Space-based optical(SBO)space surveillance has attracted widespread interest in the last two decades due to its considerable value in space situation awareness(SSA).SBO observation strategy,which is related to the per...Space-based optical(SBO)space surveillance has attracted widespread interest in the last two decades due to its considerable value in space situation awareness(SSA).SBO observation strategy,which is related to the performance of space surveillance,is the top-level design in SSA missions reviewed.The recognized real programs about SBO SAA proposed by the institutions in the U.S.,Canada,Europe,etc.,are summarized firstly,from which an insight of the development trend of SBO SAA can be obtained.According to the aim of the SBO SSA,the missions can be divided into general surveillance and space object tracking.Thus,there are two major categories for SBO SSA strategies.Existing general surveillance strategies for observing low earth orbit(LEO)objects and beyond-LEO objects are summarized and compared in terms of coverage rate,revisit time,visibility period,and image processing.Then,the SBO space object tracking strategies,which has experienced from tracking an object with a single satellite to tracking an object with multiple satellites cooperatively,are also summarized.Finally,this paper looks into the development trend in the future and points out several problems that challenges the SBO SSA.展开更多
In this study,a novel approach based on the U-Net deep neural network for image segmentation is leveraged for real-time extraction of tracklets from optical acquisitions.As in all machine learning(ML)applications,a se...In this study,a novel approach based on the U-Net deep neural network for image segmentation is leveraged for real-time extraction of tracklets from optical acquisitions.As in all machine learning(ML)applications,a series of steps is required for a working pipeline:dataset creation,preprocessing,training,testing,and post-processing to refine the trained network output.Online websites usually lack ready-to-use datasets;thus,an in-house application artificially generates 360 labeled images.Particularly,this software tool produces synthetic night-sky shots of transiting objects over a specified location and the corresponding labels:dual-tone pictures with black backgrounds and white tracklets.Second,both images and labels are downscaled in resolution and normalized to accelerate the training phase.To assess the network performance,a set of both synthetic and real images was inputted.After the preprocessing phase,real images were fine-tuned for vignette reduction and background brightness uniformity.Additionally,they are down-converted to eight bits.Once the network outputs labels,post-processing identifies the centroid right ascension and declination of the object.The average processing time per real image is less than 1.2 s;bright tracklets are easily detected with a mean centroid angular error of 0.25 deg in 75%of test cases with a 2 deg field-of-view telescope.These results prove that an ML-based method can be considered a valid choice when dealing with trail reconstruction,leading to acceptable accuracy for a fast image processing pipeline.展开更多
基金This work was supported by the National Natural Science Foundation of China(61690210,61690213).
文摘Space-based optical(SBO)space surveillance has attracted widespread interest in the last two decades due to its considerable value in space situation awareness(SSA).SBO observation strategy,which is related to the performance of space surveillance,is the top-level design in SSA missions reviewed.The recognized real programs about SBO SAA proposed by the institutions in the U.S.,Canada,Europe,etc.,are summarized firstly,from which an insight of the development trend of SBO SAA can be obtained.According to the aim of the SBO SSA,the missions can be divided into general surveillance and space object tracking.Thus,there are two major categories for SBO SSA strategies.Existing general surveillance strategies for observing low earth orbit(LEO)objects and beyond-LEO objects are summarized and compared in terms of coverage rate,revisit time,visibility period,and image processing.Then,the SBO space object tracking strategies,which has experienced from tracking an object with a single satellite to tracking an object with multiple satellites cooperatively,are also summarized.Finally,this paper looks into the development trend in the future and points out several problems that challenges the SBO SSA.
文摘In this study,a novel approach based on the U-Net deep neural network for image segmentation is leveraged for real-time extraction of tracklets from optical acquisitions.As in all machine learning(ML)applications,a series of steps is required for a working pipeline:dataset creation,preprocessing,training,testing,and post-processing to refine the trained network output.Online websites usually lack ready-to-use datasets;thus,an in-house application artificially generates 360 labeled images.Particularly,this software tool produces synthetic night-sky shots of transiting objects over a specified location and the corresponding labels:dual-tone pictures with black backgrounds and white tracklets.Second,both images and labels are downscaled in resolution and normalized to accelerate the training phase.To assess the network performance,a set of both synthetic and real images was inputted.After the preprocessing phase,real images were fine-tuned for vignette reduction and background brightness uniformity.Additionally,they are down-converted to eight bits.Once the network outputs labels,post-processing identifies the centroid right ascension and declination of the object.The average processing time per real image is less than 1.2 s;bright tracklets are easily detected with a mean centroid angular error of 0.25 deg in 75%of test cases with a 2 deg field-of-view telescope.These results prove that an ML-based method can be considered a valid choice when dealing with trail reconstruction,leading to acceptable accuracy for a fast image processing pipeline.
