Julian Steil, Marion Koelle, Wilko Heuten, Susanne CJ Boll, A. Bulling
{"title":"PrivacEye:保护隐私的头戴式眼动追踪,使用以自我为中心的场景图像和眼动特征","authors":"Julian Steil, Marion Koelle, Wilko Heuten, Susanne CJ Boll, A. Bulling","doi":"10.1145/3314111.3319913","DOIUrl":null,"url":null,"abstract":"Eyewear devices, such as augmented reality displays, increasingly integrate eye tracking, but the first-person camera required to map a user's gaze to the visual scene can pose a significant threat to user and bystander privacy. We present PrivacEye, a method to detect privacy-sensitive everyday situations and automatically enable and disable the eye tracker's first-person camera using a mechanical shutter. To close the shutter in privacy-sensitive situations, the method uses a deep representation of the first-person video combined with rich features that encode users' eye movements. To open the shutter without visual input, PrivacEye detects changes in users' eye movements alone to gauge changes in the \"privacy level\" of the current situation. We evaluate our method on a first-person video dataset recorded in daily life situations of 17 participants, annotated by themselves for privacy sensitivity, and show that our method is effective in preserving privacy in this challenging setting.","PeriodicalId":161901,"journal":{"name":"Proceedings of the 11th ACM Symposium on Eye Tracking Research & Applications","volume":"12 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"59","resultStr":"{\"title\":\"PrivacEye: privacy-preserving head-mounted eye tracking using egocentric scene image and eye movement features\",\"authors\":\"Julian Steil, Marion Koelle, Wilko Heuten, Susanne CJ Boll, A. Bulling\",\"doi\":\"10.1145/3314111.3319913\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Eyewear devices, such as augmented reality displays, increasingly integrate eye tracking, but the first-person camera required to map a user's gaze to the visual scene can pose a significant threat to user and bystander privacy. We present PrivacEye, a method to detect privacy-sensitive everyday situations and automatically enable and disable the eye tracker's first-person camera using a mechanical shutter. To close the shutter in privacy-sensitive situations, the method uses a deep representation of the first-person video combined with rich features that encode users' eye movements. To open the shutter without visual input, PrivacEye detects changes in users' eye movements alone to gauge changes in the \\\"privacy level\\\" of the current situation. We evaluate our method on a first-person video dataset recorded in daily life situations of 17 participants, annotated by themselves for privacy sensitivity, and show that our method is effective in preserving privacy in this challenging setting.\",\"PeriodicalId\":161901,\"journal\":{\"name\":\"Proceedings of the 11th ACM Symposium on Eye Tracking Research & Applications\",\"volume\":\"12 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2018-01-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"59\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 11th ACM Symposium on Eye Tracking Research & Applications\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3314111.3319913\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 11th ACM Symposium on Eye Tracking Research & Applications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3314111.3319913","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
PrivacEye: privacy-preserving head-mounted eye tracking using egocentric scene image and eye movement features
Eyewear devices, such as augmented reality displays, increasingly integrate eye tracking, but the first-person camera required to map a user's gaze to the visual scene can pose a significant threat to user and bystander privacy. We present PrivacEye, a method to detect privacy-sensitive everyday situations and automatically enable and disable the eye tracker's first-person camera using a mechanical shutter. To close the shutter in privacy-sensitive situations, the method uses a deep representation of the first-person video combined with rich features that encode users' eye movements. To open the shutter without visual input, PrivacEye detects changes in users' eye movements alone to gauge changes in the "privacy level" of the current situation. We evaluate our method on a first-person video dataset recorded in daily life situations of 17 participants, annotated by themselves for privacy sensitivity, and show that our method is effective in preserving privacy in this challenging setting.