Safety helmet wearing identification method, system and device
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
An identification method and technology of a safety helmet, applied in the field of image recognition, can solve problems such as low identification accuracy, and achieve the effects of high prediction accuracy, strong anti-noise ability, and good fitting performance.
Pending Publication Date: 2020-09-29
GUANGDONG POWER GRID CO LTD
View PDF4 Cites 5 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0005] The present invention provides a safety helmet wearing recognition method, system and equipment, which are used to solve the problem of low recognition accuracy in the prior art when carrying out safety helmet recognition on power grid construction inspection images collected by drones question
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0050] An embodiment of the present invention provides a safety helmet wearing recognition method, the method is applicable to a pre-trained neural network model and a trained random forest classifier model, the neural network model is a CNN dual-channel model; the method includes the following step:
[0051] In this embodiment, the image of the power transmission line that needs to be inspected is captured by the UAV. After the UAV captures the image of the power grid construction inspection, the image of the power grid construction inspection taken by the UAV is obtained in real time. The power grid construction inspection image is preprocessed, so that the power grid construction inspection image can be input into the neural network model for identification;
[0052] Input the preprocessed power grid construction inspection image into the trained neural network model. The CNN dual-channel in the neural network model recognizes the worker characteristics of the power grid co...
Embodiment 2
[0060] An embodiment of the present invention provides a safety helmet wearing recognition method, the method is applicable to a pre-trained neural network model and a trained random forest classifier model, the neural network model is a CNN dual-channel model; CNN dual-channel The model includes CNNa model and CNNb model. Both CNNa model and CNNb model have a 9-layer network structure, including 5 convolutional layers and 4 fully connected layers, and the last fully connected layer outputs 512 neural units.
[0061] It needs to be further explained that, if figure 2 As shown, the layers 1-5 of CNNa model and CNNb model are CL, and the number of convolution kernels are 96, 256, 384, 384, 256 respectively; the sizes of convolution kernels are 11*11*3, 5*5 respectively *48, 3*3*56, 3*3*192, 3*3*192; the steps of convolution operation are 4, 1, 1, 1, 1 respectively. The fifth layer is the convolutional network layer, the sixth layer, the seventh layer, the eighth layer, and the...
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
Login to view more
Abstract
The invention discloses a helmet wearing identification method, system and device. The method comprises the steps of: obtaining and preprocessing a power grid construction inspection image, and inputting the image into a trained neural network model to obtain the worker features of the power grid construction inspection image; evaluating the worker features, and selecting safety helmet related features; and inputting the safety helmet related features into a trained random forest classifier model to obtain a safety helmet wearing identification result in the power grid construction inspectionimage. According to the embodiment of the invention, the worker features of the power grid construction inspection image are extracted by using a dual-channel CNN data flow, the precision is higher, and the worker features in the image can be identified more accurately; the safety helmet related features are identified by utilizing the random forest classifier model, and the random forest classifier model utilizes the features of high prediction precision, strong anti-noise capability and good fitting performance of a random forest algorithm, so that the wearing condition of the safety helmetcan be accurately identified in the worker features.
Description
technical field [0001] The present invention relates to the field of image recognition, in particular to a safety helmet wearing recognition method, system and equipment. Background technique [0002] The faults of existing power grid lines are mostly caused by natural disasters such as rainfall, strong winds or mudslides. Once a fault occurs, although power inspections in a certain area can be carried out with the help of drones, the maintenance of specific lines still needs to be done manually. The usual power grid environment includes substations, forests, rivers, etc., which have the characteristics of complex environment, high risk level, and many coverings, which makes the background of the image obtained by the UAV complex, and the place where the fault occurs is mostly steep terrain, high mountains and forests. In dense places or where rivers and rivers cross, there is a high possibility of personnel accidents, so it is necessary to accurately identify the maintenanc...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more