System and method for detecting region of interest of user based on consumer-grade gaze tracker

Abstract

The invention discloses a user region-of-interest detection system and method based on a consumer-level line-of-sight tracker. The system comprises a consumer-level telemetry sight line tracker, a display and a processor. The consumer-level telemetry sight line tracker is used for providing gaze point coordinate information and timestamp information corresponding to each gaze point when a user observes a picture to the processor; The display is used for displaying a picture or scene needing to be observed and a result of detecting the user interest area to the user; And the processor is used for processing the original data provided by the consumer-level telemetry sight line tracker, carrying out high-order feature extraction on the original data, identifying the region of interest of theuser by utilizing the obtained high-order features, and inputting an identification result into the display for displaying. According to the invention, the purpose of low-cost user intention identification is achieved by extracting the high-order gaze characteristics from the original gaze point data.

Description

technical field [0001] The invention belongs to the technical field of image detection, and in particular relates to a system and method for detecting a region of interest of a user. Background technique [0002] Human sight contains a lot of potential intention information, therefore, fixation intention recognition also provides a new way for human-computer interaction. For the disabled, the non-contact gaze point-based object-of-interest recognition system can provide them with an interactive interface with computers and robotic arms, thereby helping them improve their quality of life. In view of this, how to realize the detection of the region of interest of the user by using the gaze point is a problem of great application value and prospect. [0003] At present, many scholars at home and abroad have carried out research on intent recognition based on gaze points. For professional-level gaze trackers, some existing techniques have designed some methods for extracting r...

AI Technical Summary

Problems solved by technology

However, this recognition solution for professional-grade gaze trackers is expensive and only suitable for laboratory environments

However, consumer-grade gaze trackers in the existing market can only output raw data such as gaze point coordinates and time stamps, which cannot meet the requirements of feature data required by existing gaze point-based user intent recognition systems.

Images