IP Library Granted Patent US 12,423,840
Granted Patent B2
US 12,423,840 · App. 18/296,101 · Granted Sep 23, 2025

Method and system for binocular ranging for children

Inventor: Shuicai Huang (Hangzhou, CN)
Assignees: DONGSHENG SHENZHOU TOURISM MANAGEMENT CO., LTD.; ZHEJIANG LINGCHUANG NETWORK TECHNOLOGY CO., LTD.
G06T7/50G06V10/774G06V40/172G06V40/18G06T2207/20081G06T2207/30201
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,423,840
App. No.
18/296,101
Granted
Sep 23, 2025
Kind
B2
Abstract

A method for binocular ranging for children is provided in this disclosure, which includes following steps: acquiring an image of a target area and world coordinates of a human body in left and right eyes; correcting the image to obtain a corrected image of the target area; performing face detection on the corrected image of the target area to obtain a face image and an eye image; recognizing the face image and determining whether the face image is a child's face; if yes, performing image correction based on the obtained face image; inputting the eye image into a preset eye recognition model for recognition whether the human eye is staring at a screen; and performing ranging on the eye image based on the world coordinates of the human body to obtain a distance between the screen and the human eye, if the human eye is staring at the screen.

Claims (26)

1. A method for binocular ranging for children, comprising following steps:

acquiring, by a binocular camera, an image of a target area and world coordinates of a human body in left and right eyes;

correcting, by a processor connected with the binocular camera, the image of the target area so as to obtain a corrected image of the target area;

performing, by the processor, face detection on the corrected image of the target area so as to obtain a face image and an eye image;

recognizing, by the processor, the face image based on a preset face recognition model and determining whether the face image is a child's face or not;

inputting, by the processor, the eye image into a preset eye recognition model for recognition and determining whether the human eye is staring at a screen or not; and

performing, by the processor, ranging on the eye image based on the world coordinates of the human body so as to obtain a distance between the screen and the human eye, if the human eye is staring at the screen.

2. The method for binocular ranging for the children according to claim 1 , further comprising determining whether the distance between the screen and the human eye is greater than a set value, and if yes, triggering a reminder.

3. The method for binocular ranging for the children according to claim 1 , wherein the correcting, by the processor, the image comprises parameter collection, distortion removing and stereo rectification, so as to obtain corrected image information.

4. The method for binocular ranging for the children according to claim 1 , wherein performing the face detection so as to process the image information with the face recognition model comprises image detecting, person positioning and image segmenting so as to obtain a segmented face image and eye image.

5. The method for binocular ranging for the children according to claim 1 , wherein the face recognition model is established by following steps:

acquiring, by the processor, a training sample, the training sample comprises a sample face image and labeled face discrimination information;

the sample face image being face images for 4 to 16 year old; and

taking, by the processor, the face image of the face training sample as input and the labeled face discrimination information as output to perform training so as to obtain the face recognition model.

6. The method for binocular ranging for the children according to claim 1 , wherein the eye recognition model is established by following steps:

acquiring, by the processor, a training sample, the training sample comprising a sample eye image and labeled eye discrimination information;

the sample eye image being an image in which a gaze direction of a human eye is within 15 degree in four directions of up, down, left and right directions; and

taking, by the processor, the sample eye image as input and the labeled eye discrimination information as output to perform training so as to obtain the eye recognition model.

7. A system for binocular ranging for children, comprising: a computer device, wherein an image acquisition module, a stereo rectification module, a face detection module, a face matching module, an eye gaze direction detection module and a ranging module can be stored in a memory of the computer device and executed on the computer device;

the image acquisition module is configured for acquiring an image of a target area and world coordinates of a human body in left and right eyes;

the stereo rectification module is configured for correcting the image of the target area so as to obtain a corrected image of the target area;

the face detection module is configured for performing face detection on the corrected image of the target area so as to obtain a face image and an eye image;

the face matching module is configured to recognize the face image based on a preset face recognition model and determine whether the face image is a child's face or not;

the eye gaze direction detection module is configured for detecting whether a gaze direction of human eyes is in a direction toward a screen; and

the ranging module is configured for ranging between the screen and the human eyes.

8. The system for binocular ranging for children according to claim 7 , wherein the image acquisition module is a binocular camera, which comprises two camera sensors arranged at intervals.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 11, 2023
From: HUANG, SHUICAI
To: DONGSHENG SHENZHOU TOURISM MANAGEMENT CO., LTD.; ZHEJIANG LINGCHUANG NETWORK TECHNOLOGY CO., LTD.
Reel/Frame 063282/0660 →
Priority Claims (1)
CN 202111092737.7 · Sep 17, 2021 · national
Continuity (2)
Continuation PCTCN2022113464 · Aug 19, 2022
Related Publication 20230237682A1 · Jul 27, 2023
References Cited (17)
US 8451326B2 · Inaba · 2013 [cited by examiner]
US 8970681B2 · Son · 2015 [cited by examiner]
US 11754856B2 · Yoshida · 2023 [cited by examiner]
US 20160142673A1 · Rao · 2016 [cited by examiner]
US 20180095528A1 · Tao · 2018 [cited by examiner]
US 20190147241A1 · Shudo · 2019 [cited by examiner]
US 20190208181A1 · Rowell · 2019 [cited by examiner]
US 20220092880A1 · Takei · 2022 [cited by examiner]
US 20220207662A1 · Gupta · 2022 [cited by examiner]
US 20230237694A1 · Huang · 2023 [cited by examiner]
US 20230237699A1 · Huang · 2023 [cited by examiner]
US 20240221423A1 · Wang · 2024 [cited by examiner]
US 20240379206A1 · Thompson · 2024 [cited by examiner]
CN 107369305A · 2017 [cited by applicant]
CN 110780739A · 2020 [cited by applicant]
CN 113808207A · 2021 [cited by applicant]
WO WO2017152649A1 · 2017 [cited by applicant]