Abstract: Methods, systems, and techniques for redacted video exports are disclosed. Consistent with example embodiments, a bounding box may double as a redaction boundary.

Abstract: A camera device has a dome bubble member and an imaging unit housed within the camera chamber. A heat-emitting element, such as a film, may be arranged about the lens unit and is adapted to radiate heat for heating the dome bubble member. The camera device may include a sealing member adapted to sealingly engage a portion of the dome bubble member, whereby the heat radiated from the heat-emitting element is substantially contained within the sealed sub-chamber. The imaging unit may be rotatable about a first axis and a second axis in which the second axis is offset from the center of the dome bubble member and is displaceable in at least one direction transverse to itself. The camera device may have a shroud member that is pivotal about a third axis. The camera device may also have a shroud member that is transmissive to infra-red light.

Abstract: Methods, systems, and techniques for sharing layers between convolutional neural networks (CNNs). A data processing system may include a first and a second CNN that share a first group of layers. The first CNN may include the first group of layers in series with a second group of layers and be configured such that data for the first CNN is input to the first group of layers. The second CNN may include the first group of layers in series with a third group of layers and be configured such that data for the second CNN is also input to the first group of layers.

Abstract: For a mobile device with a depleted battery, an access control reader is configured to wirelessly transfer power, thereafter authorize an access request received from the mobile device, and, in response to authorizing the access request, grant access to a resource.

Abstract: A spherical camera is disclosed. The camera includes an imaging unit. A base of the camera includes a track. A spherical housing includes a first housing part for containing the imaging unit. A second housing part includes a dove tail shaped to be slidably received within the track of the base. A loop is positionable around a periphery surface of the base, the loop being tightenable from a first position wherein the spherical housing is tiltable along the track to a second position wherein the spherical housing is locked in position.

Abstract: There is described a multi-headed camera comprising a camera base, multiple camera heads coupled to the camera base, each camera head comprising a camera lens defining an observation angle, each camera head being configured to pivot such that the observation angle may vary between a minimum observation angle and a maximum observation angle, and a protective shield attached to the camera base, extending over the camera heads and shaped such that for each camera head a distance between the shield and the camera head varies as a function of the observation angle. Attached to each camera head is a resiliently deformable and flared gasket positioned around the camera lens and extending toward the shield. The gasket is configured such that, for any observation angle between the minimum and maximum observation angles, the gasket contacts the shield about a closed light seal path for preventing light from passing between the shield and the gasket, and reaching the camera lens.

Abstract: Methods, systems, and techniques for object detection and tracking are provided. A system may include a module configured to generate a plurality of region proposals, each region proposal comprising a part of a video frame, a CNN pre-trained for object detection, the plurality of region proposals being input to the CNN; a tracker for tracking one or more targets based on outputs from the CNN across the series of video frames and generating tracking information on the one or more targets; and a module further configured to refine the plurality of region proposals to be input to the CNN, based on the tracking information.

Abstract: Methods, systems, and techniques for classifying an object-of-interest using an artificial neural network, such as a convolutional neural network. An artificial neural network receives a sample image including the object-of-interest overlaying a background and a sample background image excluding the object-of-interest and corresponding to the background overlaid by the object-of-interest. The object-of-interest is classified using the artificial neural network. The artificial neural network classifies the object-of-interest using the sample background and sample images. Prior to receiving the sample background and sample images the artificial neural network has been trained to classify the object-of-interest using training image pairs. Each of at least some of the training image pairs includes a first training image that includes a training object-of-interest overlaying a training background and a training background image excluding the training object-of-interest and corresponding to the training background.

Abstract: Methods, systems, and techniques for performing object detection using a convolutional neural network (CNN) involve obtaining an image and then processing the image using the CNN to generate a first feature pyramid and a second feature pyramid from the first pyramid. The second pyramid includes an enhanced feature map, which is generated by combining an upsampled feature map and a feature map of the first feature pyramid that has a corresponding or lower resolution of a resolution of the enhanced feature map. The upsampled feature map is generated by upsampling a feature map of the second feature pyramid that is at a shallower position in the CNN than the enhanced feature map. The enhanced feature map is split into channel feature maps of different resolutions, with each of the channel feature maps corresponding to channels of the enhanced feature map. Object detection is performed on the channel feature maps.

Abstract: Methods, systems, and techniques for redacted video exports are disclosed. Consistent with example embodiments, a bounding box may double as a redaction boundary.

