Abstract: Described is a multiple-camera system and process for detecting, tracking, and re-verifying agents within a materials handling facility. In one implementation, a plurality of feature vectors may be generated for an agent and maintained as an agent model representative of the agent. When the object being tracked as the agent is to be re-verified, feature vectors representative of the object are generated and stored as a probe agent model. Feature vectors of the probe agent model are compared with corresponding feature vectors of candidate agent models for agents located in the materials handling facility. Based on the similarity scores, the agent may be re-verified, it may be determined that identifiers used for objects tracked as representative of the agents have been flipped, and/or to determine that tracking of the object representing the agent has been dropped.

Abstract: An apparatus is provided. The apparatus receives a video feed and processes the video feed in real-time as the video feed is received. The apparatus performs object detection and recognition on the video feed to detect and classify objects therein, performs activity recognition to detect and classify activities of at least some of the objects, and outputs classified objects and classified activities in the video feed. The apparatus generates natural language text that describes the video feed, produces a semantic network, and stores the video feed, classified objects and classified activities, natural language text, and semantic network in a knowledge base. The apparatus generates a graphical user interface (GUI) configured to enable queries of the knowledge base, and presentation of selections of the video feed, classified objects and classified activities, natural language text, and semantic network.

Abstract: To efficiency search for an object associated with a sensed event, an information processing apparatus includes a sensor that analyzes a captured video and senses whether a predetermined event has occurred, a determining unit that determines a type of an object to be used as query information based on a type of the event in response to sensing of the event occurrence, and a generator that detects the object of the determined type from the video and generates the query information based on the detected object.

Abstract: It is discloses a device and method for controlling a material flow (18) in a storage and picking system (10) at a sensor-controlled node (12) of the material flow (18), where a decision on a future direction of material flow or on a velocity of the material flow (18) is to be taken, wherein at least an inlet section (28) of the node (12) is detected by a, preferably single, sensor (22), comprising the steps of: by means of the sensor (22) generating (S10) sensor data (46) representing the material flow (18) which is defined by one or more material-flow objects (36), approaching the node (12) in a downstream direction, in a field of vision (26) of the sensor (22), in particular in an inlet section (28) of the node (12); checking (S16) whether the sensor data (46) includes for each of the approaching objects (36-1, 36-2) at least one associated object feature (40) allowing certain identification of the corresponding object (36); and, if the sensor data (46) includes for each of the objects (36-1, 36-2) the at

Abstract: A method, apparatus, electronic device, and a system for selecting a to-be-masked region in a video are disclosed. The method includes: obtaining a video to be detected; determining specified target sets in the video through a preset target detection algorithm, wherein each specified target set is a set of pixels of one specified target in video frames of the video; determining whether a specified target corresponding to each specified target set is a sensitive target respectively through a preset recognition algorithm; and using a specified target set as to-be-masked regions in the video when a specified target corresponding to this specified target set is determined as a sensitive target. In this method, specified targets are first determined, and then it is determined whether the specified targets are sensitive targets.

Abstract: An information processing apparatus includes an acquisition unit configured to acquire first mapping information in which an amount of inclination of a joystick, used for controlling the image capturing direction, and a change speed in the image capturing direction of an image capturing apparatus are associated, and a change speed in an image capturing direction of an image capturing apparatus are associated, a determination unit configured to determine the change speed in the image capturing direction based on the amount of inclination of the joystick by a user operation and the first mapping information, and a generation unit configured to generate second mapping information in which the amount of inclination of the joystick and the change speed in the image capturing direction are associated, based on the change speed in the image capturing direction determined by the determination unit during a predetermined period.

Abstract: Devices, systems, and method are provided for tracking items in a store for processing a cashier-less purchase transaction. In one example, a method includes tracking a shopper in a store using one or more sensors to process an account of shopping activity performed by the shopper. The method further includes monitoring the shopper in the store using said one or more sensors. Output of the one or more sensors is processed by a processing entity associated with the store to produce input feature data for aspects of a current scenario involving actions of the shopper and one or more items in the store. The processing entity associated with the store processes the input feature data to characterize aspects of the current scenario. The processing entity characterizes aspects of the current scenario in part by accessing a trained machine learning model that is maintained for a profile of the shopper. The input feature data is for actions of the shopper in relation to the scenario.

Abstract: According to an aspect, a method includes capturing image data from a video camera at a conveyance system. Analytics of the image data can be initiated to determine a plurality of conditions of the conveyance system. A status of the conditions can be summarized as a metadata output. The metadata output can be transmitted to a support system operable to initiate a corrective action responsive to the status of the conditions.

Abstract: A biological-information detection device includes a video input section accepting video signals including three wavelength components in an infrared region of reflected light from an object, a wavelength detecting section acquiring a wavelength and an intensity of the reflected light from the video signals, a face feature amount detecting section detecting a plurality of feature points of a face based on the video signals, a measurement target area identifying section identifying a measurement target area on a basis of the plurality of feature points of the face detected, a wavelength fluctuation detecting section detecting a difference between a wavelength of reflected light from the measurement target area at a certain point in time and a wavelength of reflected light at a point in time preceding the certain point in time, and a pulse wave detecting section detecting a change in the detected difference according to the point in time.

Abstract: Embodiments of the present disclosure include automated guided vehicles (AGVs) having a steerable camera for target-tracking. In one embodiment, the AGV includes a body having one or more motorized wheels, the body having a first end and a second end opposing the first end, a console coupled in an upright position to the first end of the body, and a first camera coupled to the console, the first camera providing one or more axes of rotation and is operable to follow an object.

Abstract: This document describes techniques and systems that enable a smartphone-based radar system for determining user intention in a lower-power mode. The techniques and systems use a radar field to enable the smartphone to accurately determine the presence or absence of a user and further determine the intention of the user to interact with the smartphone. Using these techniques, the smartphone can account for the user's nonverbal communication cues to determine and maintain an awareness of users in its environment, and only respond to direct interactions once a user has demonstrated an intention to interact, which preserves battery power. The smartphone may determine the user's intention by recognizing various cues from the user, such as a change in position relative to the smartphone, a change in posture, or by an explicit action, such as a gesture.

Abstract: A surveillance apparatus for indicating the detection of motion is provided that can perform a surveillance method. A motion detection unit is configured to detect motion of an object in the field of view of a camera. A processor is configured to identify a region of video data captured by the camera that includes the motion of the object. A determination unit is configured to determine perimeter data that represents at least a portion of a perimeter of the region of the video data. A combining unit is configured to combine the perimeter data with a video feed captured by a different camera.

Abstract: Encoding an image block using a quantization parameter includes presenting, to an encoder that includes a machine-learning model, the image block and a value derived from the quantization parameter, where the value is a result of a non-linear function using the quantization parameter as input, where the non-linear function relates to a second function used to calculate, using the quantization parameter, a Lagrange multiplier that is used in a rate-distortion calculation, and where the machine-learning model is trained to output mode decision parameters for encoding the image block; obtaining the mode decision parameters from the encoder; and encoding, in a compressed bitstream, the image block using the mode decision parameters.

Abstract: Systems, methods, and computer-readable for multi-temporal scale analysis include obtaining two or more timescales associated with one or more images. A context associated with a monitoring objective is obtained, based on real time analytics or domain specific knowledge. The monitoring objective can include object detection, event detection, pattern recognition, or other. At least a subset of timescales for performing a differential analysis on the one or more images is determined based on the context. Multi timescale surprise detection and clustering are performed using the subset of timescales to determine whether any alerts are to be generated based on entropy based surprises. A set of rules can be created for the monitoring objective based on the differential analytics and alerts or entropy based surprises, if any.

Abstract: Current indoor tracking methods are inadequate to accurately and reliably point a pointer or camera at an object or a person doing an activity. An apparatus and method are provided for cooperative tracking that is operable both indoors and outdoors. The system works using ranging technology without the need for placing radiation sources and/or sensors in set locations around the location where tracking takes place. The apparatus and method may be used for automatic filming, allowing free movement of both the subject of the filming and that of the camera with a compact design, and providing easy setup at any location.

Abstract: A method for monitoring a plant health state relates to the technical field of intelligent agriculture. The method is used for intelligently determining the plant health state and timely prompting farmland managers to perform control for at least one plant in a poor plant health state. The method for monitoring the plant health state includes: performing first determination according to plant health state information; when a determination result is that there is a risk of poor plant health, performing second determination according to second plant health state information in an orientation where at least one plant at risk of poor plant health is located, so as to accurately obtain plant health state information, such that farmland managers can learn the current situation of the plant in a field timely and perform control timely. An apparatus applying the method for monitoring the plant health state is provided. The apparatus is used for monitoring the plant health state.

Abstract: A remote surveillance assembly includes a base that is positionable in a vehicle and a pole that is coupled to and extends upwardly from the base. A pan tilt zoom (PTZ) video camera is movably disposed on the pole to capture surveillance of the environment around the vehicle. A pair of articulated arms is each of the articulated arms is movably coupled to the pole. A pair of digital cameras is each coupled to a respective one of the articulated arms to capture surveillance of the environment around the vehicle. A digital video recorder is coupled to the base and a transceiver is coupled to the base. The transceiver is in wireless communication with an extrinsic communication network to broadcast the data stored in the digital video recorder to a remote data storage device.

Abstract: Systems, methods, and software are disclosed herein for associating images with content items. In an implementation, a computing device determines that an image captured of a scene includes a display of meeting content. The device identifies a content item comprising a source of the meeting content in the scene and may then create an association between an instance of the image and an instance of the content item. The device may, for example, create a link to the content item that can be embedded in or otherwise associated with the image file. The reverse may also be accomplished, whereby a link to the image may be created and embedded in or otherwise associated with the content item.

Abstract: An artificial intelligence entry management device for an entry and delivery system includes a camera, a microphone, a motion detector, a speaker, and a housing. The housing has an oval shape with a substantially open middle. The substantially open middle has a housing protrusion portion configured to house the camera, the microphone, the motion detector, and the speaker. The entry and delivery system may also include one or more robots that interface with the entry management device to monitor an area around an access point and to alert the user of activity. A robot may be an aerial robot that has a camera, a robot light, a speaker, a microphone and an actuator to enable picking and moving a package. Aerial robots may be configured around a perimeter of a building to monitor the building and may turn on a robot light when motion is detected.

Abstract: System and method for improving the shaving experience by providing improved visibility of the skin shaving area. A digital camera is integrated with the electric shaver for close image capturing of shaving area, and displaying it on a display unit. The display unit can be integral part of the electric shaver casing, or housed in a separated device which receives the image via a communication channel. The communication channel can be wireless (using radio, audio or light) or wired, such as dedicated cabling or using powerline communication. A light source is used to better illuminate the shaving area. Video compression and digital image processing techniques are used for providing for improved shaving results. The wired communication medium can simultaneously be used also for carrying power from the electric shaver assembly to the display unit, or from the display unit to the electric shaver.

Abstract: A method includes obtaining time series data for a usage or performance metric for computing resources in a service provider network comprising a plurality of observations recorded in a plurality of respective time steps. A prediction error is determined for a previous prediction of an observation in the time series data. The prediction error is used to update a standard deviation of a set of predication errors for the usage or performance metric. The standard deviation and the prediction error are then used to update a confidence coefficient. A prediction limit for the usage or performance metric is then determined based on an expected value, the confidence coefficient, and the standard deviation. One or more events may be generated based on the prediction limit, which may be used to trigger a reconfiguration or auto-scaling of the computing resources.

Abstract: A method for determining objects of interest using a vehicular vision system includes providing at least one camera and providing a control having an image processor that processes image data captured by the camera. An object present in the field of view of the camera is detected via processing at the control of a first frame of captured image data. Hypotheses filtering and hypotheses merging may be utilized when processing additional frames of captured image data to discern the detected object being an object of interest from the detected object being not an object of interest. Hypotheses filtering includes tracking the detected object over multiple additional frames of captured image data, and hypotheses merging includes comparing outputs of hypotheses filtering for the multiple additional frames of captured image data. The detected object may be determined to be an object of interest responsive to results of hypotheses merging.

Abstract: System, method, and media for providing automatic recording of an event. The event may be detected from a set of data collected at a sensor. A recording device manager may send signals to other sensors and electromechanical devices to activate these sensors and electromechanical devices based on detection of the triggering event. The sensor may collect data associated with the triggering event and the electromechanical devices may perform actions based on the triggering event.

