Abstract: Security systems and methods for a building upon occurrence of a possible event impacting safety of occupants of the building, such as a possible active shooter event.

Abstract: Disclosed herein are systems and methods for detecting an event associated with a swimmer and generating a detection signal associated with the event.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selecting a video quality. One of the methods includes: determining, for a repeating time range of a video with a first video quality, a frequency with which one or more portions of the video were accessed, each portion for a corresponding one of one or more past instances of the repeating time range; selecting, for the repeating time range and using the frequency with which the portion of the video for the repeating time range was accessed, a second video quality from two or more video qualities that includes the first video quality; and storing, in memory, one or more additional portions of the video i) captured by a camera during future instances of the repeating time range ii) at the second video quality.

Abstract: A system for identifying one or more product engagements includes one or more microsensors configured to measure one or more signals indicative of one or more near-product engagements within a retail environment. Near-product engagements product movement, customer proximity to products, temperature, and the like. In some embodiments, the system may be configured to generate spatial relationship data associated with one or more spatial relationships between one or more transmitting electronic devices and one or more sensor units. The system may perform one or more filtering steps on the near-product engagement or spatial relationship data and providing the filtered data to a user interface.

Abstract: A video recording and communication device includes a camera, a processor, a radar sensor, and memory. The processor executes instructions from memory to cause the device to operate the sensor in a first operational mode in which the camera is maintained in a low-power mode. The processor further detects, using the sensor in the first mode, possible motion of an object within a threshold distance from the sensor. Responsive to the detecting, the processor transitions the sensor from the first mode to a second operational mode. The second mode consumes more power than the first mode. The processor determines, using the radar sensor in the second mode, that the possible motion of the object occurred in a region of interest, in response to which, it transitions the sensor from the second mode to a third operational mode. The third mode consumes more power mode than the second mode.

Abstract: A monitoring system includes a doorbell unit that includes a camera and a display and that is configured to receive a request to access the property. The monitoring system includes a monitor control unit that is configured to determine an authentication protocol for determining whether to grant the visitor access to the property. The monitor control unit generates a first image and transmits authentication data to a computing device. The monitor control unit provides the first image and instructions to output the first image on the display of the doorbell unit. The monitor control unit receives a second image captured by the camera of the doorbell unit. The monitor control unit determines whether the second image includes a representation of data that is based on processing the first image in combination with the authentication data. The monitor control unit grants or denies the visitor access to the property.

Abstract: An information processing apparatus (10) includes a time and space information acquisition unit (110) that acquires high-risk time and space information indicating a spatial region with an increased possibility of an accident occurring or of a crime being committed and a corresponding time slot, a possible surveillance target acquisition unit (120) that identifies a video to be analyzed from among a plurality of videos generated by capturing an image of each of a plurality of places, on the basis of the high-risk time and space information, and analyzes the identified video to acquire information of a possible surveillance target, and a target time and space identification unit (130) that identifies at least one of a spatial region where surveillance is to be conducted which is at least a portion of the spatial region or a time slot when surveillance is to be conducted, from among the spatial region and the time slot indicated by the high-risk time and space information, on the basis of the information of the

Abstract: A vehicle exterior environment detection apparatus includes a distance image generator, a vehicle detector, a search processor, a vehicle width calculator, and a predictor. The distance image generator generates a plurality of distance images including a first distance image, a second distance image, and a third distance image, on a basis of a plurality of stereo images including a first stereo image, a second stereo image, and a third stereo image each including a left image and a right image. The predictor predicts a position of a target vehicle in the left image and the right image included in the third stereo image, on a basis of a first vehicle image width calculated on a basis of the first distance image and a second vehicle image width calculated on a basis of a selected image of the second stereo image.

Abstract: A method of provisioning a headless device includes the steps of acquiring credentials for a user application, then placing the headless device in a provisioning mode. Once in the provisioning mode, characters associated with the credentials are displayed by the user application, then the characters are read by an optical character reader (OCR) of the headless device, thereby allowing the headless device to join a network associated with the credentials.

