Intelligent unmanned photographing method and system based on deep learning

A deep learning and intelligent technology, applied in neural learning methods, TV system components, use feedback control, etc., can solve problems such as far and near not meeting expectations, high labor costs, lack of perception of shooting pictures, etc., to achieve professional shooting effects , the effect of meeting individual needs

Active Publication Date: 2018-03-02
REMO TECH CO LTD
View PDF8 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In this video shooting method, the camera is often fixed. When the lens is fixed, the range of people's activities is limited, and people lack perception of the shooting picture, resulting in peo

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 unmanned photographing method and system based on deep learning
  • Intelligent unmanned photographing method and system based on deep learning
  • Intelligent unmanned photographing method and system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] In order to further understand the features, technical means, and specific objectives and functions achieved by the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0026] An intelligent unmanned photography method based on deep learning includes the following steps:

[0027] S1: Set the camera rack on the control pan / tilt, and turn on the camera to shoot video of the target object. The pan / tilt is an existing well-known pan / tilt, which can drive the camera to rotate in various directions to achieve all-round adjustment of the angle. The camera has an automatic zoom function, which is common knowledge and will not be described in detail here.

[0028] S2: Perceive the target object and obtain the characteristic elements of the target object. The characteristic elements include scene, location, size, distance, behavior and posture. The scene refers to the environment whe...

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

The invention relates to an intelligent unmanned photographing method and system based on deep learning. The intelligent unmanned photographing method based on deep learning comprises the steps of: setting up a camera on a control holder, and turning on the camera to perform video photographing on a target object; perceiving the target object to obtain the characteristic elements of the target object; compositing a picture, and performing deep learning based on a deep neural network on the characteristic elements of the target object, so that composition of the current picture is completed; and, according to the composition condition, sending a control instruction to the holder and the camera, so that the holder moves to an appointed direction, the camera automatically zooms, and the target object is always in a proper position in a shot picture. According to the intelligent unmanned photographing method and system based on deep learning disclosed by the invention, automatic tracking and photographing can be realized; the target object is kept in the optimal position in the current picture; the photographing effect is improved; and thus, the individual requirements of users are satisfied.

Description

Technical field [0001] The invention relates to an intelligent unmanned photography method and system based on deep learning. Background technique [0002] In life, there are often scenes that require a single person to complete video shooting, such as lecture video recording, web live broadcast, dance show, etc. Usually we place the video equipment in a fixed position, and then give lectures in a fixed area in front of the camera. Activities such as live broadcast or dancing. In this video shooting method, the camera is often fixed. When the lens is fixed, people's range of motion is limited, and people also lack perception of the shooting picture, resulting in people's own position in the picture and the distance does not meet expectations. , The shooting effect is relatively poor. If you hire a professional photographer to shoot, the labor cost is very high. Summary of the invention [0003] The technical problem to be solved by the present invention is to provide an intelli...

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): H04N5/232G06N3/08G05D3/12
CPCG05D3/12G06N3/08H04N23/60H04N23/67
Inventor 张明于佳弘刘博杨星彤
Owner REMO TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap