Lightweight safety helmet detection method and system for mobile terminal
A mobile terminal and detection method technology, applied in the field of helmet detection, can solve the problems of model loss calculation and convergence, complex network structure, large amount of parameters, etc., and achieve the effect of reducing the amount of model parameters, simple network structure, and outstanding superiority.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0060] This embodiment provides a lightweight helmet detection method for a mobile terminal, including:
[0061] Obtain relevant image information;
[0062] According to the obtained relevant image information and the preset helmet detection model, the detection result of the helmet is obtained;
[0063] Among them, the hard hat detection model is obtained by improving the residual network of Darknet53 in the YOLOv3 network, specifically: according to the CspNet network architecture, the number of channels is divided into two parts, the first part and the second part, and the first part does not make any rolls. Product operation; the second part performs two convolution and Concat operations, and superimposes the feature map after the convolution operation with the second part, and concats the superimposed feature map with the first part.
[0064] Specifically, in this embodiment, the helmet detection includes the following steps:
[0065] S1: Make model training data sets a...
Embodiment 2
[0124] In this embodiment, the experimental rendering based on the pytorch framework includes the following steps:
[0125] In this embodiment, image twisting and random rotation operations are performed on the data set used for feature enhancement; the data set is a data set of 7950 hard hats, and the data set comes from network downloads, real shots on the construction site, and open source data marked by others Set, the dataset is marked as two categories, when a helmet is detected, it is displayed as hat; when no helmet is detected, it is displayed as hanger. At the same time, the data set is converted into a data format that yolo can easily handle. The main operation is: for the open source data set downloaded from the network, convert the txt label format into XML format; Save tag types in XML format.
[0126] After preprocessing the data set, the virtual environment is built. The present invention mainly builds a virtual environment through anaconda and names it torch,...
Embodiment 3
[0131] This embodiment provides a lightweight helmet detection system for a mobile terminal, including an acquisition module and a detection module;
[0132] The acquisition module is configured to: acquire relevant image information;
[0133] The detection module is configured to: obtain the detection result of the helmet according to the obtained related image information and the preset helmet detection model;
[0134] Among them, the hard hat detection model is obtained by improving the residual network of Darknet53 in the YOLOv3 network, specifically: according to the CspNet network architecture, the number of channels is divided into two parts, the first part and the second part, and the first part does not make any rolls. Product operation; the second part performs two convolution and Concat operations, and superimposes the feature map after the convolution operation with the second part, and concats the superimposed feature map with the first part.
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