Abstract: 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.

Abstract: Method, electronic device, and computer readable medium embodiments are disclosed. In one embodiment, a method includes receiving image data, manipulating the received image data based on a set of transform parameters, and analyzing the manipulated image data to generate metadata. The metadata statistically describes the received image data. The method also includes selecting a neural network from a plurality of neural networks to perform a second analysis, wherein the neural network is selected based on the generated metadata. The method additionally includes performing a second analysis of the received image data by the selected neural network based on the generated metadata to extract information from the received image data.

Abstract: Method, electronic device, and computer readable medium embodiments are disclosed. In one embodiment, a method includes training a neural network using a first image dataset and a first truth dataset, then using the trained neural network to analyze a second image dataset. The training includes modifying a loss function of the neural network to forego penalizing the neural network when a feature is predicted with higher than a first confidence level by the neural network, and the first truth dataset has no feature corresponding to the predicted feature.