Based on the eye movement data of subjects detected by eye tracker, a new eye movement index, the percentage change of eyelid spacing, is put forward. Then it is compared with such traditional eye movement indices as saccade count and pupil diameter. After significance and correlation analysis, the receiver operating characteristic (ROC) curve is used to evaluate the discriminant performance of every eye movement on the lens comfort. Experimental results show that the proposed percentage change of eyelid spacing is the best indicator to evaluate the lens comfort, followed by the pupil diameter, and the saccade index and the average fixation duration are the similar. It validates that the lens comfort can be evaluated accurately and quickly by detecting the percentage change of eyelid spacing of subjects. This research can help relevant practitioners to evaluate the lens comfort from an objective perspective, and also provides some technical and theoretical help for increasingly severe myopia prevention and control situation of China.
表 3 眼动指标的AUCTable 3 AUC for eye movement index
表 2 眼动指标与舒适度的相关性Table 2 Correlation between eye movement index and comfort
表 1 眼动指标相关性Table 1 Correlation of eye movement index
图1 aSeeGlasses眼镜式眼动仪Fig.1 aSeeGlasses eye tracker
图2 眨眼过程Fig.2 Blinking process
图3 眼睑间距箱线图Fig.3 Boxplot of eyelid spacing
图4 眼动指标的显著性Fig.4 Significance of eye movement index
图5 眼动指标的ROC曲线Fig.5 ROC curvers for eye movement index
图1 Overall framework and detail diagram of SiamADNFig.1
图2 Structure of channel attention moduleFig.2
图3 General structure of Corner detectionFig.3
图4 Overall flowchart of the proposed methodFig.4
图5 Evaluation results of trackers on OTB-2015 DatasetFig.5
图6 Comparisons among recent update trackers on UAV123Fig.6
图7 Comparisons on the LaSOT with state-of-the-art tracking methods by using success and precision plotsFig.7
图8 Example tracking results of our approach with other siamese network based trackers on the drone datasetsFig.8