Abstract: An artificial intelligence (AI) entry management (EM) security system includes a camera, a microphone, a motion detector, a speaker, and a software platform. Geofences are utilized to create boundaries around physical areas, such as locations for package delivery or property boundaries. The EM device and other devices connected to the software platform are configured to monitor the geofences and detect a presence of an activity, an event, an object, or a device. At least one license plate reader is utilized to read license plate characters. Voice recognition and voice identification are used to grant or deny permissions for individuals on a property.

Abstract: The disclosure discloses a method and device for coding an image and a method and device for decoding an image. The coding includes that: a coding block is partitioned into L micro-blocks, wherein L is a preset number of micro-block partitions in the decoding block; Displacement Vectors (DVs) between the micro-blocks and reference micro-blocks in a preset reconstructed pixel sample set are determined, wherein the DVs are vectors between pixel positions of the reference micro-blocks and pixel positions of the micro-blocks in a preset pixel coordinate system: and the DVs are coded and written into a bitstream. By the methods and the devices, the problem of low image compression and decompression efficiency during image coding and decoding in the related technology is solved, and tire effect of improving image coding and decoding efficiency is further achieved.

Abstract: A rendering processor assigns varying logical pixel dimensions to regions of an image frame and rendering pixels of the image frame based on the logical pixel dimensions. The rendering processor renders in highest resolution (i.e., with smaller logical pixel dimensions) those areas of the image that are more important (on which the viewer is expected to focus (the “foveal region”), or regions with little-to-no motion), and renders in lower resolution (i.e., with larger logical pixel dimensions) those areas of the image outside the region of interest, or regions that are speedily moving, so that loss of detail in those regions will be less noticeable to the viewer. For regions with less detail or greater magnitude of motion, larger logical pixel dimensions reduce the computational workload without affecting the quality of the displayed graphics as perceived by a user.

Abstract: The disclosed techniques include systems and methods for implementing security cameras with thermal imaging sensors. The disclosed techniques can utilize a thermal imaging sensor (TIS) and a less robust passive infrared (PIR) sensor of a security camera system to monitor a field of view.

Abstract: A system which, with data provided by one or more sensors, detects a user's alteration of the geometries of parts of his face, head, neck, and/or shoulders. It determines the extent of each alteration and normalizes it with respect to the maximum possible range of each alteration so as to assign to each part-specific alteration a numeric score indicative of its extent. The normalized part-specific scores are combined so as to produce a composite numeric code representative of the complete set of simultaneously-executed geometric alterations. Each composite code is translated, or interpreted, relative to an appropriate context defined by an embodiment, an application executing on an embodiment, or by the user. For example, each composite code might be interpreted as, or assigned to, a specific alphanumeric letter, a color, a musical note, etc.

Abstract: This disclosure relates to method of identifying a gesture from a plurality of gestures using a reservoir based convolutional spiking neural network. A two-dimensional spike streams is received from neuromorphic event camera as an input. The two-dimensional spike streams associated with at least one gestures from a plurality of gestures is preprocessed to obtain plurality of spike frames. The plurality of spike frames is processed by a multi layered convolutional spiking neural network to learn plurality of spatial features from the at least one gesture. A filter block is deactivated from the plurality of filter blocks corresponds to at least one gesture which are not currently being learnt. A spatio-temporal features is obtained by allowing the spike activations from CSNN layer to flow through the reservoir. The spatial feature is classified by classifier from the CSNN layer and the spatio-temporal features from the reservoir to obtain set of prioritized gestures.

Abstract: A method of classifying motion from video frames involves generating motion frames indicative of changes in pixel values between pairs of frames. The method also involves determining one-dimensional feature values based on the video frames or motion frames, such as the statistical values or linear transformation coefficients. Each one-dimensional feature value may be stored in a buffer, from which additional temporal feature values can be extracted indicative of the change of the one-dimensional feature values across a set of frames. A classifier may receive the one-dimensional feature values and the additional temporal feature values as inputs, and determine the class of motion present in the video frames. Some classes of motion, such as irrelevant motion, may be considered irrelevant to the execution of certain motion-triggered actions, such that the method may involve suppressing the performance of a motion-triggered action based on the determined class of motion.