Abstract: An electronic device is provided.

Abstract: Embodiments of methods and apparatuses for object detection and of computer devices are disclosed.

Abstract: Embodiments of the present disclosure provide an object tracking method and an apparatus. The method includes: obtaining multiple frames of first images shot by a first camera apparatus and a first shooting moment of each frame of the first images, where the first images include a first object; obtaining multiple frames of second images shot by a second camera apparatus and a second shooting moment of each frame of the second images, where the second images include a second object; obtaining a distance between the first camera apparatus and the second camera apparatus; and judging whether the first object and the second object are the same object according to the multiple frames of the first images, the first shooting moment of each frame of the first images, the multiple frames of the second images, the second shooting moment of each frame of the second images and the distance.

Abstract: In an embodiment, the present invention is a device locationing system operable to dynamically determine the presence of keep-out zones within a venue, and thereafter adjust positional data obtained through the device based on the presence of the previously detected keep-out zones.

Abstract: The present invention relates to a device for use in the farming sector. More specifically, the invention relates to remotely obtaining farm climate and biometric variables. It is an object of the present invention to provide a method for automatic integration of farm climate and/or biometric variables which comprises: obtaining data on a set of farm climate and/or biometric variables from a controller, equalizing the collected data on a set of farm climate and/or biometric variables to pre-defined units, and transmitting such equalized data to a remote server. It thus provides an automatized way of integrating in a web connected environment information from different farm climate and/or biometric controllers. It is also an object of the present invention to provide a device which implements the method and which may comprise a room connection unit (104), a data processing unit (103), a non-volatile data buffering unit (102) and a remote connection unit (101).

Abstract: A method for managing tracklets in a particle filter estimation framework includes executing a tracklet prediction dependent on a list of previous tracklets, thereby determining persistent tracklets and new tracklets; sampling new measurements for initializing the new tracklets, thereby determining an amount of estimated new tracklets; and determining an amount of the persistent tracklets dependent on the list of previous tracklets. The method further includes determining an amount of the new tracklets and an amount of updated persistent tracklets to be sampled dependent on the amount of estimated new tracklets, the amount of the persistent tracklets, and a memory bound; sampling the updated persistent tracklets from a list of the persistent tracklets dependent on the determined amount of the updated persistent tracklets; and sampling the new tracklets from unassociated measurements dependent on the determined amount of the new tracklets.

Abstract: A biological-information detection device includes a video input section accepting video signals including three wavelength components in an infrared region of reflected light from an object, a wavelength detecting section acquiring a wavelength and an intensity of the reflected light from the video signals, a face feature amount detecting section detecting a plurality of feature points of a face based on the video signals, a measurement target area identifying section identifying a measurement target area on a basis of the plurality of feature points of the face detected, a wavelength fluctuation detecting section detecting a difference between a wavelength of reflected light from the measurement target area at a certain point in time and a wavelength of reflected light at a point in time preceding the certain point in time, and a pulse wave detecting section detecting a change in the detected difference according to the point in time.

Abstract: A solid-state image sensor includes a pixel array section including a plurality of unit pixels each having a photoelectric conversion unit, the plurality of unit pixels being arranged in a matrix, a constant current source circuit unit having a constant current source connected to each of vertical signal lines provided in association with column arrangement of the pixel array section; and a control unit configured to control the constant current source circuit unit. The constant current source includes a plurality of transistors. The control unit switches, in a case where the plurality of transistors constituting the constant current source is regarded as one transistor having a gate width and a gate length being equivalent to each other, a ratio between the gate width and the gate length of the plurality of transistors on the basis of illumination in image-capturing environment.

Abstract: A method and apparatus includes at least one first sensor configured to be mounted to an infrastructure component, wherein the at least one sensor comprises an environmental sensor. At least one second sensor is configured to be mounted to the infrastructure component, and is configured to sense movement of the infrastructure component. The method and apparatus also includes a system that uses the at least one first sensor to detect an object position and determines an amount of correction for the object position based on movement detected by the at least one second sensor.

