基于运动感知的VR体验舒适度研究

针对观众在进行虚拟现实(virtual reality,VR)体验后出现眩晕、恶心等不适的问题，建立一种基于运动感知的VR体验舒适度评估方法。通过对立体VR视频进行稠密光流估计，分析场景中的水平运动和垂直运动计算视频帧速度矩阵，提出了基于帧差法和基于时域的帧加速度特征提取方法，将提取的速度、加速度等运动特征结合支持向量回归算法建立VR体验舒适度评估模型。实验结果表明，基于时域帧加速度特征的评估模型优于基于帧差法的模型，且性能较现有其它模型更接近主观评价值，均方根误差减小到7.0,Pearson相关系数提高到0.955 3。

Research on VR Experience Comfort Based on Motion Perception

A VR video comfort evaluation model based on motion perception is proposed for viewers who will feel discomfort such as vertigo and nausea after a virtual reality (VR) experience. By performing dense optical flow estimation on stereoscopic VR video and calculating the video frame velocity matrix by analyzing the horizontal and vertical motions in the scene, the frame acceleration feature extraction methods based on frame difference method and based on time domain are proposed. Taking the extracted velocity, acceleration and other motions features as input, a model is established using the support vector regression algorithm, and VR video experience comfort could be evaluated. The experiment shows that our model performs better than other models for introducing time-domain frame acceleration, and the results are closer to subjective evaluation values. The root mean square error (RMSE) is reduced to 7.0, and the Pearson linear correlation coefficient (PLCC) is increased to 0.955 3.