Vehicle information identification method and device
A vehicle information and vehicle technology, which is applied in the field of information identification, can solve the problem of single vehicle parameter identification, and achieve the effects of saving running time and running memory, high recognition accuracy, and improved recognition rate
Active Publication Date: 2019-10-22
NEUSOFT CORP
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] Therefore, the vehicle information identification in the related art has the problem of simplification of vehicle parameter identification
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0073] Specific embodiments of the present disclosure will be described in detail below in conjunction with the accompanying drawings. It should be understood that the specific embodiments described here are only used to illustrate and explain the present disclosure, and are not intended to limit the present disclosure.
[0074] see figure 1 , is a block diagram of a vehicle information recognition system according to an embodiment of the present disclosure. The system 100 includes: an image acquisition device 100 and a vehicle information recognition device 101 . In the embodiment of the present disclosure, the vehicle information includes: the model and body color of the vehicle.
[0075] In the embodiment of the present disclosure, the image acquisition device 100 is used for acquiring vehicle images. The image acquisition device 100 may be a camera, camera, etc. installed at an intersection, a checkpoint, or a specific acquisition location. Thus, the image capture devic...
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 present disclosure relates to a vehicle information identification method and device. The method includes: obtaining a training sample set, which includes a preset number of training samples; For training, the preset optimization goal is to minimize or converge the weighted sum of the loss function corresponding to the vehicle model and the loss function corresponding to the body color; when the training result meets the preset optimization goal, save the parameter information of the deep convolutional neural network; obtain the parameters including The target image data of the vehicle to be recognized; the target image data is input into the deep convolutional neural network constructed by parameter information, and the model and body color of the vehicle to be recognized are recognized. The disclosure can simultaneously identify two targets of vehicle type and body color, and the identification accuracy is high; a deep convolutional neural network is used to classify the two attributes, which improves the identification efficiency while improving the identification rate, and saves running time and Run memory.
Description
technical field [0001] The present disclosure relates to the technical field of information identification, and in particular, to a vehicle information identification method and device. Background technique [0002] With the rapid development of the modern economy, the number and types of vehicles are increasing day by day, and traffic supervision is facing great challenges. Due to the complex and diverse appearance of vehicles, which are affected by factors such as background, lighting, and viewing angles, it is very difficult to identify vehicle information, and the accuracy is difficult to guarantee. [0003] In the related art, when performing vehicle identification based on machine learning, it is mainly to use a classifier to identify a single target of vehicle information, for example, to identify only the model of the vehicle, or to identify the decision boundary or verify the vehicle and non-vehicle through learning. Generated vehicle candidate regions, etc. [00...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06V20/584G06V2201/08G06N3/045
Inventor 邹博邹达李昕
Owner NEUSOFT CORP