Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for adjusting of video analytics rules for camera movement. The methods, systems, and apparatus include actions of obtaining a rule that specifies a first set of coordinates applied to a first set of images from a camera, determining an amount and direction of movement of the camera after the rule was obtained, determining, based on the amount and direction of movement of the camera, a second set of coordinates applied to a second set of images captured after the camera moved.

The present disclosure provides a video jitter detection method and an apparatus. The video jitter detection method includes: acquiring a video; inputting the video into a detection model to obtain an evaluation value of the video, where the evaluation value is used to indicate a degree of jitter of the video; where the detection model is a model obtained by training using video samples in a video sample set as inputs and evaluation values of the video samples in the video sample set as outputs. By inputting the video to be detected into the detection model, the evaluation value of the video can be acquired through the detection model, thereby whether the video is jittery is determined, which realizes the video jitter detection end-to-end, and improves the detection accuracy and robustness of video jitter.

Provided is a video recording system (10) configured for capturing an object (5) moving along a path (1) including numerous path sections (2, 3, 4). The video recording system (10) includes a first camera (11) operable to capture the object (5) while moving along a first path section (2) of the path (1), a second camera (12) operable to capture the object (5) moving along a second path section (3) of the path (1), and an acquisition unit (31) connected to the first camera (11) and connected to the second camera (12), the acquisition unit (31) being operable to capture a first video stream (51) from the first camera (11) during a first time interval and to capture a second video stream (51′) from the second camera (12) during a second time interval.

Optical flow information is determined and used to identify a video clip from among a sequence of frames. The video clip may be identified based on motion features derived in part from the optical flow information. In some embodiments, semantic information is concatenated with the motion features derived from the optical flow information.

An apparatus includes at least one memory configured to store instructions, and at least one processor in communication with the at least one memory and configured to execute the instructions to perform same area dividing on each of a plurality of images, and create a composite image from the plurality of images. A first area of the composite image is composited from corresponding areas in a first number of image among the plurality of images. A second area of the composite image is composited from corresponding areas in a second number of image among the plurality of images.

An electronic device and a controlling method thereof are provided. The electronic device includes a memory, a first camera including a first image sensor and at least one processor, and the at least one processor obtains a plurality of image frames by photographing surroundings of the electronic device through the first camera, sets a region of interest (ROI) on the plurality of image frames, obtains a motion identification map corresponding to each of the plurality of image frames and select at least one image frame from among the plurality of image frames based on the obtained motion identification map, identifies whether there is a motion of an object on the ROI set on the selected at least one image frame, and performs a Super Slow Motion (SSM) function through the first camera based on a result of the identification.

The present disclosure discloses an object detection method used in an object detection apparatus that includes the steps outlined below. An image signal received from an image sensor is detected to generate an image detection signal when an image variation is detected. An infrared signal received from an infrared sensor is detected to generate an infrared detection signal when an infrared energy variation is detected. A time counting process is initialized when the image detection signal is generated. An object detection signal is generated when the infrared detection signal is generated within a predetermined time period after the time counting process is initialized. A detection distance of the image sensor is larger than a detection distance of the infrared sensor.

An autofocus (AF) frame integration unit generates at least two groups, each group including at least one focus detection area based on a comparison between a plurality of focus detection results, the plurality of focus detection results to be obtained corresponding to a specific time. A movement determination unit determines whether an object corresponding to a first group and a second group is moving, based on a focus detection result corresponding to the first group, generated based on a focus detection result corresponding to a first time, and a focus detection result corresponding to the second group, generated based on a focus detection result corresponding to a second time later than the first time.

A method is disclosed for improving the quality of photographs taken in low-light conditions by adjustment of shutter speed and digital gain based on a shutter prioritization value. Using a network of sensor, a digital camera processes various parameters, such as light level of the scene and movement of the camera or of subjects within the scene, to compute a shutter prioritization value. The value is then used to select the most appropriate shutter speed and digital gain combination from a constant exposure curve. Higher prioritization values correspond to faster shutter speeds and higher digital gain. Lower prioritization values correspond to lower shutter speeds and lower digital gain. In further embodiments, the shutter prioritization value may be manually customized by a user in order to produce artistic effects.

The disclosure includes a method for using a doorbell system to detect a presence of a visitor. The doorbell system can comprise a doorbell having a speaker, a microphone, a camera, and a button. The method can include detecting, by the doorbell system, the presence of the visitor while the visitor is located outside a building to which the doorbell is attached. The building can include a door having a lock that is configured to fasten the door to inhibit unauthorized entry into the building. In response to detecting the presence of the visitor, the method can include the step of actuating, by the doorbell system, a first appliance associated with the building.