Electronic Device Pose Identification Using Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional techniques for identifying a device pose in machine vision applications, such as SLAM, AR, and VR, are slow, leading to mismatches between the actual device pose and displayed content, causing user disorientation due to the delay in generating accurate pose information.
Innovation Solution
The electronic device estimates its pose using both non-image sensor data for rapid pose updates and image sensor data for accuracy, implementing a spatial smoothing process to adjust and refine the pose estimate, ensuring both high-rate and accurate pose identification by combining visual and non-visual pose information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional image-based pose identification techniques are used, then measurement precision is improved, but speed deteriorates
Solution Approach 1:
The patent combines image sensor data with non-image sensor data (accelerometer, gyroscope, magnetometer) to generate pose information. This fusion approach merges the high accuracy of visual data with the high speed of inertial sensor data, resolving the contradiction between measurement precision and speed by leveraging complementary strengths of different sensing modalities
Solution Approach 2:
The patent segments the pose identification process into two parallel pathways: one processing image sensor data for accurate visual pose estimation, and another processing non-image sensor data for rapid inertial pose updates. This segmentation allows each pathway to operate independently at its optimal speed while contributing to the final combined pose result
2Productivity
If image sensor data is processed at high rate, then productivity is improved, but use of energy deteriorates
Solution Approach 1:
The patent applies partial action by using non-image sensor data (which consumes less energy) to generate pose information at high rates for applications requiring speed, while reserving full image sensor processing only for moments when high accuracy is specifically needed. This partial utilization of the more energy-intensive image processing maintains productivity where necessary while reducing overall energy consumption
Data Source
AI summary
An electronic device includes one or more imaging sensors (e.g, imaging cameras) and includes one or more non-image sensors, such as an inertial measurement unit (IMU), that can provide information indicative of the pose of the electronic device. The electronic device estimates its pose based on two independent sources of pose information: pose information generated at a relatively high rate based on non-visual information generated by the non-image sensors and pose information generated at a relatively low rate based on imagery captured by the one or more imaging sensors. To achieve both a high pose-estimation rate and high degree of pose estimation accuracy, the electronic device adjusts a pose estimate based on the non-visual pose information at a high rate, and at a lower rate spatially smoothes the pose estimate based on the visual pose information.