A vector map construction method and device, a storage medium and an electronic device

By combining low-light image enhancement and multi-view BEV transformation technology with spatiotemporal information fusion, the perception and map building problems of autonomous driving systems in low-light and dynamic scenarios are solved, achieving high-precision, low-latency vector map prediction and improving the robustness and efficiency of autonomous driving systems.

CN120538490BActive Publication Date: 2026-06-09BEIHANG UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Patents(China)
Current Assignee / Owner
BEIHANG UNIV
Filing Date
2025-05-14
Publication Date
2026-06-09

AI Technical Summary

Technical Problem

In low-light environments and dynamic traffic scenarios, the perception capabilities of cameras decrease, making it difficult for autonomous driving systems to accurately understand the surrounding environment, affecting path planning and driving decisions, and resulting in insufficient stability and real-time performance of map building.

Method used

We employ low-light image enhancement, multi-view BEV transformation, and spatiotemporal information fusion techniques. We use the ResNet model and BEVFormer framework for image enhancement and feature extraction, and combine the position change information of the inertial measurement unit for feature fusion to generate vector curves and construct vector maps.

Benefits of technology

It improves the perception capabilities and map building stability of autonomous driving systems in low-light and dynamic scenarios, enabling high-precision, low-latency vector map prediction and meeting the robust application requirements in complex environments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120538490B_ABST
    Figure CN120538490B_ABST
Patent Text Reader

Abstract

The application provides a vector map construction method and device, a storage medium and electronic equipment, comprising: performing low-light image enhancement processing on N frames of current images to obtain N frames of enhanced images; performing multi-view BEV conversion processing on the N frames of enhanced images to obtain BEV current features; performing fusion processing on the BEV current features and BEV features in a historical window to obtain BEV fusion features; generating a vector curve based on the BEV fusion features, and completing vector map construction based on the vector curve. In a low-light environment and a dynamic scene, the perception ability of an automatic driving system, the stability of map construction and the calculation efficiency can be effectively improved; through fusion of high-definition enhanced images and space-time information, high-precision and low-delay vector map prediction is realized, the robust application requirements of automatic driving technology in a complex environment are met, and more reliable technical support is provided for the development of a future intelligent transportation system.
Need to check novelty before this filing date? Find Prior Art