Abstract: Introduced here are surveillance systems and associated approaches for obfuscating biometric identifiers generated by, or available to, those surveillance systems for privacy reasons. In the event that a surveillance system generates a biometric identifier (e.g., by imaging a face of a person entering the premises of an organization), caution must be taken to only share the biometric identifier with individuals as necessary for security reasons. The approaches introduced here allow the privacy of persons being surveilled to be protected. Specifically, a computer program may selectively apply blurring as an impermanent mask to obfuscate each face in a digital image. This approach limits “reidentification” of a given person to those scenarios where her identity must be determined.

Abstract: A method includes obtaining a plurality of representative vectors associated with face-related data. The method includes determining an encryption key based on a parameter stored in a record, generating an encrypted vector set by, for each respective vector of the plurality of representative vectors, encrypting the respective vector with a homomorphic encryption operation based on the encryption key, where the encrypted vector set includes a first encrypted vector that is linked to a subset of the face-related data associated with the first plurality of face vectors. The method further includes obtaining an encrypted face search vector using the encryption key to perform homomorphic encryption. The method further includes selecting a first encrypted vector based on the encrypted face search vector and retrieving the subset of the face-related data based on the first encrypted vector.

Abstract: A method for generating and selecting images of objects based on video data and text data includes receiving, at a processor of a video camera system, a video stream including a series of video frames depicting at least one object. A set of at least one classification for the object is generated. Additionally, an image that depicts the object and that includes a cropped portion of a video frame from the series of video frames is generated. A set of at least one index key is generated based on the set of at least one classification, and the image is stored based on the set of at least one index key. The processor receives a signal representing a text input from a user, and the processor performs at least one of (1) retrieval of the image or (2) generation of an alert.

Abstract: A method includes building a firmware image to execute on a bootloader of a system on chip (SoC), the firmware image including first encryption public and private keys, and digitally signing the firmware image with a second encryption private key. The signed firmware image is encrypted with a symmetric encryption key, which in turn is encrypted with a second encryption public key. The encrypted signed firmware image and the encrypted symmetric encryption key are sent to the SoC to cause the SoC to (1) decrypt the encrypted symmetric encryption key to produce the symmetric encryption key using a third encryption private key from a first asymmetric key pair, (2) decrypt the encrypted signed firmware image to produce the signed firmware image using the symmetric encryption key, and (3) verify a digital signature of the signed firmware image using a third encryption public key from a second asymmetric key pair.

Abstract: A method includes receiving, via a processor, a subkey generated concurrently with a video. The video has a first format. A compute device requests the video. The compute device is configured to play videos having a second format. The compute device is not configured to play videos having the first format. The method also includes receiving, via the processor, an encrypted video. The video is encrypted to generate the encrypted video. The method further includes decrypting, via the processor, the encrypted video using the subkey to obtain the video. The method further includes reformatting, via the processor, the video to generate a reformatted video having the second format. The method further includes sending the reformatted video to the second compute device. The method further includes deleting the subkey in response to reformatting the video to generate the reformatted video.

Abstract: In an embodiment, a method includes receiving, from a compute device associated with (1) an organization and (2) a user account that is associated with the organization, a request for sensor data captured by a sensor. The method further includes sending, to the compute device, an encrypted private key generated by encrypting a private key associated with the organization using an identifier key, to cause the compute device to decrypt the encrypted private key using the identifier key to obtain the private key after receiving the encrypted private key. The method further includes sending, to the compute device, an encrypted media key generated by encrypting a media key using a public key associated with the organization, to cause the compute device to decrypt the encrypted media key using the private key to obtain the media key after receiving the encrypted media key.

Abstract: A set of PTZ values associated with a video and a set of timestamps associated with the video are received. The set of PTZ values is generated (1) after a first command from a user to start recording PTZ changes, (2) before a second command from the user to stop recording the PTZ changes, and (3) based on sampling PTZ actions taken by the user, relative to the video, after the first command, and before the second command. Each PTZ value from the set of PTZ values has an associated timestamp from the set of timestamps that indicates a portion of the video from which that PTZ value was sampled. A modified video is generated based on the set of PTZ values and the set of timestamps.

