Traffic flow statistics method, device and equipment and storage medium
A statistical method and technology of traffic flow, applied in the field of transportation, can solve problems such as high algorithm complexity, and achieve the effect of low complexity, little influence of light and weather, and small amount of data
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0037] like figure 1 It is a flow chart of the traffic flow statistics method in Embodiment 1 of the present invention, and this embodiment can be applied to making portable mobile traffic flow monitoring equipment.
[0038] Embodiment 1 steps are as follows:
[0039] S110. Obtain training data, and train the designed convolutional neural network according to the training data to obtain an instantaneous vehicle number estimation model.
[0040] The convolutional neural network designed in this embodiment is used to complete a three-classification function, which can determine the instantaneous number of vehicles in the detection area according to the detection data of the radar in the detection area. Completing this function through the convolutional neural network is compared to The calculation speed of the traditional algorithm is faster and the requirements for the equipment are not high. In order to improve the accuracy of determining the instantaneous vehicle number thro...
Embodiment 2
[0050] Embodiment 2 of the present invention further supplements part of the content on the basis of Embodiment 1, specifically as follows:
[0051] like image 3 As shown, in step S110, the convolutional neural network designed according to the training data training to obtain the instantaneous vehicle number estimation model specifically includes:
[0052] S111. Input the input data in the training data into the designed convolutional neural network to obtain the number of vehicles at the moment of training.
[0053] S112. Comparing the output data in the training data with the training instantaneous vehicle number to obtain an error, and feedback and adjust the convolutional neural network.
[0054] S113. After iteratively performing the above steps for a predetermined number of times, the adjusted convolutional neural network is obtained as the instantaneous vehicle number estimation model.
[0055] Steps S111-113 are the training process of the convolutional neural netw...
Embodiment 3
[0064] Figure 5 A vehicle flow counting device 300 provided in Embodiment 3 of the present invention specifically includes the following modules:
[0065] The model training module 310 is used to acquire training data, and train a designed convolutional neural network according to the training data to obtain an instantaneous vehicle number estimation model.
[0066] The model application module 320 is used to obtain radar monitoring data, and input the radar monitoring data into the instantaneous vehicle number estimation model to obtain the instantaneous vehicle number and determine the driving state of the lane.
[0067] The traffic flow statistics module 330 is configured to judge lane traffic state change information according to the instantaneous vehicle number and lane traffic state, and count traffic flow according to the lane traffic state change information.
[0068] More specifically, the model training module 310 includes:
[0069] a data acquisition unit, config...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


