Monocular-Camera-Guided Depth Sensor Activation for Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current devices using sensors for localization, such as Microsoft Hololens®, Magic Leap®, ARCore®, and ARKit®, keep all sensors active, leading to unnecessary energy consumption and computational resource utilization due to lack of selective activation and deactivation of individual sensors.
Innovation Solution
A device that includes a processor to receive image data from a monocular camera, determine the benefit level of activating a depth sensor for localization, and activate it based on a satisfaction of an activation rule, reducing energy consumption and computational resources by selectively activating the depth sensor when beneficial.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If all sensors are kept active for localization, then localization accuracy and reliability are improved, but energy consumption and computational resource utilization increase
Solution Approach 1:
The patent implements dynamic sensor activation where the depth sensor is selectively activated or deactivated based on real-time evaluation of image data quality and localization benefit levels. This dynamic control allows the system to adapt sensor usage to current operational conditions, maintaining localization reliability when needed while reducing energy consumption during periods when monocular camera data is sufficient.
Solution Approach 2:
The system changes the operational state parameter of the depth sensor from always-on to conditionally-active based on evaluated parameters such as image data quality, texture richness, and localization accuracy requirements. This parameter change enables the system to optimize the trade-off between localization reliability and energy consumption by adjusting sensor activation status according to environmental and operational conditions.
2Measurement precision
If depth sensor is always active, then localization accuracy is improved, but computational resource utilization increases
Solution Approach 1:
The patent applies partial action by activating the depth sensor only partially - specifically when image data from the monocular camera indicates insufficient texture or quality for accurate localization. Instead of continuous depth sensor operation, the system uses selective activation based on real-time assessment, thereby reducing computational resource utilization while maintaining localization accuracy when genuinely needed.
Solution Approach 2:
The system implements a feedback mechanism where image data quality is continuously evaluated and used to determine depth sensor activation. The localization benefit level assessment provides feedback that controls sensor activation, creating a closed-loop system that optimizes computational resource usage by activating the depth sensor only when the feedback from image analysis indicates a benefit.
3Use of energy by moving object
If depth sensor is selectively activated based on image data, then energy consumption is reduced, but device complexity increases
Solution Approach 1:
The patent applies preliminary action by evaluating image data quality and determining localization benefit levels before activating the depth sensor. This preliminary assessment prevents unnecessary sensor activation and reduces energy consumption. The system performs preliminary analysis of monocular camera data to predict whether depth sensor activation will be beneficial, thereby simplifying the overall control logic through proactive decision-making.
Data Source
AI summary
A device is disclosed that is configured to perform localization using one or both of a monocular camera and a depth sensor that are transportable with the device. The device includes at least one processor operationally connected to the monocular camera and the depth sensor. The device also includes at least one memory storing program code that is executed by the at least one processor to perform operations to receive image data from the monocular camera. The operations determine a benefit level of activating the depth sensor for localization, based on the image data, and activate the depth sensor for localization based on a determination that the benefit level of activating the depth sensor satisfies an activation rule. Related methods and computer program products are also disclosed.