Abstract: The described technology provides a system and method of generating a 360-degree panoramic virtual reality (VR) image by using a plurality of photograph images. A plurality of image capturing devices capture and transmit the plurality of photograph images, respectively. An image conversion device receives the plurality of photograph images from the plurality of image capturing devices, calibrates each of the plurality of photograph images using characteristic information of respective one of the plurality of image capturing devices, and stitches calibrated photograph images to generate the 360-degree panoramic VR image. According to embodiments, the user can check a situation of a monitoring area while changing the viewpoint of the 360-degree panoramic VR image or enjoy the generated VR contents at a high degree of immersion.
Type:
Grant
Filed:
November 21, 2018
Date of Patent:
September 7, 2021
Assignee:
Korea Electronics Technology Institute
Inventors:
Woochool Park, Junhwan Jang, Younghwa Kim, Jinwook Yang, Sangpil Yoon, Hyunwook Kim, Eunkyung Cho, Minsu Choi, Junsuk Lee, Jaeyoung Yang
Abstract: Systems and methods for augmenting real-time semantic information to a spatial rendering of a predefined space and providing a real-time situational awareness feed.
Abstract: There are provided systems and methods for synchronizing effects for multi-user mixed reality experiences. In one implementation, such a system includes a computing platform having a hardware processor and a system memory storing a software code. The hardware processor executes the software code to receive sensor data from multiple sensors within a venue, identify an activity in the venue based on the sensor data, and track a respective perspective and a respective location within the venue of each of multiple observers of the activity. The hardware processor also executes the software code to identify a first effect triggered by an action of one of the observers, conform the first effect to the respective perspective and the respective location of each of the observers to produce multiple second effects corresponding to the first effect, and output the second effects for operating multiple actuating devices within the venue during the activity.
Type:
Grant
Filed:
September 25, 2019
Date of Patent:
August 31, 2021
Assignee:
Disney Enterprises, Inc.
Inventors:
Leslie Evans, Nicholas Newberg, Alexis P. Wieland, Clare M. Carroll, Joseph G. Hager, IV, Siroberto Scerbo, Jonathan Becker
Abstract: Computer-implemented systems and methods for video content analysis are described herein. A video feed comprising at least one image captured by a camera is received. The at least one image has a plurality of regions associated with a different level of precision required for each region. An adjustable image processing algorithm is applied to each region of the at least one image to obtain for each region the different level of precision. The image processing algorithm is adjusted based of the different level of precision associated with each region. Meta data indicative of content of the video feed is generating by the image processing algorithm.
Abstract: Disclosed are a learning data generation method and apparatus needed to learn animation characters on the basis of deep learning. The learning data generation method needed to learn animation characters on the basis of deep learning may include collecting various images from an external source using wired/wireless communication, acquiring character images from the collected images using a character detection module, clustering the acquired character images, selecting learning data from among the clustered images, and inputting the selected learning data to an artificial neural network for character recognition.
Type:
Grant
Filed:
November 26, 2019
Date of Patent:
August 31, 2021
Assignee:
ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
Inventors:
Dong Hyuck Im, Jung Hyun Kim, Hye Mi Kim, Jee Hyun Park, Yong Seok Seo, Won Young Yoo
Abstract: The present technology relates to an imaging control device and method, and a vehicle that enable distance measurement with higher accuracy. An imaging control unit controls imaging by a stereo camera system including at least a set of cameras arranged in a vertical direction, the set of cameras including at least one camera arranged to have an optical axis directed obliquely downward, and a monitoring processing unit performs monitoring processing on the basis of an image captured by the stereo camera system. For example, distance measurement processing is performed on the basis of an image captured by at least the set of cameras arranged to have at least one optical axis directed obliquely downward on a side surface of the vehicle. The present technology can be applied to driving assistance of a vehicle.