Abstract: Disclosed herein are methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling access to a property based on smart contract execution. One of the methods includes receiving credential data for a first entity requesting access to a property; in response to receiving the credential data, requesting execution of a smart contract associated with the property by a blockchain network, wherein the smart contract includes instructions to check a current status of a relationship between the first entity and a second entity associated with the property based on the credential data; receiving an execution result of the smart contract from the blockchain network; determining that the first entity is authorized to access the property based at least in part on the execution result; and in response to determining that the first entity authorized to access the property, enabling the first entity to access to the property.

Abstract: A method and apparatus includes at least one environmental sensor mounted to an infrastructure component that is capable of moving relative to ground. The at least one environmental sensor determines an object position. A system uses environmental data collected over time to learn a fixed environment that includes at least one learned reference point. The system determines an amount of movement of the infrastructure component in relation to the learned reference point. The system corrects object position to compensate for movement of the infrastructure component.

Abstract: An image capturing apparatus includes a plurality of imaging units arranged in a circumferential manner and movable in a circumferential direction, and a plurality of illumination units arranged in such a manner that each of the plurality of illumination units corresponds to a different one of the plurality of imaging units. In a case where the plurality of imaging units moves in the circumferential direction, each of the plurality of imaging units integrally moves with a corresponding one of the plurality of illumination units.

Abstract: A system finds and aggregates the most relevant and current information about the people and things that a user cares about. The information gathering is based on current context (e.g., where the user is, what the user is doing, what the user is saying/typing, etc.). The result of the context based information gathering is presented ubiquitously on user interfaces of any of the various physical devices operated by the user.

Abstract: The invention provides systems and method for generating device-specific artificial neural network (ANN) models for distribution across user devices. Sample datasets are collected from devices in a particular environment or use case and include predictions by device-specific ANN models executing the user devices. The received datasets are used with existing datasets and stored ANN models to generate updated device-specific ANN models from each of the stored instances of the device ANN models based on the training data.

Abstract: A device is provided, comprising: an image storage unit which is configured to store image data obtained by a monitoring camera; an analyzing unit which is configured to perform image analysis on the image data and, in response to a detection of a target object to be detected among objects which are possibly included in the image data, generate feature data indicating a feature of the target object; and a transmitting unit which is configured to transmit metadata including the feature data and at least one of a shooting time of the image data in which the feature data is generated or an address of the image data within the image storage unit to a file server which is accessible to another apparatus different from the device.

Abstract: The present disclosure provides an image generating device that includes processing circuitry configured to acquire an image captured by an imaging device to be installed in a water-surface movable body, acquire positional information indicative of a position of the water-surface movable body, acquire posture information indicative of a posture of the water-surface movable body, acquire additional display information including information indicative of positions of one or more locations, generate a synthesized image where a graphic rendering a three-dimensional virtual reality object indicative of the additional display information is synthesized on the captured image based on the positional information, the posture information, and the additional display information, and place the graphic across a boundary of the captured image when the captured image is placed only in a certain portion of the synthesized image.

Abstract: A first radio of a wireless, e.g., dual-SIM DSDS, device communicates wirelessly with a first, e.g., 5G CBSD, base station of a first service provider using a first spectrum type, e.g., PAL or high- or low-bandwidth GAA, while a second radio communicates wirelessly with a second, e.g., 5G non-CBSD gNB, base station of a second service provider using a second spectrum type. The first radio informs the second radio of the first spectrum type assigned to the first radio, and the second radio transmits, to the second base station, capability information for the second radio based on the first spectrum type, that capability information being used by the second base station in assigning the second spectrum type to the second base station, thereby enabling equivalent QoS to be rendered to both radios even when the first service provider cannot directly control the QoS provided by the second service provider.

Abstract: A tracking apparatus comprises a detection unit that detects a subject in an image obtained by photoelectrically converting light entering through an imaging optical system with an image sensor, a tracking unit that tracks the subject in a plurality of predetermined directions, a determination unit that determines a tracking direction in which the subject is to be tracked among the plurality of directions, and a control unit that controls the tracking unit to perform tracking in the tracking direction and suppress tracking in a direction different from the tracking direction.

