白丝美女被狂躁免费视频网站,500av导航大全精品,yw.193.cnc爆乳尤物未满,97se亚洲综合色区,аⅴ天堂中文在线网官网

Augmented reality field of view based on sensed user data

專利號
US11176753B1
公開日期
2021-11-16
申請人
INTERNATIONAL BUSINESS MACHINES CORPORATION(US NY Armonk)
發(fā)明人
Divya Kannan Chakravarthi; Kriteshwar Kaur Kohli; Vinod A. Valecha; John A. Lyons
IPC分類
G06T19/00; G06F3/01; G06K9/00; G06N20/00
技術領域
or,ar,stress,computing,in,world,augmented,user,inducing,real
地域: NY NY Armonk

摘要

User-specific augmentation of a real word field of view viewable through an augmented reality (AR) device is facilitated by a processor(s) receiving image data representative of a real world field of view viewable by a user through the AR device, and receiving sensor data indicative of the user's stress level, which is related, at least in part, to the user's real world field of view viewable through the AR device. The processor(s) processes the image data, based on the user's stress level, to identify one or more stress-inducing elements to be hidden in the real world field of view viewable through the AR device. Further, the processor(s) provides an augmented real world field of view for display to the user through the AR device, where the one or more stress-inducing elements are hidden from the user in the augmented real world field of view.

說明書

FIG. 4 is an example machine-learning training system 400 that can be utilized to perform machine-learning, such as described herein. Training data 410 used to train the model in embodiments of the present invention can include a variety of types of data, such as data generated by the AR device and/or sensors. Program code, in embodiments of the present invention, can perform machine-learning analysis to generate data structures, including algorithms utilized by the program code to perform the image processing and augmentation facility, as disclosed herein. Machine-learning (ML) solves problems that cannot be solved by numerical means alone. In this ML-based example, program code extracts various features/attributes from training data 410, which can be stored in memory or one or more databases 420. The extracted features 415 are utilized to develop a predictor function, h(x), also referred to as a hypothesis, which the program code utilizes as a machine-learning model 430. In identifying machine-learning model 430, various techniques can be used to select features (elements, patterns, attributes, etc.), including but not limited to, diffusion mapping, principle component analysis, recursive feature elimination (a brute force approach to selecting features), and/or a random forest, to select the attributes related to the user's condition, and/or to the image processing and augmentation. Program code can utilize a machine-learning algorithm 440 to train machine-learning model 430 (e.g., the algorithms utilized by the program code), including providing weights for conclusions, so that the program code can train any predictor or performance functions included in the machine-learning model 440, such as whether the user is likely to intersect with one or more stress-inducing element(s) based on determined trajectories. The conclusions can be evaluated by a quality metric 450. By selecting a diverse set of training data 410, the program code trains the machine-learning model(s) 440 to identify and weight various attributes (e.g., features, patterns) that correlate to enhance performance of the machine-learning implemented by the computing resource(s) and/or the AR device.

權利要求

1
微信群二維碼
意見反饋