A method for determining the likelihood that a pixel in a video image sequence represents true motion in the image. Light from a scene is captured to yield an original image having a sequence of frames. A prototype image is created from the original image as a geometrically accurate representation of the scene which is substantially free of contamination. A tilt variance-Gaussian mixture model and/or multi-variate Gaussian model, based upon optical turbulence statistics associated with the scene, is developed. Each pixel in the original image sequence of frames is evaluated against the prototype image using a probability density function, to yield a likelihood that the respective pixel represents true motion.

The various implementations described herein include methods, devices, and systems for detecting motion and persons. In one aspect, a method is performed at a smart home system that includes a video camera, a server system, and a client device. The video camera captures video and audio, and wirelessly communicates, via the server system, the captured data to the client device. The server system: (1) receives and stores the captured data from the video camera; (2) determines whether an event has occurred, including detected motion; (3) in accordance with a determination that the event has occurred, identifies video and audio corresponding to the event; and (4) classifies the event. The client device receives information indicative of the identified events, displays a user interface for reviewing the video and audio stored by the remote server system, and displays the at least one classification for the event.

An image processing apparatus includes a reception unit that receives an image signal acquired by an image sensor, an acceptance unit that accepts operation input made by a user for driving a device carrying the image sensor, a calculation unit that calculates a movement amount of the image sensor in an entire angle of view according to the image signal and the operation input, and a correction processing unit that performs a correction process for an image constructed from the image signal, according to the movement amount.

An image stabilization control apparatus comprising: a first receiving unit that receives a translational shake signal that indicates a translational shake in a first direction; a second receiving unit that receives a first rotational shake signal that indicates a rotational shake about a first axis that intersects with the direction of gravity and the first direction; a first calculation unit that finds a first fluctuation range of a gravitational component in the first direction based on the first rotational shake signal; a second calculation unit that finds an amount of shake in the first direction based on the translational shake signal and the first fluctuation range; and a third calculation unit that finds a target value for reducing a shake in the first direction based on the amount of shake found by the second calculation unit.

A method of de-smearing an image includes capturing image data from an imaging sensor and collecting motion data indicative of motion of the sensor while capturing the image data. The motion data is collected at a higher frequency than an exposure frequency at which the image data is captured. The method includes modeling motion of the sensor based on the motion data, wherein motion is modeled at the higher frequency than the exposure frequency. The method also includes modeling optical blur for the image data, modeling noise for the image data, and forming a de-smeared image as a function of the modeled motion, the modeled blur, and the modeled noise, and the image data captured from the imaging sensor.

A method, system, apparatus, and/or device for adjusting or removing frames in a set of frames. The method, system, apparatus, and/or device may include: associating a first frame of a set of frames with motion data that is captured approximately contemporaneously with the first frame; when a sampling rate of the motion data is greater than a frame rate of the set of frames, aggregating a first sample of the motion data captured at the first frame and a second sample of the motion data captured between the first frame and a second frame of the set of frames to obtain a movement value; when the movement value does not exceed a first threshold value, accepting the first frame from the set of frames; and when the movement value exceeds the first threshold value, rejecting the first frame from the set of frames.

An apparatus includes one or more processors and/or circuitry which function as: an object detection unit configured to detect a main object, a first motion detection unit configured to detect a motion vector of the main object, a second motion detection unit configured to detect a movement of an image capturing apparatus, a control unit configured to control a correction unit, and a determination unit configured to determine whether the main object is changed between a first timing when a first image is captured and a second timing when a second image is captured. In a case where the determination unit determines that the main object is changed, the control unit changes a control from image blur correction based on the motion vector of the main object to image blur correction based on the movement of the image capturing apparatus.

The disclosure relates to a method for the noise optimization of a camera, in particular a handheld thermal imaging camera. Images are captured by means of the camera in at least one method step; at least one movement characteristic variable is detected by means of at least one sensor unit of the camera in at least one method step; and image data of captured images is averaged by means of a computing unit of the camera in at least one method step. At least a number of images to be averaged are determined by means of the computing unit of the camera at least on the basis of an intensity of the detected movement characteristic variable, in particular a change rate, in at least one method step.

A method for stabilizing a video sequence comprises: obtaining an indication of camera movement from acquisition of a previous camera frame to acquisition of a current camera frame; determining an orientation for the camera at a time of acquiring the current camera frame; and determining a candidate orientation for a crop frame for the current camera frame by adjusting an orientation of a crop frame associated with the previous camera frame according to the determined orientation. A boundary of one of the camera frame or crop frame is traversed to determine if a specific point on the boundary of the crop frame exceeds a boundary of the camera frame. If so, a rotation of the specific point location which would bring the specific point location onto the boundary of the crop frame is determined and the candidate crop frame orientation updated accordingly before the crop frame is displayed.

An imaging device includes an imaging optical system through which object light flux passes, an image sensor to form the object light flux that has passed through the imaging optical system as an object image, a shake detector to detect shake, a blurred-image correction unit including at least one of the image sensor and an optical element that makes up at least a part of the imaging optical system, a drive circuit to drive the blurred-image correction unit in a direction different from an optical axis of the imaging optical system to move a position on the image sensor at which the object image is formed, to correct a blurred image, and a drive controller to control, based on a current position and a control objective position of the blurred-image correction unit, operation of the blurred-image correction unit by the drive circuit at a constant control cycle.