Data acquisition and labeling method and system for road camera perception and mapping

By using drones equipped with cameras and sensor modules for data collection and annotation, the problem of narrow sensor deployment range has been solved, enabling efficient and low-cost data collection and annotation, and improving the diversity and authenticity of autonomous driving data.

CN119206396BActive Publication Date: 2026-07-21WUXI RES INST OF APPLIED TECH TSINGHUA UNIV +1
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
WUXI RES INST OF APPLIED TECH TSINGHUA UNIV
Filing Date
2024-09-24
Publication Date
2026-07-21

AI Technical Summary

Technical Problem

In existing technologies, using vehicle-deployed sensors for data collection is inefficient and costly. Furthermore, the narrow deployment range of sensors cannot fully cover road sections, resulting in an overly narrow distribution of model training data, high deployment costs, and difficulty in meeting the data requirements of autonomous driving.

Method used

By using drones equipped with camera and sensor modules, images and sensor data are acquired through the drones, and data is labeled using computer equipment. High-precision map information is then used for data fusion and labeling, achieving efficient data collection and labeling.

Benefits of technology

It improves data collection efficiency, comprehensively covers different intersections and time periods, enhances data diversity and authenticity, provides high-precision data support for autonomous driving algorithms, and reduces sensor deployment costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119206396B_ABST
    Figure CN119206396B_ABST
Patent Text Reader

Abstract

The present application relates to the data acquisition and labeling method and system for road camera perception and mapping, and relates to the automatic driving technical field.The system comprises a computer device and a unmanned aerial vehicle device, and the computer device is in communication connection with the unmanned aerial vehicle device;the unmanned aerial vehicle device comprises a camera module, a sensor module, a general control module and a flight module;the general control module is in communication connection with the camera module, the sensor module and the flight module.The unmanned aerial vehicle is used to simulate the intersection camera and the sensor to collect data, improve the data collection efficiency, comprehensively cover different intersections and time periods, simulate the real visual angle, improve the data diversity and authenticity.The image data and the geographic position data are combined with high precision, and effective data support is provided for the automatic driving algorithm.
Need to check novelty before this filing date? Find Prior Art