Abstract: Techniques herein use in-memory column vectors to process data that is external to a database management system (DBMS) and logically join the external data with data that is native to the DBMS. In an embodiment, a computer maintains a data dictionary for native data that is durably stored in an DBMS and external data that is not durably stored in the DBMS. From a client through a connection to the DBMS, the computer receives a query. The computer loads the external data into an in-memory column vector that resides in random access memory of the DBMS. Based on the query and the data dictionary, the DBMS executes a data join of the in-memory column vector with the native data. To the client through said connection, the computer returns results of the query based on the data join.

Abstract: Techniques are disclosed relating to providing fast access to restored data in a cloud storage environment. A computing system stores multiple sets of incremental backup data that reflect changes in data being backed up between backup intervals and metadata that indicates which set of incremental backup data stores a given object. The computing system generates an endpoint for a requesting computing system, where the endpoint supports requests for restored backup data and data responses. In response to a request from the requesting computing system via the endpoint, the computing system queries the metadata based on the request and stores metadata retrieved from the query in a key/value store using object identification information as key data and the retrieved metadata as value data. The computing system provides requested data according to a lazy loading technique, including providing requested data via the endpoint based on the metadata in the key/value store.

Abstract: Techniques are disclosed relating to providing fast access to restored data in a cloud storage environment. A computing system stores multiple sets of incremental backup data that reflect changes in data being backed up between backup intervals and metadata that indicates which set of incremental backup data stores a given object. The computing system generates an endpoint for a requesting computing system, where the endpoint supports requests for restored backup data and data responses. In response to a request from the requesting computing system via the endpoint, the computing system queries the metadata based on the request and stores metadata retrieved from the query in a key/value store using object identification information as key data and the retrieved metadata as value data. The computing system provides requested data according to a lazy loading technique, including providing requested data via the endpoint based on the metadata in the key/value store.

Abstract: Disclosed techniques relate to security of backup data. In some embodiments, a method includes receiving, by data protection service running on a cloud computing system, a first encrypted copy of a backup of a first data store that is associated with a first account of an organization, where the first encrypted copy is encrypted using a first custodian cryptographic key that is shared between the organization and the data protection service that is different than a first production cryptographic key that is private and used by the organization to encrypt a non-backup version of the first data store. The method may include generating a second encrypted copy of the backup, including by encrypting the backup using a storage cryptographic key. The method may include storing the second encrypted copy of the backup in a second data store that is associated with the data protection service.

Abstract: Disclosed techniques relate to security of backup data. In some embodiments, a method includes receiving, by data protection service running on a cloud computing system, a first encrypted copy of a backup of a first data store that is associated with a first account of an organization, where the first encrypted copy is encrypted using a first custodian cryptographic key that is shared between the organization and the data protection service that is different than a first production cryptographic key that is private and used by the organization to encrypt a non-backup version of the first data store. The method may include generating a second encrypted copy of the backup, including by encrypting the backup using a storage cryptographic key. The method may include storing the second encrypted copy of the backup in a second data store that is associated with the data protection service.

Abstract: Disclosed techniques relate to security of backup data. In some embodiments, a method includes receiving, by data protection service running on a cloud computing system, a first encrypted copy of a backup of a first data store that is associated with a first account of an organization, where the first encrypted copy is encrypted using a first custodian cryptographic key that is shared between the organization and the data protection service that is different than a first production cryptographic key that is private and used by the organization to encrypt a non-backup version of the first data store. The method may include generating a second encrypted copy of the backup, including by encrypting the backup using a storage cryptographic key. The method may include storing the second encrypted copy of the backup in a second data store that is associated with the data protection service.

Abstract: Techniques are disclosed relating to providing fast access to restored data in a cloud storage environment. A computing system stores multiple sets of incremental backup data that reflect changes in data being backed up between backup intervals and metadata that indicates which set of incremental backup data stores a given object. The computing system generates an endpoint for a requesting computing system, where the endpoint supports requests for restored backup data and data responses. In response to a request from the requesting computing system via the endpoint, the computing system queries the metadata based on the request and stores metadata retrieved from the query in a key/value store using object identification information as key data and the retrieved metadata as value data. The computing system provides requested data according to a lazy loading technique, including providing requested data via the endpoint based on the metadata in the key/value store.

