Deep neural network for fine recognition of vehicle attributes and training method thereof
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology of deep neural network and training method, applied in the direction of neural learning method, biological neural network model, kernel method, etc., can solve the problems of single vehicle perspective, simple deep network, cumbersome process, etc., to improve the recognition time, and the framework is simple and elegant , the effect of improving the accuracy rate
Inactive Publication Date: 2018-09-18
SUN YAT SEN UNIV
View PDF10 Cites 51 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
[0008] However, the above-mentioned Chinese patent applications with publication numbers 105678275A, 105787466A, 103500327A, and 105930812A mainly use some low-level features on statistics and gradients to characterize the type of vehicle, and do not use high-level semantic features; publication numbers are 105678275A, 105787466A, The Chinese patent applications 102737221B and 103544480A have data preprocessing or result postprocessing
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
[0060] Example 1: The implementation of a VGG16-based method for identifying various refined attributes of vehicles includes four stages: data preparation, environment configuration, model training, and model testing.
[0061] 1.1 Data preparation stage:
[0062] In this embodiment, non-consistent data training is performed on several different datasets: dataset A has 160,000 pictures, and the attributes marked include car type, brand, and sub-brand; dataset B has 25,000 images of monitoring perspectives For car pictures, the marked attributes include car type, brand, and sub-brand; Dataset C has 15,000 car pictures from monitoring perspectives, and the marked attributes are colors; Dataset D has 26,000 surveillance perspective pictures, and the marked attributes are viewing angles. Dataset A is high-definition car pictures, such as image 3 As shown, the data set BCD is a car picture from a monitoring perspective, such as Figure 4 shown.
[0063] 1.2 Environment preparati...
Embodiment 2
[0083] Example 2: The implementation of ResNet-101-based multiple refined attribute recognition methods for vehicles includes four stages: data preparation, environment configuration, model training and model testing:
[0084] 2.1 Data preparation stage.
[0085] The present invention performs non-uniform data training on several different data sets. Dataset A has 160,000 pictures, and the marked attributes include car type, brand, and sub-brand; Dataset B has 25,000 car pictures from surveillance perspectives, and the marked attributes include car type, brand, and sub-brand; A picture of a car from a monitoring perspective, the marked attribute has a color; Dataset D has 26,000 pictures from a monitoring perspective, and the marked attribute has a viewing angle. Dataset A is high-definition car pictures, such as image 3 As shown, the data set BCD is a car picture from a monitoring perspective, such as Figure 4 shown.
[0086] 2.2 Environmental preparation stage.
[008...
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 deep neural network for the fine recognition of vehicle attributes and a training method thereof. The network comprises a depth residual network, a feature migration layer, aplurality of all-connection layers, a plurality of loss calculation units, and a plurality of parameter updating units. The depth residual network is used for carrying out feature extraction on an input image to obtain a feature image. The feature migration layer comprises a plurality of feature migration units and is used for enabling each of all feature migration units to be adapted to specifictasks according to the features shared by all attribute identifying tasks. The plurality of all-connection layers correspond to the branches of all attribute identifying tasks and are connected withthe feature migration layer so as to obtain feature vectors corresponding to all attribute identifying tasks. The plurality of loss calculation units correspond to the branches of all attribute identifying tasks and are respectively connected with the all-connection layers. The plurality of loss calculation units are used for calculating the loss of a loss function by adopting cross entropies as multiple classifiers. The plurality of parameter updating units correspond to the attribute identifying tasks and are connected with the loss calculation units. The parameter updating units are used for returning the loss based on the random gradient descent optimization algorithm, and updating parameters. According to the invention, various fine vehicle attributes can be identified at the same time by adopting only one neural network.
Description
technical field [0001] The invention relates to the technical field of computer vision and pattern recognition, in particular to a deep neural network for finely recognizing vehicle attributes and a training method thereof. Background technique [0002] Vehicle refined attribute recognition technology is a basic technology in the field of intelligent transportation security. Identifying vehicle attributes can improve the computer's understanding of target vehicles and help solve some more difficult problems in the field of traffic security, such as automatic vehicle retrieval and vehicle re-identification. . [0003] Vehicle attribute recognition is a classic problem in computer vision and pattern recognition. The recognized vehicle attributes generally include the color of the vehicle, the type of the vehicle, and the brand of the vehicle. attributes, and classify and label vehicles. The key technology to solve this kind of problem is the image recognition and classificat...
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