Abstract: In an example, an apparatus includes a first sensor, a second sensor, and a controller. The first sensor collects a first set of data describing a three-dimensional object that is placed in a constant position in a scene. The second sensor collects a second set of data describing the three-dimensional object. The first sensor has a first position in the scene, while the second sensor has a second position in the scene. The controller generates a first rendering of the three-dimensional object from the first set of data and generates a second rendering of the three-dimensional object from the second set of data. The controller also determines the first position and the second position based on an alignment of the first rendering and the second rendering with a three-dimensional model of the three-dimensional object.

Abstract: An image identifying method is applied to a monitoring camera and a monitoring camera system and used to determine whether a target object is a leaving object or a missing object. The image identifying method includes acquiring a foreground region within a monitoring image corresponding to the target object, analyzing whether the target object inside the foreground region conforms to a variant feature, and comparing the foreground region with a reference image for determining the target object belongs to the leaving object or the missing object when the foreground region does not conform to the variant feature.

Abstract: Aspects discussed herein relate to systems, apparatuses, and methods for providing content distribution via a breadth-first approach for peer-to-peer file sharing in a temporary ad hoc mesh network. For example, a peer-to-peer orchestrator may receive requests for the same asset from multiple mobile devices, determine which of the mobile devices are likely to travel along the same route at the same time, group them together and cause transmission of different asset parts of the requested asset to different mobile devices in the group. If the mobile devices in the group lose connection with the peer-to-peer orchestrator, they may form an ad hock mesh network and retrieve asset parts from one another. If the group reconnects with a peer-to-peer orchestrator, additional asset parts of the asset may be transmitted to the group and the process may repeat so that each mobile device may obtain each of the asset parts.

Abstract: An observation system includes a first sensor configured to observe a first portion of an observation target, a second sensor configured to observe a second portion of the observation target, and a control device including a memory and a processor coupled to the memory, the processor being configured to receive first observation data from the first sensor via a first relay device and second observation data from the second sensor via a second relay device, wherein the first observation data is not transmitted from the first sensor to the second relay device when the first observation data is transmitted from the first sensor to the control device via the first relay device, and the second observation data is not transmitted from the second sensor to first relay device when the second observation data is transmitted from the second sensor to the control device via the second relay device.

Abstract: Methods and systems for identifying events of interest in images from imagers in an edge computing network, including: detecting a movement based on image processing in images captured by the imager, cropping an area of the at least one image where the movement is detected, applying a first machine learning (ML) algorithm having a deep neural network architecture to classify an object of interest in the cropped area of the at least one image, sending the at least one image to a server, when the first ML algorithm classifies the object of interest, applying a second ML algorithm having a deep neural network architecture to detect the object of interest in the at least one image where the object of interest is detected based on context analysis.

Abstract: Systems and methods for configuration for contextual response to motion-based events are disclosed. For example, a predefined event may be detected. The system may determine that a subject associated with the event is of a given type of subjects and may determine whether another person is present in the environment associated with the event to assist in providing aid. The presence of the other person may be detected, a type of the other person may be performed, and a notification may be output on a second device associated with the other person based on the type. The system may track when the other person reach an area associated with the event and may cause the first device to perform an action to assist the other person in providing aid.

Abstract: A modular light assembly having a control housing surrounding a power driver and at least one modular component. The modular component includes two side portions, a plurality of ribs extending between the two side portions to form a grated portion, and a flat portion configured to receive a COB LED. The lighting assembly may also comprise a video assembly having a camera and control circuitry provided within the lighting and video assembly for remotely controlling the camera.

Abstract: The presently disclosed subject matter relates to a method for recognizing objects of a predefined type from among a set of types, within a set of digital images, including detecting an object of this predefined type within a digital image of the set, and determining a zone of the image encompassing the detected object, generating a signature by a convolutional neural network on the basis of this zone, allowing identification of the object in a one-to-one manner, determining on the basis of the signature of a set of attributes, storing in a database a record relating to the object associating the signature with the set of attributes, wherein the neural network is trained on a learning suite composed of a first set formed of objects associated with a set of attributes and of a second set formed of objects not associated with a set of attributes.

Abstract: Examples disclosed herein provide a computing device. As an example, the computing device includes a camera comprising a lens, and a housing comprising an opening extending through the housing, wherein the opening is to accommodate the lens. The housing further includes a shutter to selectively obscure the opening, and a mechanical trigger, upon receiving an electrical signal, to move the shutter to obscure the opening.