Rear Camera Stub Detection for Automated Driving
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated driving systems lack effective methods to detect and map intersecting roadways and potential entry/exit points while driving forward, as rear cameras are typically idle during forward motion and existing sensors may not provide sufficient data in all environments.
Innovation Solution
Employing a rear-facing camera and sensor fusion with LIDAR to detect road markings, shoulders, and curbs, using deep neural networks to identify gaps and variations indicative of intersecting roadways, and storing this information in a drive history database for future navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Difficulty of detecting and measuring
If rear camera is used to detect intersecting roadways, then detection capability is improved, but device complexity increases due to sensor fusion requirements
Solution Approach 1:
The rear-facing camera, traditionally used only for backup viewing, is repurposed to detect intersecting roadways and map features during forward driving. This multi-functional use of existing hardware improves detection capability without adding dedicated sensors, thereby limiting the increase in device complexity.
Solution Approach 2:
The system combines data from the rear-facing camera with LIDAR sensor data to detect road markings, shoulders, and curbs. By merging existing sensor data streams, the system achieves robust intersection detection without requiring entirely new sensing infrastructure.
2Measurement precision
If deep neural networks are used to identify road features, then measurement precision is improved, but use of energy increases due to computational requirements
Solution Approach 1:
The system pre-processes and stores raw sensor data from rear cameras and LIDAR in drive history databases during normal operation. When intersection detection is needed, the pre-organized data can be quickly queried and analyzed by deep neural networks, reducing real-time computational energy requirements while maintaining high measurement precision.
3Productivity
If rear camera data is utilized during forward motion, then productivity is improved by enabling route planning, but device complexity increases due to idle sensor activation
Solution Approach 1:
The system automatically activates and processes rear camera data during forward motion without requiring manual intervention. The drive history database autonomously stores and organizes sensor data, and the system self-manages the workflow from data collection to intersection detection to route planning, improving productivity while keeping activation control straightforward.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables the detection and mapping of intersecting roadways and potential entry/exit points, enhancing route planning and point-of-interest detection, even in environments without traditional lane markings, by utilizing data from a rear-facing camera and sensor fusion to improve the accuracy and robustness of automated driving systems.
Implementation Method 1
sensor fusion with LIDAR to detect road markings, shoulders, and curbs
Implementation Method 2
detect, based on the perception data, an intersecting roadway
Data Source
AI summary
A method for detecting stubs or intersecting roadways includes receiving perception data from at least two sensors. The at least two sensors include a rear facing camera of a vehicle and another sensor. The perception data includes information for a current roadway on which the vehicle is located. The method includes detecting, based on the perception data, an intersecting roadway connecting with the current roadway. The method also includes storing an indication of a location and a direction of the intersecting roadway with respect to the current roadway.