Abstract: A method for image generation, preferably including: generating a set of mission parameters for a UAV mission of the UAV associated with aerial scanning of a region of interest; controlling the UAV to perform the mission; generating an image subassembly corresponding to the mission; and/or rendering the image subassembly at a display.
Type:
Grant
Filed:
February 28, 2020
Date of Patent:
August 31, 2021
Assignee:
DroneDeploy, Inc.
Inventors:
Jonathan James Millin, Nicholas Pilkington, Devin Lane, Christopher Sullivan, Michael Winn
Abstract: A system includes a sensor and a remote processing and storage component in communication with the sensor. The sensor generates sensor data indicative of the presence of people or objects in a scene. The remote processing and storage component receives the sensor data from the sensor and performs an automated counting process to determine an automated count of people or objects. The component receives a request to perform a validation process for the sensor. The component also generates and transmits a link to a manual validation page that includes an interface for performing a manual count. The component further receives an indication to start a validation process from the manual validation page, generates an automated count value from the performed automated counting process, and receives manual count data. The component also generates a validation report based on the automated count value and the manual count data.
Type:
Grant
Filed:
January 9, 2020
Date of Patent:
August 31, 2021
Assignee:
INFRARED INTEGRATED SYSTEMS LIMITED
Inventors:
Stuart A. Holliday, Timothy J. Wheatley
Abstract: Systems and methods are disclosed for intelligently activating light devices for optimized lighting conditions in a scene, where optimized illumination is provided by a subset of light devices within an array of light devices in communication with the camera. The systems and methods detect a target within a camera's field of view and determine an optimized illumination of the target according to a video analytics model. Lighting is adjusted in accordance with the determined optimized illumination.
Type:
Grant
Filed:
February 19, 2018
Date of Patent:
August 24, 2021
Assignee:
CISCO TECHNOLOGY, INC.
Inventors:
Nicholas Dye Abalos, Ian Matthew Snyder
Abstract: A system and method for a remote state following device that includes an electronic device with a controllable operating state; an imaging device; and control system that when targeted at a control interface interprets a visual state from the control interface, and modifies the operating state in coordination with the visual state.
Abstract: Computer-implemented methods and systems for processing recorded data for storage is provided. An auditable device, such as a digital video camera, stores a set of recorded data. The auditable device also stores auditable event entries that represent auditable events detected by the auditable device. One type of auditable event is the receipt of information from a computer-aided dispatch (CAD) system that indicates an event. The auditable device marks at least one subset of the set of recorded data based on the auditable event entries, and uploads the marked at least one subset of the set of recorded data to an evidence management system.
Type:
Grant
Filed:
September 6, 2019
Date of Patent:
August 17, 2021
Assignee:
Axon Enterprise, Inc.
Inventors:
Patrick W. Smith, Mark A. Hanchett, Aaron J. Kloc, Tyler J. Conant
Abstract: Aspects of the subject disclosure may include, for example, a method that includes generating a virtual venue for the virtual reality space, wherein the generating the virtual venue including replicating an architecture of a venue associated with the event and generating a plurality of virtual stores for the virtual venue, wherein each virtual store is associated with each participant of the plurality of participants, accessing a plurality of cameras and a plurality of microphones associated with the event, generating the virtual reality space based on the plurality of participants, the virtual venue, the plurality of microphones, and the plurality of cameras, generating a plurality of images for each participant of the plurality of participants according to each profile for each participant of the plurality of participants to participate in the event, and presenting the virtual reality space to user equipment in a virtual reality format. Other embodiments are disclosed.
Type:
Grant
Filed:
June 21, 2017
Date of Patent:
August 17, 2021
Assignee:
AT&T INTELLECTUAL PROPERTY I, L.P.
Inventors:
Robert J. Koon, Christopher Carl, Miranda Bradley, Katie Alvarez, Brittany Landry, Eric Ricchezza
Abstract: An electronic device includes an image capturing device and a processor electrically connected with the image capturing device, wherein the processor is configured to obtain a first portion of a video at a first capturing speed during a first period using the image capturing device, control a first notification to indicate obtaining a second portion of the video at a set second capturing speed when the second capturing speed is set as a speed of capturing the video based on a result of analyzing the first obtained portion, and obtain the second portion at the second capturing speed during a second period following the first period using the image capturing device.
Type:
Grant
Filed:
January 12, 2018
Date of Patent:
August 17, 2021
Inventors:
Dong-Soo Kim, Hwa-Young Kang, Shuichi Shimokawa, Young-Kwon Yoon, Sang-Min Lee, Jong-Hun Won
Abstract: An integrated security system integrates broadband and mobile access and control with conventional security systems and premise devices to provide a tri-mode security network having remote connectivity and access. The integrated security system delivers remote premise monitoring and control functionality to conventional monitored premise protection and complements existing premise protection equipment. The integrated security system integrates into the premise network and couples wirelessly with the conventional security panel, enabling broadband access to premise security systems. Automation devices can be added, enabling users to remotely see live video or pictures and control home devices via a personal web portal or other client device. Camera management enables automatic configuration and management of cameras in the premise network.
Abstract: Provided is a heatmap providing apparatus and method in which a heatmap is generated and displayed for an area of interest set in a full region. The heatmap providing method includes: obtaining motion occurrence frequencies in a captured region; setting at least one area of interest in the captured region; and displaying the motion occurrence frequencies in different indications in the area of interest.
Abstract: An aspect of the invention includes a fire and smoke detection system including a 360-degree camera, and a computing platform in communication with the 360-degree camera. The computing platform is configured to receive an image or video from the 360-degree camera, determine that tire or smoke is detected in the image or video received from the 360-degree camera, and venerate at least one alert in response to determining that fire or smoke is detected in the image or video received from the 360-degree camera. The fire and smoke detection system may be portable and not removably mounted.
Type:
Grant
Filed:
August 5, 2019
Date of Patent:
August 3, 2021
Assignee:
Factory Mutual Insurance Company
Inventors:
Jaap De Vries, Stanislav Kostka, Raphael Hussni Leonessa, Kyle Richard Burchesky
Abstract: An apparatus, when it is determined that a resolution of a captured image is higher than or equal to a predetermined resolution, transmits, to an external apparatus, a first request for an image of a resolution corresponding to a resolution higher than or equal to the predetermined resolution, and when it is determined that the resolution of the captured image is not higher than or equal to the predetermined resolution, transmits, to the external apparatus, a second request for an image of a resolution corresponding to a resolution lower than the predetermined resolution, performs control to sequentially receive images that are sequentially captured by the external apparatus, and performs control to combine the images that are captured by the external apparatus with the images that are sequentially generated by the image capturing, and sequentially display the combined images.
Abstract: A computer-implemented method for providing an objective evaluation to a customer service representative regarding his performance during an interaction with a customer may include receiving a digitized data stream corresponding to a spoken conversation between a customer and a representative; converting the data stream to a text stream; generating a representative transcript that includes the words from the text stream that are spoken by the representative; comparing the representative transcript with a plurality of positive words and a plurality of negative words; and generating a score that varies according to the occurrence of each word spoken by the representative that matches one of the positive words, and/or the occurrence of each word spoken by the representative that matches one of the negative words. Tone of voice, as well as response time, during the interaction may also be monitored and analyzed to adjust the score, or generate a separate score.
Type:
Grant
Filed:
May 21, 2020
Date of Patent:
July 27, 2021
Assignee:
State Farm Mutual Automobile Insurance Company
Abstract: A video collection system includes: a plurality of terminals; and a video collection server that requests at least one of the plurality of terminals to perform information provision. The video collection server includes a calculation part, a determination part, and a request part. The calculation part calculates, based on information acquired from a camera(s), a first area(s) imaged by the camera(s). The determination part determines a second area(s) as an information provision target(s) based on a location(s) of the first area(s). The request part selects, based on respective locations of the plurality of terminals and a location(s) of the second area(s), a terminal(s) to be requested to perform the information provision from the plurality of terminals and requests the selected terminal(s) to provide video data of the second area(s).
Abstract: A viewing device for a vehicle has: a monitor that displays a captured image of a vehicle rear side; and a control device that carries out display control that compresses the captured image such that a compression rate gradually becomes higher from a vehicle inner side toward outer sides, and displays an image on the monitor.
Abstract: Techniques for delaying an alert based on suspicious activity detection are provided. An artificial intelligence system may detect suspicious behavior of a suspect within a vicinity of a school. A responder may be dispatched to investigate the suspect. An alert signal may be temporarily delayed. A time period for the delay may be associated with a time required for the responder to investigate and a severity of the alert signal. The delay may be canceled when the responder indicates the suspect behavior is not suspicious.
Type:
Grant
Filed:
November 30, 2020
Date of Patent:
July 20, 2021
Assignee:
MOTOROLA SOLUTIONS, INC.
Inventors:
Heng Cheng Chiam, Choon Kang Wong, Chee Kit Chan, Swee Yee Soo
Abstract: Methods and apparatus are described that use machine vision and machine learning to eliminate many of the steps of a typical retail transaction. For example, implementations are contemplated in which a user simply removes an item from a retail location to effect the transaction.
Type:
Grant
Filed:
November 29, 2017
Date of Patent:
July 20, 2021
Assignee:
365 Retail Markets, LLC
Inventors:
Paul McDonald, Ashwath Rajan, Tyler Garvin
Abstract: Disclosed embodiments allow media players and other electronic devices that operate under a first protocol to control the media capture devices that operate with a second protocol which may not be configurable to communicate with the first protocol. In one embodiment of the disclosure, a network device may store and/or render content within a Digital Living Network Alliance (DLNA) network and/or assist in content delivery for a DLNA device on a network. In another embodiment of the disclosure, a media capture device uses the Internet Protocol.
Abstract: An information processing apparatus according to an embodiment includes a determination unit and an output control unit. The determination unit determines whether a particular part related to a type of an object is included in a blind spot of an object of interest. The output control unit outputs output information when it is determined that the part is included in the blind spot.
Abstract: A security cover for an audio/video recording and communication device (A/V device) comprises a front wall includes first and second apertures. The first aperture is positioned to expose a camera of the A/V device. The second aperture is positioned to expose a button of the A/V device. The security cover further includes a set of one or more adjoining sidewalls extending from the front wall and being sloped outward from the front wall. The security cover further includes a mounting surface extending about the set of sidewalls, the mounting surface being spaced from the front wall. The security cover further includes a rigid mounting frame having a first surface for abutting a support surface and a second surface, opposite the first surface, for abutting the mounting surface. The front wall, the set of sidewalls, and the rigid mounting frame together form an interior compartment to contain the A/V device.
Abstract: Embodiments relate to a danger zone protection and assistance system that includes a personal trigger that is used by a user to indicate presence of danger, a microprocessor controlled device that once receives a command from the personal trigger, will use visual alarming and audible alarming capabilities available to summon assistance from people close by, and use cellular calling capability, where available, to summon assistance from people and emergency assistance services remote to the zone of danger.
Abstract: A server computing device configured to receive, via an anonymization network and from a first mobile computing device that determines a location from a set of locations of the first mobile computing device is within a threshold distance of an event, a proximity indication that a first user associated with the first mobile computing device is proximate to the event; in response to receiving an indication of a remittance for the event from a second user, generate an association between the remittance and the event; in response to receiving descriptive data that is descriptive of the event, send the descriptive data to a second mobile computing device of the second user; and in response to receiving an indication to release the remittance, send a message that executes a transaction that transfers at least a portion of the amount of the remittance to an account associated with the first user.
