding to the background-difference image and the at least one space object.
6. The system of claim 1 , comprising:
means for detecting space objects within shortwave infrared (SWIR) images of daytime sky.
7. The system of claim 1 , wherein the operations further comprise:
computing a numerical value for each pixel in an array of pixels to be used for the stacked image.
8. The system of claim 1 , wherein the operations further comprise:
computing a decorrelated value associated with a pixel of the stacked image.
9. The system of claim 1 , wherein the operations further comprise:
determining pixel response non-uniformities in one or both of the stacked image or the plurality of images.
10. The system of claim 1 , wherein the operations further comprise:
normalizing signal to noise ratios to a wavelength.
11. The system of claim 1 , wherein the ground-based camera system:
is configured to maintain dark currents less than or equal to 100 kilo-electrons per pixel per second;
is configured to capture images with a framerate greater than 100 Hertz; and
comprises an optical train that comprises one or more lowpass filters with cutoff wavelengths between 0.9-1.7 microns, the one or more lowpass filters comprising one or more infrared polarizers.
12. The system of claim 1 , wherein the ground-based camera system is responsive to wavelengths between 1.0-1.7 microns.
13. One or more non-transitory computer readable media comprising computer program instructions that, when executed by one or more processors, effectuate operations comprising:
obtaining a stacked image based on a plurality of images of daytime sky, wherein the plurality of images are obtained from a camera system comprising one or more sensors responsive at least to infrared light;
generating (i) a first image based on the stacked image and (ii) a second image by performing a convolution of the first image;
generating a background-difference image by determining a difference between the second image and the first image;
generating a matched-filter image based on the background-difference image, wherein the matched-filter image comprises an array of pixels;
selecting one or more pixels from the array of pixels based on a signal intensity of one or more corresponding pixel values of the one or more pixels in the matched-filter image;
generating at least one cluster having one or more pixel locations of each of the one or more pixels; and
generating, based on the at least one cluster, output data that indicates whether a space object has been detected.
14. The one or more non-transitory computer readable media of claim 13 , wherein the output data is generated further based on the background-difference image.
15. The one or more non-transitory computer readable media of claim 14 , wherein the operations further comprise:
performing a second convolution based on the background-difference image and a point-source function kernel to obtain the matched-filter image, wherein:
a binary mask is generated further based on the matched-filter image,
candidate space objects are detected based on the matched-filter image, and
the output data indicates whether the space object has been detected based on the candidate space objects.
16. The one or more non-transitory computer readable media of claim 15 , wherein generating the output data comprises:
retrieving, based on a location of the camera system when the plurality of images were captured, space object location information indicating a plurality of space objects; and
determining that at least one of the candidate space objects is a space object based on at least one confidence measure indicating that the at least one of the candidate space objects is not a false positive, wherein the output data comprises an indication of the space object.
17. The one or more non-transitory computer readable media of claim 13 , wherein the stacked image comprises an array of pixels, each pixel of the array of pixels has a stacked numerical value, the one or more sensors are responsive to light having a wavelength of 1 micron, and the first image is generated based on the stacked image, one or more offsets, and one or more gains.
18. The one or more non-transitory computer readable media of claim 17 , wherein the one or more sensors include one or more short-wave infrared sensors (SWIR), and the operations further comprise:
obtaining a bias value associated with each SWIR sensor of the one or more SWIR sensors, wherein the one or more offsets comprise the bias value, and wherein a stacked numerical value of each pixel of the array of pixels of the stacked image is adjusted based on the bias value.
19. The one or more non-transitory computer readable media of claim 17 , further comprising:
obtaining a correlated noise value associated with each pixel of the array of pixels of the stacked image, wherein the stacked numerical value of each pixel of the array of pixels of the stacked image is adjusted based on the correlated noise value associated with each pixel of the array of pixels of the stacked image.
20. The one or more non-transitory computer readable media of claim 17 , further comprising:
determining, based on a precomputed function representing pixel response non-uniformity (PRNU) of each sensor of the one or more sensors, a gain value of each pixel of the array of pixels of the stacked image, and wherein the stacked numerical value of each pixel of the array of pixels of the stacked image is adjusted based on the gain value associated with each pixel of the array of pixels of the stacked image.
21. The one or more non-transitory computer readable media of claim 13 , wherein the camera system further comprises one or more thermoelectric coolers (TECs).
22. The one or more non-transitory computer readable media of claim 13 , wherein generating the output data comprises:
generating an output image comprising a background-difference image and an observation of the space object.
23. A method comprising:
generating a stacked image by stacking a plurality of images of daytime sky obtained from a camera system comprising one or more sensors;
generating (i) a first image based on the stacked image and (ii) a second image by performing a convolution of the first image;
generating a background-difference image by determining a difference between the second image and the first image;
generating a matched-filter image based on the background-difference image, wherein the matched-filter image comprises an array of pixels;
selecting one or more pixels from the array of pixels based on a signal intensity of one or more corresponding pixel values of the one or more pixels in the matched-filter image for each of the selected one or more pixels;
generating at least one cluster having one or more pixel locations of each of the one or more pixels; and
generating, with the computer system and based on the at least one cluster, output data that indicates whether a space object has been detected.