Vehicle color recognition method and system

A color recognition and vehicle technology, applied in the field of vehicle color recognition, can solve problems such as affecting the accuracy rate, incorrect recognition results, and misrecognition, and achieve the effect of improving the accuracy rate and improving the fitting ability.

Active Publication Date: 2019-11-15
GOSUNCN TECH GRP
View PDF7 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the current existing technologies, most of the traditional methods are used for color recognition. In the process of selecting color area blocks, there will be great interference from factors such as illumination and vehicle attitude, which will cause errors in the recognition results. Some car windows, car fences, and sunroof areas may be intercepted, and identifying areas with non-color information will also cause misidentification, greatly affecting its accuracy

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
  • Vehicle color recognition method and system
  • Vehicle color recognition method and system
  • Vehicle color recognition method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] see figure 1 , figure 1It is a flow chart of a vehicle color recognition method provided by an embodiment of the present invention; including:

[0047] S1. Obtain a sample image of the vehicle, and perform preprocessing on the sample image; wherein, the sample image includes several different color categories;

[0048] S2. Input the preprocessed sample image into a pre-trained convolutional neural network based on an attention mechanism to output a multimodal feature map;

[0049] S3. Input the multimodal feature map into the pre-trained three-width learning network to output the color recognition result of the sample image.

[0050] Specifically, in step S1, after speaking out the sample images, the sample images are respectively converted into sample images in RGB, HSV, and LAB formats; wherein, the sample images are divided into a training set and a test set, The training set is used to train the convolutional neural network based on the attention mechanism, and t...

Embodiment 2

[0073] see Figure 6 , Figure 6 It is a schematic structural diagram of a vehicle color recognition system provided by an embodiment of the present invention; the vehicle color recognition system includes:

[0074] A sample image preprocessing module 10, configured to acquire a sample image of a vehicle, and preprocess the sample image; wherein, the sample image includes several different color categories;

[0075] The multimodal feature map acquisition module 20 is used to input the preprocessed sample image into the pre-trained convolutional neural network based on the attention mechanism to output the multimodal feature map;

[0076]The recognition module 30 is configured to input the multimodal feature map into a pre-trained three-width learning network to output the color recognition result of the sample image.

[0077] see Figure 7 , Figure 7 It is a schematic structural diagram of a convolutional neural network training module 40 in a vehicle color recognition sy...

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

No PUM Login to view more

Abstract

The invention discloses a vehicle color recognition method, and the method comprises the steps: obtaining a sample image of a vehicle, and carrying out the preprocessing of the sample image; wherein the sample image comprises a plurality of different color categories; inputting the preprocessed sample image into a pre-trained convolutional neural network based on an attention mechanism so as to output a multi-modal feature map; and inputting the multi-modal feature map into a pre-trained three-width learning network to output a color recognition result of the sample image. The invention further discloses a vehicle color recognition system. By adopting the embodiment of the invention, the feature extraction capability of the convolutional neural network of an attention mechanism is utilized, and the multi-modal feature fusion capability of width learning is effectively combined, so that vehicle color discrimination of an actual scene can be realized, and the accuracy of vehicle color identification is improved.

Description

technical field [0001] The invention relates to the technical field of vehicle color recognition, in particular to a vehicle color recognition method and system. Background technique [0002] As a reliable and distinctive feature of vehicles, vehicle color provides useful information for vehicle identification, monitoring, tracking, etc. Vehicle color recognition is a technology to determine the color of the vehicle in the image based on the input vehicle image, which has been widely used in public security law enforcement, vehicle tracking and other fields. In natural scenes, the color of vehicles is easily affected by weather, light and dust, which may cause color shift. At the same time, vehicle colors are based on people's subjective psychological feelings. In fact, only some areas can be used for vehicle color recognition. Vehicles of different types The color identification area blocks are also different. In the current existing technologies, most of the traditional ...

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
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/10G06V10/56G06V2201/08G06N3/045G06F18/253
Inventor 彭勇毛亮贺迪龙朱婷婷胡胤黄仝宇汪刚宋一兵侯玉清刘双广
Owner GOSUNCN TECH GRP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap