Elevator scene recognition method and device, electronic equipment and storage medium

A scene recognition and elevator technology, applied in the computer field, can solve problems such as inability to obtain accurate recognition effects, only recognize specific abnormal scenes, and fail to realize full scene recognition and monitoring, so as to achieve accurate recognition effects and reduce recognition errors.

Pending Publication Date: 2022-05-20
SHENZHEN XUMI YUNTU SPACE TECH CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the embodiments of the present disclosure provide an elevator scene recognition method, device, electronic equipment, and storage medium to solve the problems in the prior art that accurate recognition effects cannot be obtained, only specific abnormal scenes can be recognized, and full recognition cannot be realized. Problems with Scene Recognition and Monitoring

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
  • Elevator scene recognition method and device, electronic equipment and storage medium
  • Elevator scene recognition method and device, electronic equipment and storage medium
  • Elevator scene recognition method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system structures and techniques are presented for a thorough understanding of the embodiments of the present disclosure. It will be apparent, however, to one skilled in the art that the present disclosure may be practiced in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present disclosure with unnecessary detail.

[0018] The elevator scene recognition task refers to the real-time analysis of the video stream captured by the elevator camera, identification of the elevator running status, and timely response to the abnormal situation of the elevator. In the automatic identification and monitoring tasks of elevator scenes, due to the high information complexity, intra-class diversity and inter-class ...

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 provides an elevator scene recognition method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring video clips obtained by segmenting a video stream according to a preset time length, inputting the video clips into an elevator scene recognition model, and performing feature extraction on the video clips by using an action recognition deep network; using a first feature extraction channel to extract the spatial dimension features to obtain a first feature map, using a second feature extraction channel to extract the time dimension features to obtain a second feature map, and using a third feature extraction channel to fuse the spatial dimension features and the time dimension features to obtain a third feature map; and performing global average pooling and feature splicing on the first feature map, the second feature map and the third feature map, predicting the feature map obtained after feature splicing, and determining an elevator scene corresponding to the video clip according to a prediction result. The elevator scene can be accurately recognized, and full-scene recognition and monitoring of the elevator are achieved.

Description

technical field [0001] The present disclosure relates to the field of computer technology, and in particular to an elevator scene recognition method, device, electronic equipment and storage medium. Background technique [0002] With the development of computer technology and multimedia technology, the use of video for scene monitoring is more and more widely used. For example, by monitoring the scene in the elevator, abnormal situations can be found and responded in time. [0003] In the prior art, using a traditional video monitoring system requires manual real-time monitoring of the monitoring video, which is prone to misjudgment and missed judgment. Although some artificial intelligence algorithms based on computer vision can recognize behaviors in videos, in the process of elevator scene recognition, due to the high information complexity and intra-class diversity of the elevator scene and passenger actions that need to be recognized and inter-class similarity, which p...

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): G06V20/40G06V40/20G06V20/52G06V10/82G06N3/04G06N3/08
CPCG06N3/08G06N3/048G06N3/045
Inventor 杨战波黄泽元祁晓婷蒋召
Owner SHENZHEN XUMI YUNTU SPACE 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