Abstract: Embodiments of adaptive multi-modal event detection are disclosed herein. In one example, sensor data captured by multiple sensors is received, and an inconsistency among the sensors is detected based on performing event detection on the sensor data. An external environment of the sensors is detected based on the sensor data, and one or more configuration parameter(s) for event detection are adjusted based on the external environment of the sensors. Event detection is then performed on the sensor data based on the adjusted configuration parameter(s).

Abstract: A method and apparatus for alerting groups of user devices to similar video content of interest based on role. The method includes providing a first video to groups of user devices, each having an associated user role, receiving viewing metrics indicative of levels of viewing interest for the first video from a first group of user devices associated with a particular user role, and when a level of viewing interest is above a predetermined threshold, classifying one or more corresponding first video frames of the first video as frames of interest. The method further includes receiving a second video, determining, using the frames of interest, that video content of the second video is of interest to a second group of user devices having the particular user role, and providing an alert to the second group of user devices.

Abstract: A method and apparatus for acquiring an image is provided herein. During operation a determination is made that a user is intending to tag an object through pointing a finger at the object. In response, a pre-buffer is accessed, and an image of the object is selected from the pre-buffer that is absent the user's hand. Once the image has been selected, the image can be forwarded to other users.

Abstract: A method and apparatus for alerting groups of user devices to similar video content of interest based on role. The method includes providing a first video to groups of user devices, each having an associated user role, receiving viewing metrics indicative of levels of viewing interest for the first video from a first group of user devices associated with a particular user role, and when a level of viewing interest is above a predetermined threshold, classifying one or more corresponding first video frames of the first video as frames of interest. The method further includes receiving a second video, determining, using the frames of interest, that video content of the second video is of interest to a second group of user devices having the particular user role, and providing an alert to the second group of user devices.

Abstract: Method and device for providing safe zone information. The method includes receiving a map of an incident area sensor information from at least one sensor at the incident area. The method also includes determining a multi-dimensional model of the incident area based on the map of the incident area and the sensor information and determining a first threat location based on the sensor information, the map of the incident area, and the multi-dimensional model of the incident area. The method further includes determining a plurality of safe zone shadow areas based on the first threat location. The method also includes updating the multi-dimensional model of the incident area to include the plurality of safe zone shadow areas and to generate a safe zone shadow representation of the incident area and transmitting the safe zone shadow representation to at least one user device in the incident area.

Abstract: Method and device for providing safe zone information. The method includes receiving a map of an incident area sensor information from at least one sensor at the incident area. The method also includes determining a multi-dimensional model of the incident area based on the map of the incident area and the sensor information and determining a first threat location based on the sensor information, the map of the incident area, and the multi-dimensional model of the incident area. The method further includes determining a plurality of safe zone shadow areas based on the first threat location. The method also includes updating the multi-dimensional model of the incident area to include the plurality of safe zone shadow areas and to generate a safe zone shadow representation of the incident area and transmitting the safe zone shadow representation to at least one user device in the incident area.

Abstract: A camera flash system and method for the same. In one example, the system includes a camera including an image sensor, a plurality of lights, and an electronic processor. The camera is configured to capture an image frame. Each of the lights is configured to illuminate a region within the image frame. The electronic processor is configured to capture via the camera, while modulating an output of the plurality of lights, a first image frame and determine, using the image sensor, an object of interest within the first image frame. The electronic processor is further configured to identify a region of interest in which the object of interest is located based on the first image frame, identify, based on the region of interest, a subset of lights from the plurality of lights, and activate the subset of lights.

Abstract: Methods and systems of positioning a drone including a camera. One method includes generating, from a first image capture position of the drone, a first image or video having a first field of view. The method further includes determining a plurality of regions of interest, each of the plurality of regions of interest located within a predetermined area and having an associated priority. The method further includes determining a second image capture position different from the first image capture position for the drone as a function of the associated priority and a viewing distance of the camera. The method further includes generating a command for the drone to move to the second image capture position. The method further includes moving the drone based on the command. The method further includes generating, from the second image capture position, a second image or video having a second field of view.

Abstract: Methods and systems of positioning a drone including a camera. One method includes generating, from a first image capture position of the drone, a first image or video having a first field of view. The method further includes determining a plurality of regions of interest, each of the plurality of regions of interest located within a predetermined area and having an associated priority. The method further includes determining a second image capture position different from the first image capture position for the drone as a function of the associated priority and a viewing distance of the camera. The method further includes generating a command for the drone to move to the second image capture position. The method further includes moving the drone based on the command. The method further includes generating, from the second image capture position, a second image or video having a second field of view.

Abstract: Disclosed herein are methods and systems for increasing facial-recognition working range through adaptive super-resolution. One embodiment takes the form of a process that includes calculating one or more video metrics with respect to an input set of video frames. The process also includes obtaining a metric-specific weighting factor for each of the calculated video metrics. The process also includes calculating a weighted sum based on the obtained metric-specific weighting factors and the corresponding calculated video metrics. The process also includes selecting, based at least in part on the calculated weighted sum, a super-resolution technique from among a plurality of super-resolution techniques. The process also includes outputting an indication of the selected super-resolution technique.

Abstract: A method and apparatus for generating a super-resolved image from multiple unsynchronized cameras are provided herein. During operation logic circuitry will receive multiple images from multiple unsynchronized cameras. The logic circuitry will determine a viewshed for each image by extracting time and location information from each received image. Images sharing a similar viewshed will be used to generate a super-resolved image.

Abstract: Disclosed herein are methods and systems for increasing facial-recognition working range through adaptive super-resolution. One embodiment takes the form of a process that includes calculating one or more video metrics with respect to an input set of video frames. The process also includes obtaining a metric-specific weighting factor for each of the calculated video metrics. The process also includes calculating a weighted sum based on the obtained metric-specific weighting factors and the corresponding calculated video metrics. The process also includes selecting, based at least in part on the calculated weighted sum, a super-resolution technique from among a plurality of super-resolution techniques. The process also includes outputting an indication of the selected super-resolution technique.