Abstract: The various embodiments described herein include methods, devices, and systems for categorizing motion events. In one aspect, a method is performed at a camera device. The method includes: (1) capturing a plurality of video frames via the image sensor, the plurality of video frames corresponding to a scene in a field of view of the camera; (2) sending the video frames to the remote server system in real-time; (3) while sending the video frames to the remote server system in real-time: (a) determining that motion has occurred within the scene; (b) in response to determining that motion has occurred within the scene, characterizing the motion as a motion event; and (c) generating motion event metadata for the motion event; and (4) sending the generated motion event metadata to the remote server system concurrently with the video frames.

Abstract: Processing a digital image in a distributed computing environment comprising a communications network interconnecting two or more computing nodes. A segmentation of the digital image into two or more image segments is determined. For each of the image segments, a number of non-background pixels comprised by the image segment is determined. An assignment of each of the image segments to one of the computing nodes is determined. The determination of the assignment may include balancing, based on the number of non-background pixels determined for each of the image segments, the workload of the assigned computing nodes responsive to processing the image segments. Each of the assigned computing nodes may be caused to process the image segments assigned to the computing node.

Abstract: Remote neural network retraining for surveillance systems is disclosed. In some cases, systems and methods enable remote training and retraining of neural networks, while processing data in real life using the trained and retrained neural networks locally at the surveillance system. The surveillance system can determine a change of location and can retrain the neural network and/or initiate the retraining of the neural network remotely, such as on a cloud server, to retrain the neural network based on new image and/or video data taken from the new location. The remote server can transmit the retrained neural network and/or weights for nodes of the retrained neural network back to the surveillance system. The surveillance system can then update its neural network and process future image and/or video data based on the retrained neural network and/or weights.

Abstract: A method for monitoring a robot includes monitoring a safety condition and operating the robot in a limitation operating mode for as long as the monitored safety condition is not fulfilled. A deceleration of the robot is commanded and monitored in the limitation operating mode for as long as the robot exceeds a velocity limit.

Abstract: Systems and methods for providing time-delimited action suggestions are provided. In one example embodiment, a method includes receiving, by one or more computing devices from a user device, data indicative of a user-requested time-bound activity. The time-bound activity is associated with a time period. The method includes identifying, by the one or more computing devices, one or more parameters associated with a user that requested the time-bound activity. The method includes determining, by the one or more computing devices, a suggested action based at least in part on the one or more parameters associated with the user and the time period associated with the time-bound activity. The method includes providing, by the one or more computing devices, an output indicative of the suggested action to the user device.

Abstract: A method performed by an electronic device is described. The method includes receiving first optical data and first depth data corresponding to a first frame. The method also includes registering the first depth data to a first canonical model. The method further includes fitting a three-dimensional (3D) morphable model to the first optical data. The method additionally includes registering the 3D morphable model to a second canonical model. The method also includes producing a 3D object reconstruction based on the registered first depth data and the registered 3D morphable model.

Abstract: An information handling system may include a host system comprising a processor and a management controller communicatively coupled to the processor, the management controller comprising firmware having a security module configured to enforce access control in accordance with a security policy.

Abstract: Disclosed herein are system, method, and computer program product embodiments for tracking shop information using blockchain. In an embodiment, a shop application system may gather information related to a shop using various sensors within the shop. For example, the shop application system may identify a flow rate of traffic within the shop or outside of the shop. The shop application system may securely transmit this information to a blockchain cloud platform to be stored onto a blockchain. The blockchain may also maintain store information from a client application system related to shop ownership or tenancy. In this manner, the blockchain may provide a public means for accessing transactions related to a shop as well as provide confidence in the information provided.

Abstract: Technologies and implementations for facilitating visual analysis of transactions utilizing analytics are generally disclosed.

Abstract: The present disclosure relates to systems and methods of multi-camera. The method may include determining a level of a camera in a multi-camera system based on the status of an object, and determining a mode of the camera based on the level. The mode may relate to one of a bit rate, an I frame interval, or a coding algorithm. The method may further include generating a monitor file relating to the object based on the level of the camera in the multi-camera system.

