An Edge Computing Algorithm Based on Multi-Level Star Sensor Cloud

Star sensors are an important means of autonomous navigation and access to space information for satellites.They have been widely deployed in the aerospace field.To satisfy the requirements for high resolution,timeliness,and confidentiality of star images,we propose an edge computing algorithm based on the star sensor cloud.Multiple sensors cooperate with each other to forma sensor cloud,which in turn extends the performance of a single sensor.The research on the data obtained by the star sensor has very important research and application values.First,a star point extraction model is proposed based on the fuzzy set model by analyzing the star image composition,which can reduce the amount of data computation.Then,a mappingmodel between content and space is constructed to achieve low-rank image representation and efficient computation.Finally,the data collected by the wireless sensor is delivered to the edge server,and a differentmethod is used to achieve privacy protection.Only a small amount of core data is stored in edge servers and local servers,and other data is transmitted to the cloud.Experiments show that the proposed algorithm can effectively reduce the cost of communication and storage,and has strong privacy.

Multi-Directional Reconstruction Algorithm for Panoramic Camera

A panorama can reflect the surrounding scenery because it is an image with a wide angle of view.It can be applied in virtual reality,smart homes and other fields as well.A multi-directional reconstruction algorithm for panoramic camera is proposed in this paper according to the imaging principle of dome camera,as the distortion inevitably exists in the captured panorama.First,parameters of a panoramic image are calculated.Then,a weighting operator with location information is introduced to solve the problem of rough edges by taking full advantage of pixels.Six directions of the mapping model are built,which include up,down,left,right,front and back,according to the correspondence between cylinder and spherical coordinates.Finally,multi-directional image reconstruction can be realized.Various experiments are performed in panoramas(1024×1024)with 30 different shooting scenes.Results show that the azimuth image can be reconstructed quickly and accurately.The fuzzy edge can be alleviated effectively.The rate of pixel utilization can reach 84%,and it is 33%higher than the direct mapping algorithm.Large scale distortion is also further studied.

DRIB:Interpreting DNN with Dynamic Reasoning and Information Bottleneck

The interpretability of deep neural networks has aroused widespread concern in the academic and industrial fields.This paper proposes a new method named the dynamic reasoning and information bottleneck(DRIB)to improve human interpretability and understandability.In the method,a novel dynamic reasoning decision algorithmwas proposed to reduce multiply accumulate operations and improve the interpretability of the calculation.The information bottleneck was introduced to the DRIB model to verify the attribution correctness of the dynamic reasoning module.The DRIB reduces the burden approximately 50%by decreasing the amount of computation.In addition,DRIB keeps the correct rate at approximately 93%.The information bottleneck theory verifies the effectiveness of this method,and the credibility is approximately 85%.In addition,through visual verification of this method,the highlighted area can reach 50%of the predicted area,which can be explained more obviously.Some experiments prove that the dynamic reasoning decision algorithm and information bottleneck theory can be combined with each other.Otherwise,the method provides users with good interpretability and understandability,making deep neural networks trustworthy.