Real-time traffic sign detection method based on multi-scale pixel feature fusion

A pixel feature and real-time traffic technology, applied in the field of deep learning and target detection, can solve the problem of low real-time performance of detection algorithms, achieve high-precision real-time traffic sign detection, improve detection performance, and use less memory.
CN112183203APending Publication Date: 2021-01-05BEIJING UNIV OF TECH

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
BEIJING UNIV OF TECH
Publication Date
2021-01-05

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a real-time traffic sign detection method based on multi-scale pixel feature fusion, and belongs to the field of deep learning and target detection. Firstly, an image containing a traffic sign is obtained and preprocessed; secondly, inputting the preprocessed image into a MobileNetv2 network to carry out feature extraction; inputting the extracted multi-scale feature map into a pixel feature fusion module for pixel rearrangement, and splicing to generate a fusion feature map with semantic information and detail information; performing down-sampling on the fusion featuremap to obtain six scale feature maps, inputting the six scale feature maps into an efficient channel attention module, and allocating weights to feature channels according to importance degrees; inputting the weighted six-scale feature map into an SSD detection layer to predict the position of the bounding box and the category of the object; and finally, carrying out non-maximum suppression to obtain an optimal traffic sign detection result. According to the method, the real-time performance and the accuracy can be considered when the traffic sign image is detected, and the robustness is veryhigh.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the field of deep learning and target detection, and in particular relates to a real-time traffic sign detection method based on multi-scale pixel feature fusion. Background technique

[0002] For road traffic safety, traffic signs are crucial. In a real driving scene, there are lighting changes caused by natural environments such as sunlight and weather, and there are also special situations such as fading, deformation, and occlusion of traffic signs. Human eyes may miss or misidentify traffic signs, resulting in confusion about the road ahead. Misjudgment can lead to traffic accidents, personal property and vehicle losses, and even life-threatening threats. As an important part of advanced driver assistance systems, real-time and accurate traffic sign detection technology can assist drivers to ensure driving safety and avoid danger, and has important applications in the fields of traffic safety and automatic driving. [000...

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