Type:
Grant
Filed:
August 26, 2018
Date of Patent:
July 13, 2021
Inventors:
Arthur Oliver Tucker, IV, Christopher Delton Karlen
Abstract: A waterproof effect enhancing structure that can make an imaging apparatus compact. A camera unit including an imaging element, a rotation shaft that is a center of rotation of the camera unit, a bearing that rotatably supports the rotation shaft, a base member that supports the bearing, a presser member that is fixed to the rotation shaft, an ultrasonic motor that is disposed on a same axis as the rotation shaft, and has a rotor that is brought into pressure contact with the presser member, and a stator that is brought into pressure contact with the base member, and a waterproof unit disposed between the base member and the camera unit are placed in the imaging apparatus, and the camera unit, the waterproof unit, the base member, the ultrasonic motor, and the presser member are disposed in a rotation axis direction in this order.
Abstract: Multi-time search analytics for smart video indexing based on active search and video database, which is configured to be operated without any need for a second broadcast with a camera, a second large data index, additional servers, a third additional software for indexing and analytics, a third additional face recognition system, a license recognition system, an object recognition system, or an additional net bandwidth for a new hardware. The method of operating multi-time search analytics for the additional net bandwidth for new hardware includes following steps: recognizing objects, activating software components and/or incoming alarms, collecting the alarms in an alarm database pool, extracting a first video with a same length in the alarm database pool, performing a motion recognition with H264/H265, recording detected motions by a video content recorder, transferring the detected motions to a timeline adjuster and changing the detected motions in accordance with an Alpha Time Zone.
Abstract: A dome for a surveillance camera and the surveillance camera including the same is provided. The dome may include a spherical part having a hemispherical shape, an aspherical part having a cylindrical shape extending from an end of the spherical part, and a bracket including a first surface coupled to an inner surface of the aspherical part and a second surface extending a curved surface of an inner surface of the spherical part.
Abstract: A method for generating a surround view (SV) image for display in a view port of an SV processing system is provided that includes capturing, by at least one processor, corresponding images of video streams from each camera of a plurality of cameras and generating, by the at least one processor, the SV image using ray tracing for lens remapping to identify coordinates of pixels in the images corresponding to pixels in the SV image.
Type:
Grant
Filed:
March 1, 2019
Date of Patent:
June 29, 2021
Assignee:
Texas Instruments Incorporated
Inventors:
Hemant Vijay Kumar Hariyani, Martin Fritz Mueller, Vikram VijayanBabu Appia
Abstract: A monitoring camera (1) photographs a predetermined location and outputs a photographed image; an image processing apparatus (2) acquires the photographed image from the monitoring camera (1) and performs a mask process of a specific part in the photographed image; and a monitoring apparatus (3) acquires and displays the photographed image after the mask process from the image processing apparatus (2). Further, the image processing apparatus (2) detects a frame image of a display device (101) in the acquired photographed image, and performs the mask process of an image of a display screen on the display device (101) on the basis of the detected frame image.
Abstract: In an access control system, a registration procedure for a visitor is implemented to control access to an access-restricted zone in a building or a site. At the invitation of a host, the visitor sends a digital image, an invitation identification number and a device-specific identifier of the electronic device of the visitor to the access control system. The image data and the identifier are assigned to a visitor profile previously created for the visitor by means of the identification number of the invitation. The image data are processed by the access control system to generate a reference template, the reference template being stored in the visitor profile.
Abstract: When a second condition is satisfied in a case in which an automated driving control unit performs switching from automated driving to manual driving, a request for a remote operation is sent to an outside-vehicle facility using a communicator, and remote driving for automatically controlling at least one of acceleration/deceleration and steering of a vehicle is executed on the basis of control information received from the outside-vehicle facility.
