Adjustable Stereo Camera Width for Depth and Blind Spot Trade-off
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous driving systems face challenges in effectively balancing the trade-off between maximum measurable depth and blind spot areas using stereo cameras, where increasing the camera width enhances depth measurement but expands blind spots, and decreasing it improves visibility but reduces depth measurement capability.
Innovation Solution
The autonomous driving apparatus dynamically adjusts the width of the stereo camera based on the estimated driving situation, using a controller to select the appropriate camera configuration and distance between cameras to prioritize either greater depth measurement or a wider visual field depending on the driving conditions, such as speed and environment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the width of the stereo camera is increased to enhance depth measurement capability, then the maximum measurable depth is improved, but the blind spot areas expand
Solution Approach 1:
The patent applies the dynamics principle by making the stereo camera width adjustable rather than fixed. The controller dynamically changes the distance between the left and right cameras based on driving situations, allowing the system to optimize between depth measurement capability and blind spot coverage in real-time. This resolves the contradiction by enabling the camera configuration to adapt to different operational requirements.
Solution Approach 2:
The patent implements parameter changes by varying the physical distance between cameras as a controllable parameter. The controller adjusts this parameter according to driving conditions, such as setting a larger camera width for highway driving where depth measurement is critical, and a smaller width for urban environments where blind spot coverage is more important. This dynamic parameter adjustment resolves the fundamental trade-off between the two competing requirements.
2Area of stationary object
If the width of the stereo camera is decreased to improve visual field coverage, then the blind spot areas are reduced, but the maximum measurable depth is reduced
Solution Approach 1:
The system dynamically adjusts the camera width parameter based on real-time driving situation assessment. When the controller determines that wide visual field coverage is more important than maximum depth measurement, it decreases the distance between cameras, thereby reducing blind spot areas while maintaining adequate depth measurement for the current scenario.
Solution Approach 2:
The controller changes the camera width parameter in response to different driving conditions. For example, in urban environments with frequent lateral movements and parking maneuvers, the system reduces camera width to improve visual field coverage and reduce blind spots, accepting the trade-off of reduced maximum measurable depth which is less critical in these scenarios.
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
This approach allows for effective depth measurement and object recognition while minimizing blind spots, enabling safe path planning and obstacle detection without the need for costly lidar or radar systems, thereby enhancing the vehicle's ability to navigate various driving scenarios.
Implementation Method 1
measuring a depth of an object located in the first direction based on output images of the two cameras
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Disclosed is a stereo camera-based autonomous driving method and apparatus, the method including estimating a driving situation of a vehicle, determining a parameter to control a stereo camera width of a stereo camera based on the estimated driving situation, controlling a capturer configured to control arrangement between two cameras of the stereo camera for a first direction based on the determined parameter, and measuring a depth of an object located in the first direction based on two images respectively captured by the two cameras with the controlled arrangement.