Unlock instant, AI-driven research and patent intelligence for your innovation.

Intelligent interval shooting of video by reducing bitrate of video to save bandwidth on camera device by means of neural network input

A technology of video frames and video streams, which is applied in the field of computer vision and can solve problems such as data usage

Pending Publication Date: 2022-03-01
AMBARELLA INT LP
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Continuous uploading of data can result in heavy data usage

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Intelligent interval shooting of video by reducing bitrate of video to save bandwidth on camera device by means of neural network input
  • Intelligent interval shooting of video by reducing bitrate of video to save bandwidth on camera device by means of neural network input
  • Intelligent interval shooting of video by reducing bitrate of video to save bandwidth on camera device by means of neural network input

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] Embodiments of the present invention include on the camera device by means of neural network input to provide intelligent interval shooting video by reducing the bit rate of the video to save bandwidth. Embodiments of the present invention can perform the following operations: (i) implement on the edge device Event detection; (ii) implement video encoding on edge devices; (iii) generate smart timelapse videos with varying frame rates based on detected events / objects; (iv) use convolutional neural networks implemented on processors network to detect objects / events; (v) adjust the timelapse frame rate to capture all video frames when an event / object is detected; (vi) perform facial recognition and / or object classification; (vii) integrate encoded smart timelapse Upload videos instead of complete recordings to cloud storage servers; (viii) enable configuration of parameters for uploading videos; (ix) reduce the amount of data being transferred to cloud storage services; (x)...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

An apparatus for enabling the capture of video at bandwidth-saving intervals by reducing the bitrate of the video by means of neural network input on a camera device comprises an interface and a processor. The interface may be configured to receive pixel data generated by a capture device. The processor may be configured to: perform a computer vision operation on a video frame to detect an object; performing classification of the detected object based on a characteristic of the object; determining whether the classification of the object corresponds to an event; generating a complete video stream in response to all the video frames; and generating an encoded video frame. The complete video frame may be recorded to a storage medium local to the device. The encoded video frame may be transmitted to a cloud service. The encoded video frame may include a first sample of the video frame selected at a first rate when the event is not detected and a second sample of the video frame selected at a second rate when the event is detected.

Description

technical field [0001] The present invention relates generally to computer vision, and more particularly to methods and / or apparatus for implementing time-lapse shooting on camera devices with the aid of neural network inputs to save bandwidth by reducing the bit rate of the video video. Background technique [0002] The timelapse video mode for conventional Internet-connected / cloud-enabled cameras is typically implemented by software operating on cloud servers. The software relies on distributed processing resources (ie, scalable computing) using cloud servers. Displays timelapse video clips at a fixed frame rate for a fast-forward effect. For example, video frames are selected at fixed intervals to create a time-lapse video (ie, every thirtieth frame is selected from thirty frames-per-second video to create a time-lapse video). [0003] The internet-connected / cloud-enabled camera encodes the video data and then streams the encoded video to the cloud server. Uses many e...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): H04N7/18H04N5/76H04N5/232H04N21/2743G06N3/04
CPCH04N7/181H04N7/188H04N5/76H04N21/2743H04N23/667G06N3/045H04N19/132H04N19/162H04N19/136H04N19/177G06V20/52G06V20/44G06V10/82H04N19/115H04N19/114H04N19/146G06V20/41
Inventor 汤坚许瑞桉
Owner AMBARELLA INT LP