Abstract: A snapshot hyperspectral imaging method includes the steps of: S1, selecting a set of reference wavelengths for calibration, rectifying the shifted positions due to dispersion at each reference wavelength, and selecting a center wavelength; S2, estimating relative dispersion at each reconstructed wavelength with respect to the center wavelength; S3, generating a dispersion matrix describing the direction of dispersion, and generating a spectral response matrix using a spectral response curve of a sensor; S4, capturing images blurred with dispersion; S5, deblurring the dispersed images captured in S4 using the dispersion matrix and the spectral response matrix generated in S3 to obtain spectral data spatially aligned in all spectrums; and S6, projecting the aligned spectral data obtained in S5 into color space, extracting a foreground image by a threshold method, sampling the dispersed images obtained in S4 as strong prior constraints for the foreground image, and reconstructing accurate spatial hyperspectral

Abstract: Techniques are disclosed relating to providing protection groups and rapid determination of expired objects and associated storage resources in a cloud-based backup storage context. In various embodiments, the disclosed techniques include generating, by a computing system, incremental backup data for a backup based on protection group information, including a set of cloud-based key-value data store buckets, filter information, and policy information. Disclosed techniques also include rapid determination of expired objects and associated storage resources. Disclosed techniques may advantageously provide a centralized view across buckets, accounts, and regions and allow users to target specific subsets of their data stores for backup, which may improve performance and reduce backup storage costs, relative to traditional techniques.

Abstract: A method for removing periodic noise from a reconstructed light field image includes the steps of: acquiring a light field image of a sample; acquiring an optical center position map without the sample; calibrating the imaging centers of the microlenses and performing reconstruction on the light field image; transforming a reconstructed light field image to the frequency domain and generating an image frequency spectrum; preprocessing the image frequency spectrum; generating a low-pass filter; multiplying the low-pass filter with the preprocessed image frequency spectrum, and then setting the frequency spectrum value of the low-frequency component to zero; performing binarization on the reconstructed light field image frequency spectrum to obtain an image mask; removing the high-frequency periodic noise component from the original frequency spectrum of the reconstructed light field image; and transforming the filtered reconstructed light field image frequency spectrum back to the spatial domain to obtain the

Abstract: Techniques are disclosed relating to providing protection groups and rapid determination of expired objects and associated storage resources in a cloud-based backup storage context. In various embodiments, the disclosed techniques include generating, by a computing system, incremental backup data for a backup based on protection group information, including a set of cloud-based key-value data store buckets, filter information, and policy information. Disclosed techniques also include rapid determination of expired objects and associated storage resources. Disclosed techniques may advantageously provide a centralized view across buckets, accounts, and regions and allow users to target specific subsets of their data stores for backup, which may improve performance and reduce backup storage costs, relative to traditional techniques.

Abstract: Techniques are disclosed relating to providing data views from a time-series data lake to a data warehousing system. In various embodiments, the disclosed techniques include providing, by a cloud-based service, a data lake service that maintains a time-series data lake storing a time-series representation of data from a plurality of data sources associated with a first organization. In some embodiments, the cloud-based service may receive additional backup data, including a first backup image of a first data source, associated with the first organization as part of a backup operation. The cloud-based service may then store a logical backup of the first data source in the data lake and, in response to a query from a data warehousing system, the cloud-based service may retrieve a particular view of the backup data from the data lake and provide it to the data warehousing system.

Abstract: Techniques are disclosed relating to providing protection groups and rapid determination of expired objects and associated storage resources in a cloud-based backup storage context. In various embodiments, the disclosed techniques include generating, by a computing system, incremental backup data for a backup based on protection group information, including a set of cloud-based key-value data store buckets, filter information, and policy information. Disclosed techniques also include rapid determination of expired objects and associated storage resources. Disclosed techniques may advantageously provide a centralized view across buckets, accounts, and regions and allow users to target specific subsets of their data stores for backup, which may improve performance and reduce backup storage costs, relative to traditional techniques.