Abstract: The invention provides a method for video surveillance in a video-surveillance system comprising the steps of capturing video images by a video camera observing an area of surveillance; wherein the capturing the video images comprises making objects in the area of surveillance irrecognizable or invisible in captured video images; receiving, by a processor, a predetermined signal; based on the received predetermined signal, generating a first control signal by the processor and transmitting the first control signal to the video camera; receiving the first control signal by the video camera; based on the received first control signal, stopping making objects in the area of surveillance irrecognizable or invisible in the captured video images.
Type:
Grant
Filed:
October 17, 2019
Date of Patent:
June 29, 2021
Assignee:
IDEMIA Identity & Security Germany AG
Inventors:
Stefan Langhammer, Norbert Wendt, Christian Winter
Abstract: A surveillance system monitors a predetermined environment based on received data. The surveillance system includes a first intelligent appliance configured to capture video and/or still images and configured to be in wireless communication with a second intelligent appliance that operates based on data from the first intelligent appliance. The surveillance system can detect a person located within the predetermined environment and can track the person's movement. The surveillance system is configured to allow remote viewing of data and/or controlling cameras.
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating object interaction predictions using a neural network. One of the methods includes obtaining a sensor input derived from data generated by one or more sensors that characterizes a scene. The sensor input is provided to an object interaction neural network. The object interaction neural network is configured to process the sensor input to generate a plurality of object interaction outputs. Each respective object interaction output includes main object information and interacting object information. The respective object interaction outputs corresponding to the plurality of regions in the sensor input are received as output of the object interaction neural network.
Type:
Grant
Filed:
November 18, 2019
Date of Patent:
June 22, 2021
Assignee:
Waymo LLC
Inventors:
Alper Ayvaci, Yu-Han Chen, Ruichi Yu, Chen Wu, Noha Waheed Ahmed Radwan, Jonathon Shlens
Abstract: A control apparatus includes an acquisition unit that acquires selection information for selecting, based on a detection result of a sensor, an image capturing device that captures an image to be displayed and/or stored by a terminal device from among a plurality of image capturing devices, and a control unit that performs control in such a manner that a communication amount related to a captured image from an image capturing device that is unlikely to be selected from among the plurality of image capturing devices based on the acquired selection information becomes less than a communication amount related to a captured image from an image capturing device that is likely to be selected based on the acquired selection information.
Abstract: A surveillance system monitors a predetermined environment based on received data. The surveillance system includes a first intelligent appliance configured to capture video and/or still images and configured to be in wireless communication with a second intelligent appliance that operates based on data from the first intelligent appliance. The surveillance system can detect a person located within the predetermined environment and can track the person's movement. The surveillance system is configured to allow remote viewing of data and/or controlling cameras.
Abstract: Systems for detecting occupancy of an area comprising one or more zones can include one or more sensors and one or more processors configured to receive sensor data from the one or more sensors over time. The one or more processors can be further configured to receive or store data about an arrangement of the zones in the area. The one or more processors can apply a probabilistic model considering the sensor data received over time to determine the number of subjects in each zone by determining a most likely current state of occupancy of the area among a plurality of possible scenarios.
Type:
Grant
Filed:
July 10, 2017
Date of Patent:
June 15, 2021
Assignee:
Infrared Integrated Systems Limited
Inventors:
Stuart A. Holliday, Christopher A. Evans, Neil Johnson
Abstract: A device, system and method for generating an alert and an automatic search for a candidate subject is provided. The device monitors one or more data sources to identify a candidate subject. The device determines, from rules for rating candidate subjects stored in a memory, a rating of the candidate subject. When the rating meets a first threshold: the device transmits, to one or more communication devices, an alert identifying the candidate subject. When the rating meets a second threshold, lower than the first threshold: the devices provides, a classifier defining the candidate subject to an object recognition engine to cause the object recognition engine to automatically search for the candidate subject, using the classifier, in multimedia data received at one or more edge devices. The multimedia data may include images.
