Comparative Analysis of Kinect-Based and Oculus-Based Gaze Region Estimation Methods in a Driving Simulator

📄 arXiv: 2402.05248v1 📥 PDF

作者: David González-Ortega, Francisco Javier Díaz-Perna, Mario Martínez-Zarzuela, Míriam Antón-Rodríguez

分类: cs.CV

发布日期: 2024-02-04

备注: 25 pages

期刊: Sensors 2021, 21, 26

DOI: 10.3390/s21010026

💡 一句话要点

提出基于Oculus的注视区域估计方法以提升驾驶模拟器性能

🎯 匹配领域: 支柱九：具身大模型 (Embodied Foundation Models)

关键词: 注视估计 虚拟现实 驾驶模拟器 Kinect Oculus Rift 多模态分析 驾驶安全 人机交互

📋 核心要点

  1. 现有的注视估计方法在准确性和实时性上存在不足，尤其是在复杂驾驶场景中。
  2. 本文提出了基于Kinect和Oculus的两种注视区域估计模块，利用头部运动与注视位移的关系进行估计。
  3. 实验结果显示，Oculus Rift的注视区域估计方法在准确性上显著优于Kinect，提升幅度达到97.94%。

📝 摘要（中文）

驾驶员的注视信息在驾驶研究中至关重要，因为它与驾驶员的注意力相关。本文提出了两个集成在驾驶模拟器中的注视区域估计模块，一个使用3D Kinect设备，另一个使用虚拟现实Oculus Rift设备。这些模块能够在每个处理帧中检测驾驶员注视的区域。通过对12名用户的实验，结果表明Oculus Rift在注视估计方面优于Kinect，最高准确率达到97.94%。Oculus Rift模块提供的信息丰富了驾驶模拟器的数据，使得多模态驾驶性能分析成为可能，同时提升了虚拟现实体验的沉浸感和真实感。

🔬 方法详解

问题定义：本文旨在解决现有注视估计方法在驾驶模拟器中准确性不足的问题，尤其是在不同硬件平台下的表现差异。

核心思路：通过集成Kinect和Oculus Rift设备，利用头部运动与注视位移之间的关系，设计了两种注视区域估计模块，以提高估计的准确性和实时性。

技术框架：整体架构包括数据采集模块（Kinect和Oculus），注视区域估计模块（基于简单点和分类器的四种方法），以及结果分析模块。

关键创新：最重要的创新在于将虚拟现实技术与注视估计结合，Oculus Rift的使用显著提升了注视估计的准确性，尤其是在复杂场景下的表现。

关键设计：在设计中，采用了多层感知器（MLP）和支持向量机（SVM）作为分类器，并通过实验优化了参数设置，以确保在不同显示设备下的最佳性能。

📊 实验亮点

实验结果显示，基于Oculus的注视区域估计方法在准确性上达到了97.94%，显著优于Kinect设备的表现。这一结果表明，Oculus Rift在复杂驾驶场景中的应用具有更高的实用价值，能够为驾驶模拟器提供更丰富的数据支持。

🎯 应用场景

该研究的潜在应用领域包括驾驶安全研究、驾驶员行为分析以及虚拟现实训练系统。通过准确的注视区域估计，能够更好地理解驾驶员的注意力分布，从而为改善驾驶安全性和提升驾驶体验提供数据支持。未来，该技术还可扩展到其他需要注视跟踪的领域，如游戏、医疗和人机交互等。

📄 摘要（原文）

Driver's gaze information can be crucial in driving research because of its relation to driver attention. Particularly, the inclusion of gaze data in driving simulators broadens the scope of research studies as they can relate drivers' gaze patterns to their features and performance. In this paper, we present two gaze region estimation modules integrated in a driving simulator. One uses the 3D Kinect device and another uses the virtual reality Oculus Rift device. The modules are able to detect the region, out of seven in which the driving scene was divided, where a driver is gazing at in every route processed frame. Four methods were implemented and compared for gaze estimation, which learn the relation between gaze displacement and head movement. Two are simpler and based on points that try to capture this relation and two are based on classifiers such as MLP and SVM. Experiments were carried out with 12 users that drove on the same scenario twice, each one with a different visualization display, first with a big screen and later with Oculus Rift. On the whole, Oculus Rift outperformed Kinect as the best hardware for gaze estimation. The Oculus-based gaze region estimation method with the highest performance achieved an accuracy of 97.94%. The information provided by the Oculus Rift module enriches the driving simulator data and makes it possible a multimodal driving performance analysis apart from the immersion and realism obtained with the virtual reality experience provided by Oculus.