Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Laser point cloud three-dimensional target detection model and method for complex traffic scene

A traffic scene, laser point cloud technology, applied in three-dimensional object recognition, biological neural network model, character and pattern recognition and other directions, can solve the problem that cannot meet the perception needs of smart cars, cannot adapt to complex traffic scenes, and the detection effect of small objects is not good. It is beneficial to real-time detection, alleviating category imbalance, and making the network easier to optimize.

Pending Publication Date: 2022-01-11
JIANGSU UNIV
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In view of the fact that most of the current 3D target detection algorithms cannot adapt to complex traffic scenes, the detection of long-distance vehicles and short-distance pedestrians, cyclists and other small targets is not effective, and cannot meet the perception needs of smart cars in complex traffic situations.

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
  • Laser point cloud three-dimensional target detection model and method for complex traffic scene
  • Laser point cloud three-dimensional target detection model and method for complex traffic scene
  • Laser point cloud three-dimensional target detection model and method for complex traffic scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] The present invention will be further described below in conjunction with accompanying drawing.

[0050] A laser point cloud three-dimensional target detection method for complex traffic environments proposed by the present invention, such as figure 1 As shown, it specifically includes the following process:

[0051] Step 1. Select the Huawei ONCE data set as the training data set and verification data set of the detection network, and add a class-balanced sampling enhancement method during training.

[0052] The Huawei ONCE dataset is collected by 7 cameras and 1 40-line lidar, which contains 5 categories, namely cars, trucks, buses, pedestrians and cyclists. The data set collects scenes of different weather (sunny, cloudy, rainy), different time (morning, Chinese, afternoon, evening), and different road conditions (city center, suburbs, highways, tunnels, bridges), which can be better Represents complex traffic situations. The ONCE data set collects 144 hours of au...

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 laser point cloud three-dimensional target detection model and method for a complex traffic scene, a three-dimensional encoder in the model is beneficial to the detection of long-distance targets and small targets, and sparse convolution and sub-manifold convolution can greatly improve the coding efficiency of voxel features. The residual structure of the two-dimensional encoder can keep more complete information, detection of a long-distance target and a small target is facilitated, meanwhile, the network is easier to optimize, feature extraction and receptive field expansion can be carried out on an original scale and a self-calibration scale through self-calibration convolution, more complete and rich features can be extracted. Useful feature expression is enhanced in the space direction and the channel direction through space attention and channel attention, and useless information is inhibited. The final detection precision of vehicles is 81.88%, the final detection precision of pedestrians is 47.82%, the final detection precision of riders is 69.81%, the average precision is 66.25%, the average precision is 9.9% higher than that of an existing VOXEL RCNN algorithm, 13.8 FPS is achieved on RTX 2080Ti display, and the detection precision and speed can meet the sensing requirements of intelligent vehicles in complex traffic environments.

Description

technical field [0001] The invention belongs to the field of intelligent vehicle perception, and specifically refers to a laser point cloud three-dimensional target detection model and method for complex traffic scenes. Background technique [0002] A smart car is a complex system including perception, decision-making, and control. Among them, environmental perception technology is the basis of intelligent vehicles, which provides necessary environmental information for subsequent decision-making and control. The accuracy of traditional machine learning algorithms can no longer meet the operating requirements of current smart cars. As a result, deep learning-based perception algorithms have developed rapidly and made great progress in the field of 2D object detection and segmentation. However, the camera will be affected by night, rain, fog, strong light and other conditions, which will affect the detection effect. With the reduction of the cost of lidar and the improveme...

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): G06V20/64G06K9/62G06N3/04G06V10/82G06V10/774G06V10/764G06V20/54
CPCG06N3/045G06F18/214G06F18/2431
Inventor 王海陈智宇蔡英凤陈龙刘擎超李祎承
Owner JIANGSU UNIV
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
Eureka Blog
Learn More
PatSnap group products