Vehicle-Trajectory Road Surface Estimation in Adverse Conditions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for estimating road surface geometry face challenges in adverse conditions such as adverse weather, occlusions, and undulating roads, making accurate estimation difficult using direct visual observation.
Innovation Solution
Utilizing vehicle detection by tracking the trajectory of reference vehicles ahead of the ego vehicle through a series of images to estimate road surface geometry, leveraging visual odometry and vehicle sensors for precise positioning and scaling.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If direct visual observation of road surface is used for geometry estimation, then the method is simple, but accuracy deteriorates in adverse conditions such as adverse weather, occlusions, and undulating roads
Solution Approach 1:
The patent uses detected vehicles as intermediary objects to indirectly estimate road surface geometry. Instead of directly observing the road surface which is affected by adverse conditions, the system observes vehicles traveling on the road and uses their detected positions and trajectories as mediators to infer road geometry, thereby bypassing the harmful effects of adverse weather, occlusions, and undulating roads
Solution Approach 2:
The patent replaces direct mechanical/visual road surface observation with a computational approach using vehicle detection and trajectory analysis. By substituting the direct road surface measurement mechanism with a vehicle-based indirect measurement system, the method achieves more reliable geometry estimation under adverse conditions where direct observation fails
2Measurement precision
If vehicle detection and trajectory tracking is used for road surface estimation, then accuracy in adverse conditions improves, but device complexity increases
Solution Approach 1:
The patent makes the vehicle detection system multi-functional by using it for both its primary purpose (vehicle detection and tracking) and a secondary purpose (road surface geometry estimation). The same detected vehicle data and trajectory information are reused for both functions, thereby avoiding the need for separate dedicated road observation systems and reducing overall device complexity
Solution Approach 2:
The system uses the vehicles already present on the road as natural reference objects for geometry estimation. These vehicles, which are naturally occurring in the scene and not specifically added for measurement purposes, serve the dual role of being traffic participants and measurement references, thereby simplifying the system by eliminating the need for artificial reference markers or dedicated infrastructure
Data Source
AI summary
Various aspects of the present disclosure generally relate to autonomous driving and driver assistance systems. In some aspects, a device associated with an ego vehicle may obtain a series of images that depict a reference vehicle traveling along a road segment ahead of the ego vehicle. The device may estimate, based on the series of images, a size of the reference vehicle and/or a position of the reference vehicle relative to the ego vehicle. The device may track a trajectory of the reference vehicle along the road segment ahead of the ego vehicle based on the estimated size of the reference vehicle and/or the estimated position of the reference vehicle over the series of images. The device may estimate a surface geometry associated with the road segment ahead of the ego vehicle based on the tracked trajectory of the reference vehicle. Numerous other aspects are described.