Abstract: Methods, systems, infrastructures and techniques for operating a multi-process application are described. The method includes starting a master process and the master process instantiating a first child process and a first inter-process communication (IPC) channel; and instantiating a second child process and a second IPC channel. The method further includes the master process instantiating a third IPC channel used for a direct peer-to-peer (P2P) communication; and providing first and second handles of the third IPC channel to the first and second child processes, using the first and second IPC channels, respectively. The first child process and the second child process can communicate directly using the received first and second handles of the third IPC channel.

Abstract: A system for streaming multiple encodings of a source video stream is disclosed. A source video device system captures and/or receives source video comprising a plurality of source video frames. The source video device system encodes the source video frames into virtual frames, with each of the virtual frames being encoded using at least one different encoding parameter. To each virtual frame is appended virtual stream identifier which is appropriate for a selected transmission mechanism. The source video device system forms a container frame from the virtual frames and transmits the container frame over a network. Devices receiving transmissions over unreliable connections may reconstruct the transmitted streams using the synchronization headers.

Abstract: A physical security system is described comprising a simplified method for selection of a compute node from a cluster of compute nodes with which to assign a role or acquire a service. The method determines a scalar priority value for compute nodes in the cluster, and allows selection of a compute node by simply choosing the highest priority scalar value. Scalar priority values may be determined by one or more of: a compute node license type, capacity limits, a hardware capability, a software capability, and a current node load.

Abstract: An electronic movement-controlled apparatus that includes a camera and a movable arm is disclosed. The movable arm has both a stationary end and a movable end with the camera being attached to the movable end so as to be movable therewith. The stationary end is configured to be coupled to a rigid support structure. The movable arm includes a plurality of arm segments connected in series to form the movable arm. The arm segments are configured to have cooperating segment regions in terms of each of the arm segments being compressible and expandable in unison to move the movable end and effect a pan and tilt movement of the camera.

Abstract: Methods, systems, and techniques for performing a hash-based appearance search. A processor is used to obtain a hash vector that represents a search subject that is depicted in an image. The hash vector includes one or more hashes as a respective one or more components of the hash vector. The processor determines which one or more of the hashes satisfy a threshold criterion and which one or more of the components of the hash vector qualify as a scoring component. The one or more components that qualify correspond to a respective one or more hashes that satisfy the threshold criterion and that are represented in a scoring database that is generated based on different examples of a search target. The processor determines a score representing a similarity of the search subject to the different examples of the search target.

Abstract: Tile stream selection for mobile bandwidth optimization is disclosed. Also disclosed is a method that includes storing a plurality of video tiles combinable to form a larger portion or all of a high resolution video. The method also includes processing a request to stream at least a first video tile of the video tiles. The processing includes determining a size of a first portion of a region of interest falling within the first video tile; determining whether the size of the first portion is below a threshold size; and transmitting, over at least one network, a first video stream that includes the first video tile. The first video tile is transmitted in: a first resolution when the size of the first portion is below the threshold size; and a second resolution when the size of the first portion is above the threshold size.

Abstract: A method, system and computer program product for interactively identifying same individuals or objects present in video recordings is disclosed. When a thumbnail in a set of thumbnails is selected, new information is obtained. The new information may be that an individual or object is present in the portion of the video recording associated with the thumbnail. A search can be carried out for the individual or object based on the new information. The search generates new match likelihoods for each of displayed thumbnails within a user interface page. The displayed thumbnails are re-ordered based on the new match likelihoods.

Abstract: A camera device has a dome bubble member and an imaging unit housed within the camera chamber. A heat-emitting element, such as a film, may be arranged about the lens unit and is adapted to radiate heat for heating the dome bubble member. The camera device may include a sealing member adapted to sealingly engage a portion of the dome bubble member, whereby the heat radiated from the heat-emitting element is substantially contained within the sealed sub-chamber. The imaging unit may be rotatable about a first axis and a second axis in which the second axis is offset from the center of the dome bubble member and is displaceable in at least one direction transverse to itself. The camera device may have a shroud member that is pivotal about a third axis. The camera device may also have a shroud member that is transmissive to infra-red light.

Abstract: Methods, systems, and techniques for tracking and pictorially displaying locations of tracked individuals involve retrieving a location of the tracked individual and pictorially representing the location of the tracked individual on a display. The location can be acquired using a credentials acquisition device to read credentials issued to the tracked individuals. Pictorially representing the location on a display may involve showing one or both of the location and number of the tracked individuals on a map.