高级检索

面向虚拟场景交互任务的分阶段视线预测技术

StagedGaze Prediction in Virtual Scene Interaction Tasks

  • 摘要: 视线预测技术在人机交互、医疗诊断、广告研究、游戏设计等领域中有重要的应用价值. 现有的在虚拟场景中进行视线预测的方法通常使用泛化的模型, 在各类具体交互任务上仍有较大的提升空间. 本文交互任务设置为在虚拟场景中寻找-接近-触碰物体, 首先构建了该任务场景的第一个数据集, 包含21名用户在3个交互场景下各进行5次交互任务过程中记录的注视点、物体、头盔、手柄4类参数序列和录制视频; 进一步将用户完成交互任务的过程分为三个阶段: (1) 寻找目标物体; (2) 锁定目标物体; (3) 接近目标物体. 再逐阶段进行相关性分析, 选择与视线相关度最高的参数集输入网络进行训练. 所提方法在本文构建的数据集上进行验证, 与当前最优算法的3.31°的预测误差相比, 本文提出的模型达到了2.60°的预测误差, 预测误差减小21.45%, 提升了该任务场景下的预测精度.

     

    Abstract: The technique of gaze prediction has significant application value in various fields, including human-computer interaction, medical diagnosis, advertising research, and game design. However, current methods for predicting gaze in virtual scenes typically rely on generalized models and still have considerable room for improvement in specific interactive tasks. This paper focuses on improving gaze prediction for the common interactive pattern of finding, approaching, and touching objects in virtual scenes. We first construct the first dataset for this task, consisting of gaze recordings, object, helmet and controller parameters, as well as recorded videos, during five interacting tasks performed by 21 users in three interactive scenes. The users' completion of the task is divided into three stages: (1) finding the target object; (2) locking onto the target object; and (3) approaching the target object. We then conduct Spearman correlation analysis at each stage, selecting the parameter set with the highest correlation with gaze to input into the network for training. The proposed method is validated on the constructed dataset, achieving a gaze prediction error of 2.60°, which represents a 21.45% improvement over the current best method's error of 3.31°, significantly enhancing gaze prediction accuracy for this task.

     

/

返回文章
返回