# US 10,372,995 B2 · System and method for previewing video

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 10,372,995 B2
- Document ID: US10372995B2
- Status: Granted
- Kind: B2
- Application number: 15/092,557
- Filed: 2016-04-06
- Published: 2017-07-13
- Granted: 2019-08-06
- Earliest claimed: 2016-01-12
- Assignees: Shanghai Xiaoyi Technology Co., Ltd.
- Applicants: Shanghai Xiaoyi Technology Co., Ltd.
- Inventors: Junfeng Zhang; Lili Zhao; Feng Li
- Web page: https://patentgrep.com/patent/US10372995B2

## CPC

- G06V 20/47: {Detecting features for summarising video content}
- G06F 16/739: {in form of a video summary, e.g. the video summary being a video sequence, a composite still image or having synthesized frames}
- G08B 13/19669: {Event triggers storage or change of storage policy}
- G11B 27/031: Electronic editing of digitised analogue information signals, e.g. audio or video signals
- H04N 7/188: {Capturing isolated or intermittent images triggered by the occurrence of a predetermined event, e.g. an object reaching a predetermined position (signal generation from motion picture films H04N5/253)}
- G06V 20/44: {Event detection}
- G08B 13/19695: {Arrangements wherein non-video detectors start video recording or forwarding but do not generate an alarm themselves}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G11B: INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER (recording measured values in a way that does not require playback through a transducer G01D9/00; recording or playback apparatus using mechanically marked tape, e.g. punched paper tape, or using unit records, e.g. punched or magnetically marked cards G06K; transferring data from one type of record carrier to another G06K1/18; circuits for coupling output of reproducer to radio receiver H04B1/20; gramophone pick-ups or like acoustic electromechanical transducers or circuits therefor H04R)
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

A device for previewing a video includes a memory device configured to store instructions, and one or more processors configured to execute the instructions to receive a video captured by a camera and analyze the video. The one or more processors are also configured to detect a special event from the analysis of the video. The special event includes at least one of an object, a moving object, or a sound detected in the video. The one or more processors are further configured to extract, from the video, at least one of a video preview frame or audio segment corresponding to the special event, and generate a preview video including the at least one of the video preview frame or audio segment corresponding to the special event.

## Claims

### Claim 1

A device for previewing a video, the device comprising:
a memory device configured to store instructions; and
one or more processors configured to execute the instructions to:
receive the video captured by a camera, wherein the camera includes an image sensor, a sound sensor, and a motion sensor including an ultrasonic sensor;
obtain information relating to a potential special event detected by the camera, wherein the information relating to the potential special event is obtained by at least one of the motion sensor or the sound sensor, the ultrasonic sensor configured to emit ultrasonic signals to detect an object within a vicinity of the camera based on reflected ultrasonic signals and the motion sensor configured to generate a signal indicating that the object is present, the sound sensor configured to generate a signal if the sounds sensor detects an ambient sound level exceeding a threshold, wherein a processor of the camera is responsive to the signal generated by the motion sensor or the sound sensor to instruct the image sensor to start capturing the video;
analyze the captured video;
detect a special event from the analysis of the video by comparing an identified feature with one or more object, motion, or sound models previously constructed, the special event including at least one of an object, a moving object, or a sound detected in the video;
extract, from the video, at least a first video preview frame or audio segment corresponding to the special event based on information relating to the potential special event, wherein the one or more processors are further configured to skip frames before extracting a second video preview frame or audio segment, depending on whether the special event is detected in the first video preview frame or audio segment, wherein the skipped frames correspond to a time period selected by the one or more processors for skipping frames, a length of the time period being selected based on whether the special event is detected in a previous time period; and
generate a preview video including the at least first video preview frame or audio segment corresponding to the special event.

### Claim 2 (depends on 1)

The device of claim 1, wherein the one or more processors are further configured to execute the instructions to transmit the preview video to a user.

### Claim 3 (depends on 1)

The device of claim 1, wherein the special event is a first special event, the one or more processors being further configured to execute the instructions to:
detect a second special event from the analysis of the video, the second special event including at least one of an object, a moving object, or a sound detected in the video; and
extract, from the video, at least one of a video preview frame or audio segment corresponding to the second special event, wherein the preview video further includes the at least one of the video preview frame or audio segment corresponding to the second special event.

### Claim 4 (depends on 1)

The device of claim 1, wherein the video is a first video and the special event is a first special event, the one or more processors being further configured to execute the instructions to:
receive a second video captured by the camera;
analyze the second video;
detect a second special event from the analysis of the second video, the second special event including at least one of an object, a moving object, or a sound detected in the second video; and
extract, from the second video, at least one of a video preview frame or audio segment corresponding to the second special event, wherein the preview video further includes the at least one of the video preview frame or audio segment corresponding to the second special event.

### Claim 5 (depends on 3)

The device of claim 3, wherein the one or more processors are further configured to execute the instructions to:
receive another video captured by the camera;
analyze the another video;
detect a third special event from the analysis of the another video, the third special event including at least one of an object, a moving object, or a sound detected in the another video; and
extract, from the another video, at least one of a video preview frame or audio segment corresponding to the third special event, wherein the preview video further includes the at least one of the video preview frame or audio segment corresponding to the third special event.

### Claim 6

A system for previewing a video, the system comprising:
a camera including an image sensor, a sound sensor, a motion sensor including an ultrasonic sensor, and a first processor, the camera configured to:
emit ultrasonic signals, by the ultrasonic sensor, to detect an object within a vicinity of the camera;
detect at least one of an object, by the motion sensor, based on reflected ultrasonic signals or an ambient sound, by the sound sensor, that exceeds a threshold;
generate a signal by the motion sensor indicating that the object is present or a signal by the sound sensor indicating the ambient sound exceeds the threshold;
transmit the signal generated by the motion sensor or the sound sensor to the first processor;
receive an instruction, from the first processor responsive to the signal generated by the motion sensor or the sound sensor, to start capturing a video;
capture, by the image and sound sensors, the video,
transmit a request for uploading the video,
receive a response including an address for uploading the video, and upload the video; and
a processing server including a second processor, the processing server configured to:
receive the video,
analyze the video,
detect a special event from the analysis of the video by comparing an identified feature with one or more object, motion, or sound models previously constructed, the special event including at least one of an object, a moving object, or a sound detected in the video,
extract, from the video, at least a first video preview frame or audio segment corresponding to the special event, wherein the processing server is further configured to skip frames before extracting a second video preview frame or audio segment, depending on whether the special event is detected in the first video preview frame or audio segment, wherein the skipped frames correspond to a time period selected by the processing server for skipping frames, a length of the time period being selected based on whether the special event is detected in a previous time period, and
generate a preview video including the at least first video preview frame or audio segment corresponding to the special event.

### Claim 7 (depends on 6)

The system of claim 6, further comprising a distributing server, including a third processor, the distributing server configured to:
receive, from the camera, the request for uploading the first video, and
generate, in response to the request, the response including the address for uploading the video, wherein
the camera is further configured to upload the video to the address included in the response, and
the processing server is further configured to receive the video from the address to which the first video is uploaded.

### Claim 8 (depends on 6)

The system of claim 6, wherein the camera is further configured to:
receive a signal indicating the potential special event including at least one of a potential object, a potential moving object, or a potential sound; and
capture the video including the potential special event.

### Claim 9 (depends on 8)

The system of claim 8, wherein:
the camera is further configured to:
obtain information relating to the potential special event, and
transmit, to the processing server, the information relating to the potential special event; and
the processing server is further configured to:
receive the information relating to the potential special event, and
detect the special event based, at least in part, on the information relating to the potential special event.

### Claim 10 (depends on 6)

The system of claim 6, wherein the special event is a first special event, and the processing server is further configured:
detect a second special event from the analysis of the video, the second special event including at least one of an object, a moving object, or a sound detected in the video; and
extract, from the video, at least one of a video preview frame or audio segment corresponding to the second special event, wherein the preview video further includes the at least one of the video preview frame or audio segment corresponding to the second special event.

### Claim 11

A method for previewing a video, the method comprising:
receiving the video captured by a camera, wherein the camera includes an image sensor, a sound sensor, and a motion sensor including an ultrasonic sensor;
obtaining information relating to a potential special event detected by the camera, wherein the information relating to the potential special event is obtained by at least one of the motion sensor or the sound sensor, the ultrasonic sensor configured to emit ultrasonic signals to detect an object within a vicinity of the camera based on reflected ultrasonic signals and the motion sensor configured to generate a signal indicating that the object is present, the sound sensor configured to generate a signal if the sounds sensor detects an ambient sound level exceeding a threshold, wherein a processor of the camera is responsive to the signal generated by the motion sensor or the sound sensor to instruct the image sensor to start capturing the video;
analyzing the captured video;
detecting a special event from the analysis of the video by comparing an identified feature with one or more object, motion, or sound models previously constructed, the special event including at least one of an object, a moving object, or a sound detected in the video;
extracting, from the video, at least a first video preview frame or audio segment corresponding to the special event based on information relating to the potential special event, and skipping frames before extracting a second video preview frame or audio segment, depending on whether the special event is detected in the first video preview frame or audio segment, wherein the skipped frames correspond to a time period selected for skipping frames, a length of the time period being selected based on whether the special event is detected in a previous time period; and
generating a preview video including the at least first video preview frame or audio segment corresponding to the special event.

### Claim 12 (depends on 11)

The method of claim 11, further comprising transmitting the preview video to a user.

### Claim 13 (depends on 11)

The method of claim 11, wherein the special event is a first special event, the method further comprising:
detecting a second special event from the analysis of the video, the second special event including at least one of an object, a moving object, or a sound detected in the video; and
extracting, from the video, at least one of a video preview frame or audio segment corresponding to the second special event, wherein the preview video further includes the at least one of the video preview frame or audio segment corresponding to the second special event.