Abstract: An image processing system, which generates a virtual viewpoint image on the basis of captured images from a plurality of image capturing apparatuses for capturing an object from a plurality of directions, detects an error in at least one of the plurality of image capturing apparatuses, and generates the virtual viewpoint image using a captured image from an image capturing apparatus, among the plurality of image capturing apparatuses, in which an error has not been detected, as an image of a capturing field of the image capturing apparatus in which the error has been detected.

Abstract: An image processing apparatus configured to extract an object region corresponding to a predetermined object from an extraction target image based on image capturing performed by an image capturing apparatus includes an acquisition unit configured to acquire information about an image to be displayed on a display surface located in an image capturing range of the image capturing apparatus, an identification unit configured to identify, as a region from which extraction of the object region is not to be performed, a region corresponding to the display surface in the extraction target image, based on the information acquired by the acquisition unit, and an extraction unit configured to extract the object region formed by part of a plurality of pixels not included in the region identified by the identification unit among a pixel included in the extraction target image.

Abstract: A video surveillance system includes: a detection unit that detects a predetermined event on the basis of an image captured by a first imaging apparatus; and a control unit that controls a second imaging apparatus such that the second imaging apparatus captures an image of a predetermined position after the detection of the predetermined event.

Abstract: An information processing apparatus (10) includes a time and space information acquisition unit (110) that acquires high-risk time and space information indicating a spatial region with an increased possibility of an accident occurring or of a crime being committed and a corresponding time slot, a possible surveillance target acquisition unit (120) that identifies a video to be analyzed from among a plurality of videos generated by capturing an image of each of a plurality of places, on the basis of the high-risk time and space information, and analyzes the identified video to acquire information of a possible surveillance target, and a target time and space identification unit (130) that identifies at least one of a spatial region where surveillance is to be conducted which is at least a portion of the spatial region or a time slot when surveillance is to be conducted, from among the spatial region and the time slot indicated by the high-risk time and space information, on the basis of the information of the

Abstract: A method, system, and apparatus are provided for capturing a video image and speed of a target vehicle. A ranging device detects a distance to a target vehicle. The focal distance or zoom of a video camera is set and adjusted based on the distance. The speed of travel of the vehicle is detected, displayed, and/or stored in association with a video image captured of the vehicle by the video camera. A range of distances within which to capture the video image and speed of the vehicle may be set by detecting distances between a pair of landmarks or using GPS and compass heading data. An inclinometer is provided to aid initiation of a power-conservation mode. A target tracking time may be determined and compared to a minimum tracking time period. A device certification period can be stored and displayed and the device deactivated upon expiration thereof.

Abstract: Systems and methods for managing alert notifications from a secured area are provided. Such systems and methods can include a surveillance device monitoring the secured area and transmitting data captured from the secured area to an artificial intelligence module, the artificial intelligence module using the data to identify a scenario associated with the secured area and a notification priority of the scenario, and when the notification priority is at or above a preconfigured level, the artificial intelligence module transmitting an alert notification to a cloud server indicative of the scenario.

Abstract: Presented here is technology to efficiently process camera images to generate lead part artistic images and videos using an artificial intelligence module receiving inputs from multiple sensors. Multiple sensors can include a depth sensor, a conventional camera, and a motion tracker providing inputs to the artificial intelligence module. Based on the inputs, the artificial intelligence module can segment the received image and/or video into a foreground image and a background image to produce portrait imagery by blurring the background image and/or video. The artificial intelligence module can select the most aesthetically pleasing image from a video. In addition, the artificial intelligence module can adjust lighting in an image or video to create artistic lighting effects. All the processing can be done in real time due to efficient combination of artificial intelligence modules, traditional image processing techniques, and use of specialized hardware.

Abstract: The theft prevention monitoring device, system and method are provided. The theft prevention monitoring device includes: a housing, a moving mechanism, a controller, and a video control module, the controller includes a moving control module, an image recognition module, and a sound and light control module; the moving control module is adapted to control a moving mechanism to move along a running route; the video control module is adapted to use a camera to scan environment information, real-time build dynamic map of environment, and generate the running route; the image recognition module is adapted to match captured videos or images of people with pre-stored videos or images of people to obtain matching result, provide corresponding control instructions; a sound and light alarm of the sound and light control module is adapted to give an alarm by sending out sound and light according to the corresponding control instructions.