Abstract: Introduced here is a surveillance system that is able to employ an approach to sharing security information, such that organizations have the ability to voluntarily share relevant security information with the individuals who frequent the corresponding buildings. The surveillance system introduced here may not only be able to protect the safety of organizations, but also the privacy of users. In order for a member of the public to truly feel safe—not only from material loss or bodily harm—it is crucial for her to know what information is being recorded, stored, and used.

Abstract: A first document including a decrypting version of a first key and a second document including a representation of a login token are received from the first compute device. An encrypted second key that has been encrypted by an encrypting version of the first key is received after receiving the login token from a second compute device. The second compute device stores the encrypting version of the first key before the receiving of the first document. The encrypted second key is decrypted using the decrypting version of the first key to obtain a plaintext second key. Encrypted sensor data that includes plaintext sensor data that has been (1) captured prior to the receiving of the first document, and (2) encrypted by the plaintext second key is received from the second compute device. The encrypted sensor data is decrypted using the plaintext second key to obtain the plaintext sensor data.

Abstract: A set of PTZ values associated with a video and a set of timestamps associated with the video are received. The set of PTZ values is generated (1) after a first command from a user to start recording PTZ changes, (2) before a second command from the user to stop recording the PTZ changes, and (3) based on sampling PTZ actions taken by the user, relative to the video, after the first command, and before the second command. Each PTZ value from the set of PTZ values has an associated timestamp from the set of timestamps that indicates a portion of the video from which that PTZ value was sampled. A modified video is generated based on the set of PTZ values and the set of timestamps.

Abstract: A non-transitory, processor-readable medium stores instructions that, when executed by a processor, cause the processor to generate, using a first compute device, a video file. The non-transitory, processor-readable medium also stores instructions that, when executed by a processor, cause the processor to cause the video file to be sent to a second compute device that is cloud based, to cause the second compute device to: encode the video file, using a set of at least one software container, to generate an encoded video file; execute, at the set of at least one software container, a streaming protocol to generate a stream based on the encoded video file; and cause, via the set of at least one software container, generation of a set of analytics associated with the video file, based on the stream and using a virtualized software application environment.

Abstract: A method for hybrid video encoding includes receiving, via a browser, a signal representing a requested media, and determining whether the browser is compatible with high efficiency video encoding (H.265). When the browser is compatible with H.265, the requested media is transmitted, via a first video encoder, in a non-transcoded, H.265 format. When the browser is incompatible with H.265, one of: (1) a H.265 version of the requested media is transcoded to a transcoded H.264 version when the requested media includes recorded video footage, (2) the H.265 version of the requested media is transcoded to the transcoded H.264 version when the requested media does not include recorded video footage and includes full resolution video footage, or (3) the requested media is transmitted via a second video encoder in a non-transcoded, H.264 format when the requested media does not include recorded video footage and does not include full resolution video footage.

Abstract: A non-transitory, processor-readable medium stores instructions that, when executed by a processor, cause the processor to generate, using a first compute device, a video file. The non-transitory, processor-readable medium also stores instructions that, when executed by a processor, cause the processor to cause the video file to be sent to a second compute device that is cloud based, to cause the second compute device to: encode the video file, using a set of at least one software container, to generate an encoded video file; execute, at the set of at least one software container, a streaming protocol to generate a stream based on the encoded video file; and cause, via the set of at least one software container, generation of a set of analytics associated with the video file, based on the stream and using a virtualized software application environment.