### Claim 14 (depends on 11)

The method of claim 11, wherein the video is a first video and the special event is a first special event, the method further comprising:
receiving a second video captured by the camera;
analyzing the second video;
detecting a second special event from the analysis of the second video, the second special event including at least one of an object, a moving object, or a sound detected in the second video; and
extracting, from the second video, at least one of a video preview frame or audio segment corresponding to the second special event, wherein the preview video further includes the at least one of the video preview frame or audio segment corresponding to the second special event.

### Claim 15 (depends on 13)

The method of claim 13, further comprising:
receiving another video captured by the camera;
analyzing the another video;
detecting a third special event from the analysis of the another video, the third special event including at least one of an object, a moving object, or a sound detected in the another video; and
extracting, from the another video, at least one of a video preview frame or audio segment corresponding to the third special event, wherein the preview video further includes the at least one of the video preview frame or audio segment corresponding to the third special event.

### Claim 16

A method for previewing a video, the method comprising:
emitting ultrasonic signals, by an ultrasonic sensor, to detect an object within a vicinity of a camera, wherein the camera includes an image sensor, a sound sensor, a motion sensor including the ultrasonic sensor, and a camera processor;
at least one of detecting an object based on reflected ultrasonic signals or detecting by the sound sensor if an ambient sound level exceeds a threshold;
at least one of generating a signal, by the motion sensor, indicating that the object is present or generating a signal, by the sound sensor, indicating the ambient sound level exceeds the threshold;
receiving an instruction, from the camera processor responsive to the signal generated by the motion sensor or the sound sensor, to start capturing the video by the image sensor and the sound sensor;
capturing, by the camera, the video;
transmitting, by the camera, a request for uploading the video;
receiving, by the camera, a response including an address for uploading the video;
transmitting, by the camera, the video to the address included in the response;
receiving, by a processing server, the video;
analyzing, by the processing server, the video;
detecting, by the processing server, a special event from the analysis of the video by comparing an identified feature with one or more object, motion, or sound models previously constructed, the special event including at least one of an object, a moving object, or a sound detected in the video;
extracting, by the processing server, from the video at least a first video preview frame or audio segment corresponding to the special event, wherein the processing server is further configured to skip frames before extracting a second video preview frame or audio segment, depending on whether the special event is detected in the first video preview frame or audio segment, wherein the skipped frames correspond to a time period selected by the processing server for skipping frames, a length of the time period being selected based on whether the special event is detected in a previous time period; and
generating, by the processing server, a preview video including the at least first video preview frame or audio segment corresponding to the special event.

### Claim 17 (depends on 16)

The method of claim 16, further comprising:
receiving, by a distributing server from the camera, the request for uploading the video, and
generating, by the distributing server, the response including the address for uploading the video, wherein
the camera uploads the video to the address included in the response, and
the processing server receives the video from the address to which the video is uploaded.

### Claim 18 (depends on 16)

The method of claim 16, further comprising:
receiving, by the camera, a signal indicating the potential special event including at least one of a potential object, a potential moving object, or a potential sound; and
capturing, by the camera, the video including the potential special event.

### Claim 19 (depends on 18)

The method of claim 18, further comprising:
obtaining, by the camera, information relating to the potential special event;
transmitting, from the camera to the processing server, the information relating to the potential special event;
receiving, by the processing server, the information relating to the potential special event; and
detecting, by the processing server, the special event based, at least in part, on the information relating to the potential special event.

### Claim 20

A non-transitory computer readable medium embodying a computer program product, the computer program product comprising instructions configured to cause a computing device to:
receive the video captured by a camera, wherein the camera includes an image sensor, a sound sensor, and a motion sensor including an ultrasonic sensor;
obtain information relating to a potential special event detected by the camera, wherein the information relating to the potential special event is obtained by at least one of the motion sensor or the sound sensor, the ultrasonic sensor configured to emit ultrasonic signals to detect an object within a vicinity of the camera based on reflected ultrasonic signals and the motion sensor configured to generate a signal indicating that the object is present, the sound sensor configured to generate a signal if the sounds sensor detects an ambient sound level exceeding a threshold, wherein a processor of the camera is responsive to the signal generated by the motion sensor or the sound sensor to instruct the image sensor to start capturing the video;
analyze the captured video;
detect a special event from the analysis of the video by comparing an identified feature with one or more object, motion, or sound models previously constructed, the special event including at least one of an object, a moving object, or a sound detected in the video;
extract, from the video, at least a first video preview frame or audio segment corresponding to the special event based on information relating to the potential special event, wherein the instructions further cause the computing device to skip frames before extracting a second video preview frame or audio segment, depending on whether the special event is detected in the first video preview frame or audio segment, wherein the skipped frames correspond to a time period selected for skipping frames, a length of the time period being selected based on whether the special event is detected in a previous time period; and
generate a preview video including the at least first video preview frame or audio segment corresponding to the special event.