Type:
Grant
Filed:
March 15, 2018
Date of Patent:
June 15, 2021
Assignee:
MOTOROLA SOLUTIONS, INC.
Inventors:
Alejandro G. Blanco, Scott M. Alazraki, Shervin Sabripour, Patrick D. Koskan
Abstract: To provide a motion video segmenting method, a motion video segmenting device, and a motion video processing system that increase accuracy of motion video analysis performed by segmenting a motion video. A difficulty degree of each image configuring a pack is determined, and in a case where an image of a difficulty degree of Low continues for a predetermined value F_cnt or more, a motion video is segmented with an image one before a last of consecutive images to form a pack.
Abstract: An information processing apparatus generates, for two or more videos including an overlapping region that overlap each other, overlapping region information that indicates the overlapping region, and transmits the overlapping region information to a display control apparatus that generates a video by concatenating the two or more videos. The display control apparatus obtains the overlapping region information from another apparatus, generates a video by concatenating the two or more videos based on the overlap information, and causes the display unit to display the generated video.
Abstract: An apparatus includes a movement mechanism, a sensor, a microphone, a speaker, a processor and a memory. The processor selects a target region, controls the movement mechanism to cause the apparatus to move to the target region, and causes a speaker to output a first sound. When counting a predetermined number, the processor causes the sensor to trace a movement locus of a user. In a case where the processor has determined that an acquired sound contains a predetermined speech, the processor controls the movement mechanism to cause the apparatus to move through a predetermined space. When the processor has determined that the apparatus is not to intentionally lose in a game of hide-and-seek, the processor controls the movement mechanism to cause the apparatus to move to a target blind spot within the predetermined space, and causes the speaker to output a second sound.
Abstract: Systems, devices, methods, and computer processing products for automatically checking for errors in segmentation (contouring) using heuristic and/or statistical evaluation methods.
Type:
Grant
Filed:
January 21, 2019
Date of Patent:
June 15, 2021
Assignee:
VARIAN MEDICAL SYSTEMS INTERNATIONAL AG
Inventors:
Thomas Albrecht, Peter Hess, Nawal Houhou
Abstract: In determining luminance, a location of human presence is referred. An infrared sensor detects the human presence in its proximity. The infrared sensor's effective detecting region includes a first region and a second region. The first region is farther from the infrared sensor than the second region is. And the first region surrounds the second region. Second, a first luminance is set for human presence within the first region; a second luminance is set for human presence within the second region; and a third luminance is set for nonoccurrence of human presence within both the first region and the second region. In addition, the second luminance is higher than the first illuminance, and the first illuminance is higher than the third illuminance. Third, an illuminating device is activated by applying the first luminance, the second luminance, or the third luminance, in response to a location of the detected human presence.
Abstract: An image processing apparatus includes a communication interface and a controller. The communication interface is configured to acquire a first video image capturing an outside area of a moving body. The controller is configured to cause a second video image corresponding to a display region of the first video image to be displayed on a display apparatus. The controller is also configured to detect at least a portion of a detection object in the display region of the first video image, determine whether one or more conditions are met based on a relative positional relationship between the moving body and the detection object and, when it is determined that the one or more conditions are met, cause a first marker corresponding to the detection object to be superimposed on the second video image and displayed on the display apparatus.
Abstract: A method of selectively broadcasting a message to a client by a server without knowing the client's internet protocol (IP) address includes receiving video feeds of an area of interest from one or more cameras, performing target recognition and tracking on one or more targets, including position of the one or more targets, extracting target-specific context parameters from the one or more recognized and tracked targets, encoding the target-specific context parameters into a header, thereby generating a context address for the one or more targets, appending the context address to a message for the one or more targets from a predetermined set of messages based on the position of the one or more targets, thereby generating one or more packets of information, and broadcasting the one or more packets wirelessly to one or more client mobile devices each associated with the one or more targets.