Distance Estimation Using Bounding Box Ratios
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in accurately estimating the distance to peripheral vehicles, especially under adverse weather or lighting conditions, as they rely heavily on recognizing feature information like tail lights and license plates, which can be occluded.
Innovation Solution
A distance estimation apparatus using a camera and processing circuitry to generate a bounding box around a target vehicle, calculate ratios of its rear and side surfaces, and estimate distances based on these ratios, allowing for accurate rectilinear and lateral distance measurement and vehicle control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If autonomous vehicles rely on recognizing feature information (tail lights, license plates) to identify peripheral vehicles, then the system complexity is reduced, but measurement precision deteriorates under adverse weather or lighting conditions when feature information is occluded
Solution Approach 1:
The patent introduces an intermediary geometric model (bounding box with rear region ratio) that mediates between the simple camera imaging system and the complex task of accurate distance estimation. By using the ratio of the rear region width to the bounding box width as an intermediate parameter, the system can estimate distances accurately without relying on complex feature recognition, thus maintaining low system complexity while improving measurement precision.
2Ease of operation
If autonomous vehicles use simple feature recognition methods, then ease of operation is improved, but reliability deteriorates when feature information is occluded due to worsened weather, traffic conditions, or lighting conditions
Solution Approach 1:
The patent changes the parameter used for vehicle recognition from feature-based parameters (tail lights, license plates) to geometric parameters (bounding box dimensions, rear region ratio). This parameter change makes the recognition system more reliable under adverse conditions while maintaining ease of operation, as the geometric parameters can be extracted directly from the image without complex feature detection.
3Device complexity
If autonomous vehicles use traditional distance estimation methods based on feature recognition, then device complexity is reduced, but measurement precision deteriorates in adverse environmental conditions
Solution Approach 1:
The patent introduces an intermediary geometric model (bounding box with rear region ratio) that mediates between the simple camera imaging system and the complex task of accurate distance estimation. By using the ratio of the rear region width to the bounding box width as an intermediate parameter, the system can estimate distances accurately without relying on complex feature recognition, thus maintaining low system complexity while improving measurement precision.
Data Source
AI summary
An apparatus, system, method, and/or non-transitory computer readable media of a distance estimation apparatus including at least one camera includes obtaining a bounding box corresponding to a target vehicle on the basis of an image obtained through the at least one camera, obtaining a first rectilinear distance to the target vehicle, obtaining a first world width on the basis of the first rectilinear distance and a width of the bounding box, obtaining a second ratio of a region, corresponding to a rear surface of the target vehicle, of a region of the bounding box on the basis of a first ratio, and calculating a second world width of the target vehicle on the basis of the second ratio, wherein the first ratio represents a ratio of the rear surface and a side surface of the target vehicle.