Vehicle brand identification method and device, and readable storage medium
A vehicle brand and identification method technology, which is applied in the field of devices, readable storage media, and vehicle brand identification methods, can solve the problems of low efficiency of vehicle brand identification, and achieve the effect of improving the efficiency of vehicle brand identification
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
no. 1 example
[0027] Please refer to figure 2 , figure 2 The flow chart of the vehicle brand recognition method provided by the embodiment of the present invention is shown. The vehicle brand recognition method includes the following steps:
[0028] Step S101 , acquire a vehicle picture, input the vehicle picture into a preset convolutional neural network, and use the first network of the convolutional neural network to perform feature extraction to obtain a first feature map.
[0029]In the embodiment of the present invention, the vehicle picture may be a picture containing the front face of the vehicle, and the vehicle picture may include left headlight, right headlight, vehicle logo, left rearview mirror, right rearview mirror, left fog lamp, right fog lamp Areas such as lamps and grilles. The vehicle picture can be captured by the camera 300 in real time, or can be downloaded from the network in advance. The convolutional neural network is used for feature extraction and vehicle b...
no. 2 example
[0066] see Figure 4 , Figure 4 A schematic block diagram of the vehicle brand recognition device 200 provided by the embodiment of the present invention is shown. The vehicle brand recognition device 200 includes a first feature extraction module 201 , an area detection module 202 , a second feature extraction module 203 , an execution module 204 and a brand recognition module 205 .
[0067] The first feature extraction module 201 is configured to obtain a vehicle picture, input the vehicle picture into a preset convolutional neural network, and use the first network of the convolutional neural network to perform feature extraction to obtain a first feature map.
[0068] The area detection module 202 is configured to perform area detection on the first feature map to obtain a first vehicle feature area in the first feature map.
[0069] The second feature extraction module 203 is configured to use the second network of the convolutional neural network to perform secondary ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