Abstract: A power management system for a lighting circuit may include a grid shifting controller that includes a processor and a connection to an external power source. The power management system may also include a communication interface associated with the grid shifting controller. The grid shifting controller may be configured to provide control information to a processor of at least one grid shifting electrical fixture over the communication interface, the control information being configured to direct the at least one grid shifting electrical fixture on the use of power from the external power source and an energy storage device associated with the at least one grid shifting electrical fixture.

Abstract: A hybrid relay for high density venues may be provided. First, a user density value at an Access Point (AP) disposed above a ground level may be determined. Then a user density value at an AP-relay disposed at the ground level may be determined. Next, it may be determined that a difference between the user density value at the AP and the user density value at the AP-relay is greater than a predetermined threshold. The AP-relay may then be switched from a sensor mode to an AP-relay mode in response to determining that the difference between the user density value at the AP and the user density value at the AP-relay is greater than the predetermined threshold.

Abstract: In various embodiments, the system provides input to and facilitates various operations of media production. An automated script content generator uses recurrent artificial neural networks trained using machine learning on a corpus of stories or scripts to generate and suggest script content and indicates effects changes to the script would have of the scenes, characters, interactions and other entities of the script. An automated producer breaks down the script to automatically generate storyboards, calendars, schedules and budgets and provides this as input to the pre-production operation within a media production environment. The system also provides information to affect and facilitate the greenlighting operation and other operations in the media production environment in an iterative script review and revision process.

Abstract: Embodiments of a method and system described herein enable capture of video data streams from multiple, different devices and the processing of the video data streams. The video data streams are merged such that various data protocols can all be processed with the same worker processors on different types of operating systems, which are typically distributed. An embodiment uses a mobile device (such as a mobile phone) as a device and deploys a video sensor application on the mobile device for encoding consecutive video files, time stamping the consecutive video files, and pushing the consecutive video files to a file server to produce a stable stream of video data. Thus avoiding the inefficiencies associated with having video processing in the data flow loop.

Abstract: The partitioning method for a working space of a robot includes defining the working space of the robot; setting a plurality of partitioning planes based on at least three non-collinear points in the working space; if the setting of the plurality of partitioning planes is completed, defining partitioning lines by intersecting the plurality of partitioning planes; dividing the plurality of partitioning planes into a plurality of designated sections and a plurality of extended sections based on the partitioning lines; combining the plurality of designated sections for constructing a full partitioning plane; partitioning the working space into two working regions based on the full partitioning plane; and setting the working region containing an origin of the robot as an operation region. Therefore, the partitioning process can be simplified.

Abstract: An audio-video communication system comprises a wireless exterior module located proximate an entrance, a computerized controller running a software application, and a remote peripheral device. The wireless exterior module includes a proximity sensor for detecting a person at the entrance, a video camera for recording an image of the person at the entrance, a microphone for recording the person at the entrance, a speaker for playing audio to the person at the entrance, a transmitter for communicating sounds and images of the person at the entrance, and a receiver for receiving communications at the wireless exterior module. The computerized controller is disposed in wireless electronic communication with the wireless exterior module via the transmitter and the receiver of the wireless exterior module. The remote peripheral device is configured to electronically communicate with the computerized controller for viewing an image from the video camera communicated from the wireless exterior module.

Abstract: A threshold detection system may include multiple wireless devices, wherein each individual wireless device may include a transmitter to transmit a wireless signal. The threshold detection system may also include a receiver array of multiple receivers to detect the wireless signal of each individual wireless device in response to the individual wireless device being in range of the receiver array. The threshold detection system may also include a controller to receive detection signals from the receivers and determine a direction of travel of an individual wireless device relative to a predetermined threshold based on the received detection signals. The controller may also determine that the individual wireless device has crossed the predetermined threshold and trigger an audio or visual alert in response to the determination that the wireless device has crossed the predetermined threshold and is traveling in an exit direction based on the determined direction of travel.

Abstract: Systems and methods are described for dynamically adjusting an amount of retrieved recognition data based on the needs of a show, experience, or other event where participants are recognized. The retrieved recognition data may be deleted once it is no longer needed for the event. Recognition data retrieval is limited to just what is needed for the particular task, minimizing the uniqueness of any retrieved recognition data to respect participant privacy while providing an enhanced participant experience through recognition.

