Retrograde motion judgment method and device based on image recognition, equipment and storage medium
A technology of image recognition and motion direction, which is applied in the field of public services and can solve problems such as errors, false detection alarms, retrograde detection and missed detection, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0066] figure 1 It is a flow chart of an image recognition-based retrograde judgment method provided in Embodiment 1 of the present invention. As shown in the figure, the retrograde judgment method based on image recognition specifically includes:
[0067] Step S101: Acquiring video data of the escalator area in real time.
[0068] The escalator area refers to the area where escalators are installed in public places. Generally speaking, two escalators are installed in an escalator area to transport passengers in two directions. between). Of course, according to the actual passenger transportation needs and the specific design of public places, one escalator area may also be installed with one escalator or more than two escalators, and the two escalators in an escalator area may also run in the same direction. In order to ensure the normal operation of the escalator and avoid equipment failure and stampede incidents caused by disorderly behavior in public places, there are s...
Embodiment 2
[0081] figure 2 It is a flow chart of an image recognition-based retrograde judgment method provided by Embodiment 2 of the present invention. This embodiment is embodied on the basis of the above-mentioned embodiments.
[0082] Specifically, refer to figure 2 , the retrograde judgment method based on image recognition provided in this embodiment specifically includes:
[0083] Step S201: Acquiring video data of the escalator area in real time.
[0084] Step S202: Detect the head region in the video data.
[0085] Specifically, the detection of the head area in the video data needs to detect the head area in each frame of the video data and the head orientation in the head area. The head orientation is detected by a head orientation classifier, and the head orientation classifier is obtained by training the escalator sample image data through a preset convolutional neural network.
[0086] Specifically, the preset convolutional neural network includes sequentially conne...
Embodiment 3
[0109] Figure 4 It is a schematic structural diagram of an image recognition-based retrograde judging device provided in Embodiment 3 of the present invention. refer to Figure 4 , the image recognition-based retrograde judging device includes: a video data acquisition unit 301 , a head region tracking unit 302 , a head number judging unit 303 , a first retrograde judging unit 304 and a second retrograde judging unit 305 .
[0110] Wherein, the video data acquisition unit 301 is used to obtain video data of the escalator area in real time; the head area tracking unit 302 is used to detect the head area in the video data, and perform target tracking on the head area to obtain the head area. direction of movement; the head number judging unit 303, configured to confirm whether the number of the head regions is greater than a preset threshold; the first retrograde judging unit 304, used to determine if the number of the head regions is greater than a preset threshold value, ac...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com