DoorINet: A Deep-Learning Inertial Framework for Door-Mounted IoT Applications

• URL: http://arxiv.org/abs/2402.09427v1
• Date: Wed, 24 Jan 2024 05:28:29 GMT
• Title: DoorINet: A Deep-Learning Inertial Framework for Door-Mounted IoT Applications
• Authors: Aleksei Zakharchenko, Sharon Farber, Itzik Klein
• Abstract summary: We propose DoorINet, an end-to-end deep-learning framework to calculate the heading angle from door-mounted, low-cost inertial sensors without using magnetometers. We record a unique dataset containing 391 minutes of accelerometer and gyroscope measurements and corresponding ground-truth heading angle.
• Score: 2.915868985330569
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Many Internet of Things applications utilize low-cost, micro, electro-mechanical inertial sensors. A common task is orientation estimation. To tackle such a task, attitude and heading reference system algorithms are applied. Relying on the gyroscope readings, the accelerometer readings are used to update the attitude angles, and magnetometer measurements are utilized to update the heading angle. In indoor environments, magnetometers suffer from interference that degrades their performance. This mainly influences applications focused on estimating the heading angle like finding the heading angle of a closet or fridge door. To circumvent such situations, we propose DoorINet, an end-to-end deep-learning framework to calculate the heading angle from door-mounted, low-cost inertial sensors without using magnetometers. To evaluate our approach, we record a unique dataset containing 391 minutes of accelerometer and gyroscope measurements and corresponding ground-truth heading angle. We show that our proposed approach outperforms commonly used, model based approaches and data-driven methods.

Related papers

• ARS-DETR: Aspect Ratio-Sensitive Detection Transformer for Aerial Oriented Object Detection [55.291579862817656]
  Existing oriented object detection methods commonly use metric AP$_50$ to measure the performance of the model. We argue that AP$_50$ is inherently unsuitable for oriented object detection due to its large tolerance in angle deviation. We propose an Aspect Ratio Sensitive Oriented Object Detector with Transformer, termed ARS-DETR, which exhibits a competitive performance.
  arXiv  Detail & Related papers  (2023-03-09T02:20:56Z)
• Deep Learning for Inertial Sensor Alignment [1.9773109138840514]
  We propose a data-driven approach to learn the yaw mounting angle of a smartphone equipped with an inertial measurement unit (IMU) and strapped to a car. The proposed model uses only the accelerometer and gyroscope readings from an IMU as input. The trained model is deployed on an Android device and evaluated in real-time to test the accuracy of the estimated yaw mounting angle.
  arXiv  Detail & Related papers  (2022-12-10T07:50:29Z)
• Support Vector Machine for Determining Euler Angles in an Inertial Navigation System [55.41644538483948]
  The paper discusses the improvement of the accuracy of an inertial navigation system created on the basis of MEMS sensors using machine learning (ML) methods. The proposed algorithm based on MO has demonstrated its ability to correctly classify in the presence of noise typical for MEMS sensors.
  arXiv  Detail & Related papers  (2022-12-07T10:01:11Z)
• Gate-based spin readout of hole quantum dots with site-dependent $g-$factors [101.23523361398418]
  We experimentally investigate a hole double quantum dot in silicon by carrying out spin readout with gate-based reflectometry. We show that characteristic features in the reflected phase signal arising from magneto-spectroscopy convey information on site-dependent $g-$factors in the two dots.
  arXiv  Detail & Related papers  (2022-06-27T09:07:20Z)
• Position fixing with cold atom gravity gradiometers [56.45088569868981]
  We propose a position fixing method for autonomous navigation using partial gravity gradient solutions from cold atom interferometers. Using standard open source global gravity databases, we show stable navigation solutions for trajectories of over 1000km.
  arXiv  Detail & Related papers  (2022-04-11T16:42:32Z)
• Incremental learning of LSTM framework for sensor fusion in attitude estimation [2.064612766965483]
  This paper presents a novel method for attitude estimation of an object in 3D space by incremental learning of the Long-Short Term Memory (LSTM) network. Inertial sensors data are fed to the LSTM network which are then updated incrementally to incorporate the dynamic changes in motion occurring in the run time. The proposed framework offers a significant improvement in the results compared to the traditional method, even in the case of a highly dynamic environment.
  arXiv  Detail & Related papers  (2021-08-04T09:03:53Z)
• IDOL: Inertial Deep Orientation-Estimation and Localization [18.118289074111946]
  Many smartphone applications use inertial measurement units (IMUs) to sense movement, but the use of these sensors for pedestrian localization can be challenging. Recent data-driven inertial odometry approaches have demonstrated the increasing feasibility of inertial navigation. We present a two-stage, data-driven pipeline using a commodity smartphone that first estimates device orientations and then estimates device position.
  arXiv  Detail & Related papers  (2021-02-08T06:41:47Z)
• Deep Soft Procrustes for Markerless Volumetric Sensor Alignment [81.13055566952221]
  In this work, we improve markerless data-driven correspondence estimation to achieve more robust multi-sensor spatial alignment. We incorporate geometric constraints in an end-to-end manner into a typical segmentation based model and bridge the intermediate dense classification task with the targeted pose estimation one. Our model is experimentally shown to achieve similar results with marker-based methods and outperform the markerless ones, while also being robust to the pose variations of the calibration structure.
  arXiv  Detail & Related papers  (2020-03-23T10:51:32Z)
• On the Arbitrary-Oriented Object Detection: Classification based Approaches Revisited [94.5455251250471]
  We first show that the boundary problem suffered in existing dominant regression-based rotation detectors, is caused by angular periodicity or corner ordering. We transform the angular prediction task from a regression problem to a classification one. For the resulting circularly distributed angle classification problem, we first devise a Circular Smooth Label technique to handle the periodicity of angle and increase the error tolerance to adjacent angles.
  arXiv  Detail & Related papers  (2020-03-12T03:23:54Z)
• Under the Radar: Learning to Predict Robust Keypoints for Odometry Estimation and Metric Localisation in Radar [26.382149876115918]
  We run experiments on 280km of real world driving from the Oxford Radar RobotCar dataset. We improve on the state-of-the-art in point-based radar odometry, reducing errors by up to 45%. We provide a framework capable of full mapping and localisation with radar in urban environments.
  arXiv  Detail & Related papers  (2020-01-29T12:59:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.