Abstract: A trajectory-based object search process includes receiving a user request specifying a geographic region of interest and/or a time period of interest. A set of video-derived object trajectories is identified based on the user request. At least one event is identified based on the set of video-derived object trajectories, by processing each video-derived object trajectory individually or by aggregating video-derived object trajectories, from the set of video-derived object trajectories, that overlap with respect to at least one feature. For each event, a preview image is selected that includes a thumbnail image and/or a video frame, based on the user request and using a ranking algorithm, and event metadata associated with the preview image is received. Also for each event, a video segment associated with that event is received, and the preview image and/or the video segment is caused to be displayed to a user associated with the user request.

Abstract: A first document including a decrypting version of a first key and a second document including a representation of a login token are received from the first compute device. An encrypted second key that has been encrypted by an encrypting version of the first key is received after receiving the login token from a second compute device. The second compute device stores the encrypting version of the first key before the receiving of the first document. The encrypted second key is decrypted using the decrypting version of the first key to obtain a plaintext second key. Encrypted sensor data that includes plaintext sensor data that has been (1) captured prior to the receiving of the first document, and (2) encrypted by the plaintext second key is received from the second compute device. The encrypted sensor data is decrypted using the plaintext second key to obtain the plaintext sensor data.

Abstract: A method for generating and selecting images of objects based on video data and text data includes receiving, at a processor of a video camera system, a video stream including a series of video frames depicting at least one object. A set of at least one classification for the object is generated. Additionally, an image that depicts the object and that includes a cropped portion of a video frame from the series of video frames is generated. A set of at least one index key is generated based on the set of at least one classification, and the image is stored based on the set of at least one index key. The processor receives a signal representing a text input from a user, and the processor performs at least one of (1) retrieval of the image or (2) generation of an alert.

Abstract: A trajectory-based object search process includes receiving a user request specifying a geographic region of interest and/or a time period of interest. A set of video-derived object trajectories is identified based on the user request. At least one event is identified based on the set of video-derived object trajectories, by processing each video-derived object trajectory individually or by aggregating video-derived object trajectories, from the set of video-derived object trajectories, that overlap with respect to at least one feature. For each event, a preview image is selected that includes a thumbnail image and/or a video frame, based on the user request and using a ranking algorithm, and event metadata associated with the preview image is received. Also for each event, a video segment associated with that event is received, and the preview image and/or the video segment is caused to be displayed to a user associated with the user request.

Abstract: A non-transitory, processor-readable medium stores instructions that, when executed by a processor, cause the processor to generate, using a first compute device, a video file. The non-transitory, processor-readable medium also stores instructions that, when executed by a processor, cause the processor to cause the video file to be sent to a second compute device that is cloud based, to cause the second compute device to: encode the video file, using a set of at least one software container, to generate an encoded video file; execute, at the set of at least one software container, a streaming protocol to generate a stream based on the encoded video file; and cause, via the set of at least one software container, generation of a set of analytics associated with the video file, based on the stream and using a virtualized software application environment.

Abstract: First video data captured by a first camera from a set of cameras is received and caused to be stored in a first data stripe from a set of data stripes. Second video data captured by the first camera is received and caused to be stored in a second data stripe from the set of data stripes. An indication is received that the first video data has become inaccessible. Data associated with the first data stripe is received from a subset of cameras from the set of cameras that excludes the first camera. The first video data is generated based on the data received from the subset of cameras.

Abstract: A computer vision processor of a camera generates hyperzooms for persons or vehicles from image frames captured by the camera. The hyperzooms include a first hyperzoom associated with the persons or vehicles. The computer vision processor tracks traffic patterns of the persons or vehicles while obviating network usage by the camera by predicting positions of the persons or vehicles using a Kalman Filter from the first hyperzoom. The persons or vehicles are detected in the second hyperzoom. The positions of the persons or vehicles are updated based on detecting the persons or vehicles in the second hyperzoom. The first hyperzoom is removed from the camera. Tracks of the persons or vehicles are generated based on the updated positions. The second hyperzoom is removed from the camera. Track metadata is generated from the tracks for storing in a key-value database located on a non-transitory computer-readable storage medium of the camera.