A method of generating a segmentation outcome which indicates individual instances of one or more object classes for an image in a sequence of images is disclosed. The method comprises: determining (501) a coherent region of the image; processing (502) the image to determine a tensor representing pixel-specific confidence scores; generating (503) a series of temporary segmentation masks for the coherent region, wherein each temporary segmentation mask is generated by interpreting the tensor with respect to a single object class using a different temporary confidence score threshold; evaluating (504) the series of temporary segmentation masks to determine if an object mask condition is met; depending on the outcome of the evaluation, setting (505) the temporary confidence score threshold as a final confidence score threshold for the pixels of the temporary segmentation mask, or setting (505) a default confidence score threshold as a final confidence score threshold for the coherent region; and generating (506) a final segmentation outcome for the image.

Systems, methods, and apparatus for identifying, tracking, and disrupting UAVs are described herein. A tracking system can include one or more first computing devices that receive sensor data associated with an object in a particular airspace from one or more sensors. The first computing device can analyze the sensor data relating to the object to determine information about the object. A portable countermeasure device can include one or more second computing devices. The second computing device can receive the information relating to the object. The second computing device can display a visual indicator indicating the information on a display.

Systems, methods, and apparatus for identifying and tracking UAVs including a plurality of sensors operatively connected over a network to a configuration of software and/or hardware. A computing device can tune the RF receiver to a particular frequency set. The computing device can receive RF signal data corresponding to a plurality of RF signals via the RF receiver. The computing device can detect a plurality of signal characteristics corresponding to the plurality of RF signals from the RF signal data. The computing device can identify a matching RF signal by comparing the RF signal data to a plurality of known RF signals. The computing device can apply a predetermined rule set to the matching RF signal to determine at least one action to take.

Systems, methods, and apparatus for detecting UAVs in an RF environment are disclosed. An apparatus is constructed and configured for network communication with at least one camera. The at least one camera captures images of the RF environment and transmits video data to the apparatus. The apparatus receives RF data and generates FFT data based on the RF data, identifies at least one signal based on a first derivative and a second derivative of the FFT data, measures a direction from which the at least one signal is transmitted, analyzes the video data. The apparatus then identifies at least one UAV to which the at least one signal is related based on the analyzed video data, the RF data, and the direction from which the at least one signal is transmitted, and controls the at least one camera based on the analyzed video data.

Techniques for augmenting a reality captured by an image capture device are disclosed. In one example, a system includes an image capture device that generates a two-dimensional frame at a local pose. The system further includes a computation engine executing on one or more processors that queries, based on an estimated pose prior, a reference database of three-dimensional mapping information to obtain an estimated view of the three-dimensional mapping information at the estimated pose prior. The computation engine processes the estimated view at the estimated pose prior to generate semantically segmented sub-views of the estimated view. The computation engine correlates, based on at least one of the semantically segmented sub-views of the estimated view, the estimated view to the two-dimensional frame. Based on the correlation, the computation engine generates and outputs data for augmenting a reality represented in at least one frame captured by the image capture device.

A remote-controlled weapon system, mounted in a moving platform, includes at least one processor that implements: a first posture calculator that calculates a first pixel movement amount corresponding to a posture change amount of a camera during a time interval between a first image and a second image, received after the first image; a second posture calculator that calculates a second pixel movement amount corresponding to a control command for changing a posture of the camera to match a moving target, detected from the second image, with an aiming point; and a region of interest (ROI) controller that calculates a third pixel movement amount corresponding to vibration of the camera based on the first pixel movement amount and the second pixel movement amount, and estimate a location of an ROI that is to be set on the moving target of the second image, based on the third pixel movement amount.

Systems, methods, and computer program products for identifying hostile fire. A characteristic of a fired projectile is detected using an optical system and the projectile's travel path in relation to a vehicle is determined. If the determined travel path of the projectile is within a predetermined distance from the vehicle, it is determined that the projectile is hostile towards the vehicle and a warning is output.

For automated detection and tracking of multiple targets, an apparatus, method, and program product are disclosed. The apparatus includes a camera that captures video data and a processor that compensates for camera motion in the video data, processes the compensated video data to remove noise and spurious returns, detects one or more targets within the processed video data, and identifies target information for each target in the processed video data.

A shot detection system can include a shooting target that is made of paper and printed to include fiducials, borders and a bar code together with a scoring region and markings. A method of camera adjustment control can find and lock onto a target. A target acquisition procedure can include extracting a region of interest (image of the shooting target), calibrating the region of interest and then target locking. The real-time target locking procedure can include correcting an image of the region of interest to account for tilt, rotation and skew. A methodology of shot detection can include acquiring probable and confirming shot candidates and then verifying the probably shot candidate with the confirming shot candidates to substantially eliminate falsely identified shots candidates, thereby significantly improving performance and experience.

Various embodiments associated with a composite image are described. In one embodiment, a handheld device comprises a launch component configured to cause a launch of a projectile. The projectile is configured to capture a plurality of images. Individual images of the plurality of images are of different segments of an area. The system also comprises an image stitch component configured to stitch the plurality of images into a composite image. The composite image is of a higher resolution than a resolution of individual images of the plurality of images.