Supercharge Your Innovation With Domain-Expert AI Agents!

Method, device and computer program product for intelligently identifying road state

A computer program and road state technology, applied in the field of road recognition, can solve problems such as failure to provide early warning of road state information and inability to synchronize signals, and achieve the effect of enhancing the robustness of the system and increasing the amount of information

Inactive Publication Date: 2019-10-22
HEREN KEJI WUHAN LLC
View PDF11 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition to the same problems as the above-mentioned vehicle-mounted non-contact sensors, the detected signal cannot be synchronized with the state of the vehicle, so it cannot provide real-time and effective early warning of road state information

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
  • Method, device and computer program product for intelligently identifying road state
  • Method, device and computer program product for intelligently identifying road state
  • Method, device and computer program product for intelligently identifying road state

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] Please refer to figure 1 , figure 1 It is a schematic flow chart of a method for intelligently identifying road states of the present application. The method of this embodiment includes the following steps:

[0045] Step 101, taking a spectral image of a preset spectral band of the current road and a polarization image of a preset polarization state.

[0046] Step 102, merging the spectral image and the polarization image into a high-dimensional image, the high-dimensional image includes information about the preset spectral band and information about the preset polarization state.

[0047] Step 103: Input the high-dimensional image into the trained neural network, and the neural network outputs the current state of the road.

[0048] The method of this embodiment is implemented by using a device for intelligently identifying road conditions. Please refer to figure 2 and image 3 , the device 200 for intelligently identifying road conditions in this embodiment inc...

Embodiment 2

[0056] The method and device of Embodiment 1 can greatly improve the road recognition capability of the road detection system. However, since the road scene is in a complex environment, the collected images will be affected by ambient light. For example, at a certain angle at a certain moment, the sensor may be affected by the reflection of sunlight, and all the frequency bands it can receive will be strongly interfered, making it impossible to effectively analyze the current frame. In order to deal with various corner cases, please refer to Figure 6 , the present embodiment provides the following method steps for intelligently identifying road conditions:

[0057] Step 301: Continuously shoot spectral images of preset spectral bands and polarization images of preset polarization states on the current road.

[0058] Step 302, merging the spectral image and the polarization image into N frames of high-dimensional images, wherein the high-dimensional images include the informa...

Embodiment 3

[0071] The technical idea of ​​this embodiment is basically the same as that of Embodiment 1 and Embodiment 2. The difference is that this embodiment has characteristics in the training method of the neural network. details as follows:

[0072] During the training process of the neural network in the data processing module 204, the input end of the neural network is the high-dimensional image data fused by the data preprocessing module 202 from the series of images collected by the hyperspectral imaging device 201, which is different from the traditional neural network. Input (usually visible light red, green and blue three-channel input).

[0073] Since the training of the neural network adopts the supervised learning method, it is necessary to manually label the network input. However, in addition to the information in the visible light frequency band, the information in other frequency bands and polarization information of high-dimensional images cannot be understood by h...

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 provides a method, a device and a computer program product for intelligently identifying a road state. The method comprises the following steps: shooting a spectral image of a preset spectral band of a current road and a polarization image of a preset polarization state; fusing the spectral image and the polarization image into a high-dimensional image, wherein the high-dimensional image comprises information of the preset spectral band and information of the preset polarization state; and inputting the high-dimensional image into a trained neural network, wherein the neural network outputs the state of the current road. The road state can be accurately and remotely detected in real time, the method, the device and the computer program can be applied to all-weather scenes andcomplex environments, the implementation is easy, and the cost is controllable.

Description

technical field [0001] The present application relates to the technical field of road recognition, in particular to a method, device and computer program product for intelligently recognizing road states. Background technique [0002] With the improvement of people's living standards, cars have entered thousands of households and gradually become the first choice for people to travel. With the continuous growth of car ownership and the increase in the frequency of car use, how to ensure driving safety has gradually become a common concern. There are many factors that affect driving safety. In addition to human subjective factors, there are also objective factors such as the vehicle's own condition, weather conditions, surrounding vehicle environment conditions, and road conditions. Among them, due to the influence of the natural environment, the road state changes in complex forms and at a fast rate, and its impact on driving safety is difficult to predict. Especially when...

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
IPC IPC(8): G06K9/00G06N3/04
CPCG06V20/56G06N3/045
Inventor 王星泽彭显明陈维宇
Owner HEREN KEJI WUHAN LLC
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com