Peripheral Image Sensors for Indoor Pose Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Mobile computing devices face challenges in accurately determining their pose and location, especially indoors, due to the limitations of GPS signals and the accumulation of errors in inertial measurement units over time.
Innovation Solution
Equipping mobile devices with a set of image sensors around their periphery to capture visual data, which processes images to estimate the device's pose and location, even in environments without GPS signals, using low-resolution imaging systems that provide a wide field of view and reduce power consumption, while maintaining privacy through image degradation and abstraction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS sensors are used to determine device location, then high-resolution geo-location measurements are obtained outdoors, but GPS signal reception fails or provides poor precision indoors due to signal noise
Solution Approach 1:
The system segments the location determination function across multiple sensor types (GPS, IMU, image sensors) rather than relying on a single sensor. Each sensor handles specific environmental conditions, with image sensors specifically addressing indoor environments where GPS fails.
Solution Approach 2:
Image sensors serve as an intermediary mechanism between the device and the environment for location determination. Instead of directly using GPS signals that fail indoors, the system captures images of environmental features and processes them to infer location, effectively mediating the location determination process.
2Duration of action of moving object
If IMUs are used to track device motion over time, then motion tracking is achieved, but error accumulates during prolonged periods
Solution Approach 1:
The system uses image sensors to provide periodic feedback on absolute position by recognizing environmental features. This feedback corrects the cumulative drift error from IMU integration, resetting the error baseline and enabling accurate tracking over extended durations.
Solution Approach 2:
The system performs preliminary actions by capturing images and processing visual data to establish reference points and environmental features before relying on IMU tracking. This preparation enables error correction to be applied proactively rather than reactively.
3Measurement precision
If multiple image sensors are placed around the device periphery to achieve wide field of view, then pose estimation accuracy improves, but device complexity increases
Solution Approach 1:
The image sensors serve multiple functions: capturing images for pose estimation, identifying environmental features for location determination, and providing visual data for both indoor and outdoor environments. This multi-functionality justifies the added complexity by eliminating the need for separate sensor systems.
4Measurement precision
If high-resolution images are captured for accurate pose estimation, then measurement precision improves, but power consumption increases
Solution Approach 1:
The system applies partial action by capturing images at lower resolutions than maximum capability and processing only the necessary visual features for pose estimation. This selective approach provides sufficient precision for location determination while significantly reducing the computational power required for image processing.
Data Source
AI summary
This specification discloses computer-based systems, methods, devices, and other techniques for estimating the pose of a device, including estimating the pose based on images captured by a set of image sensors disposed around the device's periphery. Some implementations include a system that obtains visual data representing at least one image captured by one or more image sensors of a mobile device. The at least one image show an environment of the mobile device, and the one or more image sensors are located at respective corners of the mobile device, or at other locations around its periphery. The system processes the visual data to determine a pose of the mobile device. Further, the system can determine a location of the mobile device in the environment based on the pose, and can present an indication of the location of the mobile device in the environment.