Abstract: The present disclosure relates to training and utilizing an image exposure transformation network to generate a long-exposure image from a single short-exposure image (e.g., still image). In various embodiments, the image exposure transformation network is trained using adversarial learning, long-exposure ground truth images, and a multi-term loss function. In some embodiments, the image exposure transformation network includes an optical flow prediction network and/or an appearance guided attention network. Trained embodiments of the image exposure transformation network generate realistic long-exposure images from single short-exposure images without additional information.

Abstract: A security device registered to a client device used by a user generates an event message and event video. A network-connected device or the client device determines, based on one or more of characteristics of the event message, event video, location of the client device, connection information of the client device, connection information of the security device, an area boundary, and a connection threshold whether to automatically populate the event video on the client device in full-screen or partial-screen view. Based on this determination, device command is generated controlling display of the event video on the client device.

Abstract: Dynamic methods and systems for monitoring an environment. The methods and systems adopt functional nodes with at least one context node and one or more application nodes. The application nodes include at least one of a processing application node, a notifying application node, and/or an action application node. Input data of the environment are analyzed and detected. Representative data are extracted and compared with a group of comparative data by calculating a deviation between the representative data and the most similar comparative data. The notifying application node may send an alarm as a function of the deviation detected as above. An environment monitoring network is formed as a function of the functional nodes. The environment monitoring network is topologically variable as a function of i) the environment to be monitored, ii) the functions of the functional nodes and iii) the deviation detected. Monitoring occurs as a function of the topology of the implemented environment monitoring network.

Abstract: A system which, with data provided by one or more sensors, detects a user's alteration of the geometries of parts of his face, head, neck, and/or shoulders. It determines the extent of each alteration and normalizes it with respect to the maximum possible range of each alteration so as to assign to each part-specific alteration a numeric score indicative of its extent. The normalized part-specific scores are combined so as to produce a composite numeric code representative of the complete set of simultaneously-executed geometric alterations. Each composite code is translated, or interpreted, relative to an appropriate context defined by an embodiment an application executing on an embodiment, or by the user. For example, each composite code might be interpreted as, or assigned to, a specific alphanumeric letter, a color, a musical note, etc.

Abstract: A medical observation apparatus includes: a display unit that displays thereon an observation image corresponding to a result of examination on a subject; a first camera that performs imaging of plural persons surrounding the subject, and outputs a surrounding image; a selecting unit that selects, based on the surrounding image, an indicator from the plural persons; a line of sight detecting unit that detects a line of sight of the indicator; and a display control unit that causes the display unit to display thereon a superimposed image having a pointer superimposed on the observation image, the pointer being at a position according to a destination of the line of sight of the indicator.

Abstract: A computer vision processing device is provided which comprises memory configured to store data and a processor. The processor is configured to store captured image data in a first buffer and acquire access to the captured image data in the first buffer when the captured image data is available for processing. The processor is also configured to execute a first group of operations in a processing pipeline, each of which processes the captured image data accessed from the first buffer and return the first buffer for storing next captured image data when a last operation of the first group of operations executes.

Abstract: Systems and methods for relating configuration data to IP cameras are provided. Some methods can include a video streaming server device receiving a message identifying an IP address of an IP camera from a DHCP server device, the video streaming server device using the IP address to connect to the camera, the video streaming server device receiving a video data stream from the camera, the video streaming server device extracting a MAC address of the camera from a connection with the IP camera, the video streaming server device transmitting the video data stream, the IP address, and the MAC address to a mobile device, a manager server device receiving configuration information for the IP camera, the IP address, and the MAC address from the mobile device, and the manager server device relating and binding the configuration information with the IP address and the MAC address.

Abstract: Disclosed is a method and system for synchronously reproducing multi-media multi-information. The method is a method of combining a plurality of relevant files or a plurality of information streams that have an associated information relationship using a “multi-information modulation unit”, and then synchronously reproducing the relevant files or the information streams using a dedicated player capable of synchronously reproducing and playing back the multi-information.