Obstacle Detection Using Depth Cues for Occluded Vehicles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing automated driving technologies struggle to accurately determine the relative positional relationship between obstacles that are obstructed or obscured, leading to inaccurate obstacle detection.
Innovation Solution
An obstacle detection method that involves acquiring a road scene image, performing obstacle recognition to obtain region and depth-of-field information, determining occlusion relationships, and using ranging results to calculate accurate obstacle detection results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If distance detection is performed through sensors to determine hazard levels of obstacles, then automated driving safety is improved, but accurate determination of relative positional relationships between obscured obstacles deteriorates
Solution Approach 1:
The patent introduces depth-of-field information as an additional dimensional parameter beyond basic distance detection. By analyzing depth-of-field values from road scene images, the system can determine relative positional relationships of obscured obstacles in the depth dimension, resolving the contradiction between safety detection and positional accuracy for occluded objects.
Solution Approach 2:
The patent uses depth-of-field information as an intermediary parameter to bridge the gap between sensor-based distance detection and visual obstacle recognition. This intermediary enables the system to accurately determine relative positions of obscured obstacles by comparing depth-of-field values, thereby improving measurement precision without compromising safety.
2Measurement precision
If multiple sensors and complex detection systems are used to improve obstacle detection accuracy, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent makes the existing ranging apparatus serve multiple functions: it provides both distance information and depth-of-field information for obstacle detection. By extracting depth-of-field values from existing image data and combining them with ranging results, the system achieves improved detection accuracy without adding complex dedicated depth sensing hardware.
Solution Approach 2:
The system uses its own existing resources (road scene images from cameras and ranging data from existing sensors) to solve the detection accuracy problem. By processing and analyzing data already collected by the automated driving system, it derives depth-of-field information without requiring external additional equipment, thereby avoiding increased device complexity.
Data Source
AI summary
An obstacle detection method can improve the accuracy of determining a relative positional relationship between two or more obstacles that are obstructed or obscured during automated driving. A road scene image of a road where a target vehicle is located is acquired. Obstacle recognition is performed to obtain region information and depth-of-field information corresponding to each obstacle in the road scene image. Target obstacles in an occlusion relationship and a relative depth-of-field relationship between the target obstacles are determined. A ranging result of each obstacle is acquired using a ranging apparatus corresponding to the target vehicle. An obstacle detection result of the road is determined based on the relative depth of field relationship between the target obstacles and the ranging result of each obstacle, thereby improving the accuracy of determining a positional relationship of obstructed or obscured obstacles during automated driving.