Abstract: Techniques are disclosed relating to providing object-level incremental backups and data restoration management techniques in a cloud-based backup storage context. In various embodiments, the disclosed techniques include generating, by a computing system, object-level differentials that maintain differences between successive inventories (e.g., added, deleted, and amended objects) and are used to perform incremental backups. Disclosed techniques also include restoration management methods that leverage parallelization, via chunks of data that may be processed in parallel by cloud worker modules, and protection group mechanisms to restore single buckets, multiple buckets, single objects, multiple objects, objects and buckets that match specific search criteria, etc. Disclosed techniques may advantageously improve performance of data backup and restoration operations, relative to traditional techniques.

Abstract: A method for removing periodic noise from a reconstructed light field image includes the steps of: acquiring a light field image of a sample; acquiring an optical center position map without the sample; calibrating the imaging centers of the microlenses and performing reconstruction on the light field image; transforming a reconstructed light field image to the frequency domain and generating an image frequency spectrum; preprocessing the image frequency spectrum; generating a low-pass filter; multiplying the low-pass filter with the preprocessed image frequency spectrum, and then setting the frequency spectrum value of the low-frequency component to zero; performing binarization on the reconstructed light field image frequency spectrum to obtain an image mask; removing the high-frequency periodic noise component from the original frequency spectrum of the reconstructed light field image; and transforming the filtered reconstructed light field image frequency spectrum back to the spatial domain to obtain the

Abstract: Techniques herein use in-memory column vectors to process data that is external to a database management system (DBMS) and logically join the external data with data that is native to the DBMS. In an embodiment, a computer maintains a data dictionary for native data that is durably stored in an DBMS and external data that is not durably stored in the DBMS. From a client through a connection to the DBMS, the computer receives a query. The computer loads the external data into an in-memory column vector that resides in random access memory of the DBMS. Based on the query and the data dictionary, the DBMS executes a data join of the in-memory column vector with the native data. To the client through said connection, the computer returns results of the query based on the data join.

Abstract: Techniques are disclosed relating to the storage of backup data using a time-series data lake. For example, in various embodiments, the disclosed techniques include providing a cloud-based data lake service that maintains data for a plurality of organizations and where, for a first organization, the cloud-based data lake service maintains a time-series data lake that stores a time-series representation of data associated with the first organization. In various embodiments, the data lake service may receive backup data from a plurality of data sources associated with the first organization, generate metadata associated with the backup data, and store the backup data, along with the corresponding metadata, in the time-series data lake.

Abstract: Techniques herein use in-memory column vectors to process data that is external to a database management system (DBMS) and logically join the external data with data that is native to the DBMS. In an embodiment, a computer maintains a data dictionary for native data that is durably stored in an DBMS and external data that is not durably stored in the DBMS. From a client through a connection to the DBMS, the computer receives a query. The computer loads the external data into an in-memory column vector that resides in random access memory of the DBMS. Based on the query and the data dictionary, the DBMS executes a data join of the in-memory column vector with the native data. To the client through said connection, the computer returns results of the query based on the data join.

Abstract: A snapshot hyperspectral imaging method includes the steps of: S1, selecting a set of reference wavelengths for calibration, rectifying the shifted positions due to dispersion at each reference wavelength, and selecting a center wavelength; S2, estimating relative dispersion at each reconstructed wavelength with respect to the center wavelength; S3, generating a dispersion matrix describing the direction of dispersion, and generating a spectral response matrix using a spectral response curve of a sensor; S4, capturing images blurred with dispersion; S5, deblurring the dispersed images captured in S4 using the dispersion matrix and the spectral response matrix generated in S3 to obtain spectral data spatially aligned in all spectrums; and S6, projecting the aligned spectral data obtained in S5 into color space, extracting a foreground image by a threshold method, sampling the dispersed images obtained in S4 as strong prior constraints for the foreground image, and reconstructing accurate spatial hyperspectral

Abstract: Techniques are disclosed relating to the modification of data in a time-series data lake. For example, in various embodiments, the disclosed techniques include a cloud-based service that maintains a time-series data lake that includes, for an organization, a time-series representation of data from one or more of the organization's data sources. The cloud-based service may receive a request to modify data associated with a particular user of the organization. As a non-limiting example, this request may correspond to a “Right to Be Forgotten” request from the particular user. This request may include one or more search parameters and an indication of one or more modifications to be performed. Based on the request, the cloud-based service may parse the time-series data lake to identify a subset of data that matches the one or more search parameters and perform the requested modifications on the subset of data in the time-series data lake.