Intelligent vehicle systems and control logic for surround view enhancement

By using natural surround vision technology and depth inference, AI neural networks are used to identify and replace objects in vehicle sensor images to generate virtual view images. This solves the problem of narrow near-field field of view in sensor systems and achieves more accurate target detection and improved virtual scene quality.

CN116137655BActive Publication Date: 2026-04-24GM GLOBAL TECHNOLOGY OPERATIONS LLC
6 Cites 0 Cited by

Patent Information

Application Number
CN202211240544.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Priority Date
2021-11-17
Filing Date
2022-10-11
Publication Date
2026-04-24
Estimated Expiration
2042-10-11

AI Technical Summary

Technical Problem

Existing sensor systems for motor vehicles are limited in terms of narrow near-field field of view, accuracy, and application, making it difficult to provide comprehensive context awareness and virtual scene quality.

Method used

Using natural surround vision technology, the system identifies objects and replaces them with 3D models through image segmentation and depth inference, generating virtual perspective images. It combines in-vehicle camera networks and system control logic to perform object recognition and model replacement.

Benefits of technology

It achieves more accurate target detection and classification, provides more comprehensive context awareness, generates virtual perspective images to improve vehicle response, and enhances the intelligence of driver assistance systems.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

An intelligent vehicle system with networked in-vehicle cameras with camera view enhancement capability, methods of manufacturing / using such a system, and vehicles equipped with such a system are presented. A method for operating a motor vehicle includes a system controller receiving from a network of in-vehicle cameras camera image data containing a target object from the perspective of one or more cameras. The controller analyzes the camera image to identify characteristics of the target object and classifies those characteristics into a corresponding model collection associated with a type of the target object. The controller then identifies a 3D object model assigned to the model collection associated with the type of the target object. A new "virtual" image is generated by replacing the target object with the 3D object model positioned in a new orientation. The controller commands the resident vehicle system to perform a control operation using the new image.
Need to check novelty before this filing date? Find Prior Art