Method and system for identifying illegal hazardous chemicals transport vehicles based on convolutional neural network
A convolutional neural network and transportation vehicle technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as high labor costs, time-consuming, and unrealizable problems, and achieve reduced labor costs and less time-consuming , the effect of improving flexibility and portability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0077] refer to figure 1 , which is a convolutional neural network-based identification method for illegal hazardous chemicals transport vehicles disclosed in the present invention, comprising the following steps:
[0078] S100. Obtain training data, and then perform data standardization processing on the training data. The training data is an initial labeled image library, and the initial labeled image library includes labeled hazardous chemical pictures, hazardous chemical icons, and standard hazardous chemical transport vehicles. examples.
[0079] Wherein, step S100 further includes:
[0080] S110, image grayscale processing: Gaussian blur is performed on the image of the training data to reduce image noise, and then weighted grayscale processing is performed on the R, G, and B channels of the image. In this embodiment, the weights of R, G, and B are respectively selected 0.299, 0.587, 0.114.
[0081] S120. Image edge analysis: use the canny algorithm to detect edges in t...
Embodiment 2
[0120] refer to Image 6 , an illegal hazardous chemicals vehicle identification system based on a convolutional neural network, comprising a first data input processing unit 401, a convolution operation unit 402, a second data input processing unit 403 and a decision output unit 404, wherein the convolution operation unit 402 It is connected to the first data input processing unit 401 , the second data input processing unit 403 is connected to the convolution operation unit 402 , and the decision output unit 404 is connected to the second data input processing unit 403 .
[0121] The first data input processing unit 401 is used for acquiring training data and performing standardization processing on the training data, where the training data is an initial labeled image library.
[0122] The convolution operation unit 402 includes a convolutional neural network calculation model, which is used to perform convolution operations on the processed training data, and obtain the fin...
Embodiment 3
[0127] refer to Figure 7 , is an embodiment of an electronic device provided in the present invention, and the electronic device includes: a processor 501 , and a memory 502 configured to store executable instructions of the processor 501 . Optionally, it may also include: a communication interface 503, configured to communicate with other devices.
[0128] Wherein, the processor 501 is configured to execute the method corresponding to the foregoing method embodiment by executing the executable instruction, and the specific implementation process may refer to the foregoing method embodiment, and details are not repeated here.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


