IP Library › Granted Patent US 12,639,826
Granted Patent B2
US 12,639,826 · App. 18/088,433 · Granted May 26, 2026

Method and device of binding security inspection information, electronic apparatus, and readable storage medium

Inventors: Ziran Zhao (Beijing, CN); Jianping Gu (Beijing, CN); Yingxin Wang (Beijing, CN); Shaoming Yuan (Beijing, CN); Li Gu (Beijing, CN); Yitao Jiao (Beijing, CN)
Assignees: NUCTECH COMPANY LIMITED; Tsinghua University; Beijing Shenmutek Company Limited
G06T7/20G01N23/04G06V10/44G06V10/761G06T2207/30112G06T2207/30196G06V2201/07
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 12,639,826
App. No.
18/088,433
Granted
May 26, 2026
Kind
B2
Abstract

Provided are a method and a device of binding security inspection information, an electronic apparatus and a storage medium, which may be applied to the field of security inspection technology. In the method of binding security inspection information of the present disclosure, the pedestrian detection frame is acquired by detecting the video stream, and each pedestrian detection frame has the coordinate information and the tracking information. According to the coordinate information and the tracking information of the pedestrian detection frame, the baggage security inspection information, the pedestrian security inspection information, and the identity information are bound to acquire all security inspection information of a detected person, so that a security inspection efficiency is improved.

Claims (42)

1 . A method of binding security inspection information, comprising:

acquiring a video stream of pedestrians at each position in a security inspection channel, detecting the video stream to acquire a pedestrian detection frame, wherein the pedestrian detection frame has a coordinate information in a three-dimensional coordinate space and a tracking information;

extracting a pedestrian feature through the pedestrian detection frame, and continuously tracking each pedestrian in the video stream according to the pedestrian feature and the coordinate information;

verifying an identity information of a pedestrian by an identity verification device through face recognition, scanning of identity card, and ticket inspection, and binding the verified identity information with the tracking information, wherein the verified identity information is used to allow the pedestrian to enter the security inspection channel;

binding a baggage deposition information with the tracking information at a baggage placement site;

acquiring a baggage security inspection information and the baggage deposition information detected by a detection apparatus, and binding the baggage security inspection information with the tracking information according to the baggage deposition information;

acquiring a pedestrian security inspection information by a human body security inspection device by performing security inspection on the pedestrian when the pedestrian passes through the human body security inspection device, and binding the pedestrian security inspection information with the tracking information; and

binding the baggage security inspection information, the pedestrian security inspection information and the identity information according to the tracking information,

wherein the baggage deposition information comprises a baggage placement table number and a baggage basket number, and

wherein the binding a baggage deposition information with the tracking information at a baggage placement site comprises:

acquiring a baggage placement table number and a baggage basket number;

acquiring a placement table coordinate of the baggage placement table according to the baggage placement table number;

searching a tracking information of the pedestrian detection frame within a preset range of the placement table coordinate, and selecting the pedestrian detection frame closest to the placement table coordinate as a baggage depositor; and

binding a tracking information of the baggage depositor with the baggage basket number.

2 . The method according to claim 1 , wherein the coordinate information is converted from a global coordinate system where the security inspection channel is located and a relative coordinate system where the detection apparatus is located, and

wherein the coordinate information comprises an x-axis coordinate and a y-axis coordinate that are parallel to a horizontal plane and perpendicular to each other, and a z-axis coordinate perpendicular to the horizontal plane, and the coordinate information is acquired by a depth image calculation.

3 . The method according to claim 2 , wherein the detection apparatus comprises at least one of the identity verification device, a camera device, the human body security inspection device, a baggage placement device and a baggage security inspection device.

4 . The method according to claim 1 , wherein the extracting a pedestrian feature through the pedestrian detection frame comprises:

intercepting a pedestrian image on a visible light image of the video stream by using the pedestrian detection frame, and extracting a pedestrian feature of the pedestrian image by using a feature extraction network.

5 . The method according to claim 1 , wherein the video stream is acquired through at least one camera,

wherein the continuously tracking each pedestrian in the video stream according to the pedestrian feature and the coordinate information comprises:

continuously tracking each pedestrian in a single-camera video stream, and

continuously tracking each pedestrian in a multi-camera video stream.

6 . The method according to claim 5 , wherein the continuously tracking each pedestrian in a single-camera video stream comprises:

matching and associating the pedestrian detection frame of a current frame in the single-camera video stream with pedestrian detection frames of adjacent frames in the single-camera video stream to continuously track each pedestrian,

wherein the pedestrian features of the matched and associated pedestrian detection frame of the current frame and pedestrian detection frames of adjacent frames meet a preset feature similarity, and the coordinate information of the matched and associated pedestrian detection frame of the current frame and pedestrian detection frames of adjacent frames meets a preset distance.

7 . The method according to claim 5 , wherein the continuously tracking each pedestrian in a multi-camera video stream comprises:

matching and associating pedestrian detection frames having a same tracking information in a same time period in video streams shot by different cameras to continuously track each pedestrian,

wherein the pedestrian features of the matched and associated pedestrian detection frames meet a preset feature similarity, and the coordinate information of the matched and associated pedestrian detection frames meets a preset distance.

8 . The method according to claim 1 , wherein the acquiring a baggage security inspection information and the baggage deposition information detected by a detection apparatus, and binding the baggage security inspection information with the tracking information according to the baggage deposition information comprises:

performing a ray irradiation on the baggage through the detection apparatus to generate the baggage security inspection information, wherein the baggage security inspection information comprises a ray radiation image;

performing a ray irradiation on the baggage basket through the detection apparatus, acquiring a ray radiation image of the baggage basket, processing the ray radiation image of the baggage basket and acquiring the baggage basket number; and

binding the tracking information bound with the baggage basket with the baggage security inspection information.

9 . The method according to claim 1 , wherein the acquiring a pedestrian security inspection information detected by the detection apparatus, and binding the pedestrian security inspection information with the tracking information comprises:

acquiring the pedestrian security inspection information detected by the detection apparatus;

acquiring a coordinate of the detection apparatus according to the pedestrian security inspection information;

searching a tracking information of the pedestrian detection frame within a preset range of the coordinate of the detection apparatus, and selecting the pedestrian detection frame closest to the coordinate of the detection apparatus as a target pedestrian detection frame; and

binding the pedestrian security inspection information with a tracking information of the target pedestrian detection frame.

10 . An electronic apparatus, comprising:

one or more processors; and

a storage device for storing executable instructions, wherein the executable instructions, when being executed by the processor, implement the method according to claim 1 .

11 . A non-transitory computer-readable storage medium having executable instructions thereon, wherein the instructions, when being executed by a processor, implement the method according to claim 1 .

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 17, 2026
From: ZHAO, ZIRAN; GU, JIANPING; WANG, YINGXIN; YUAN, SHAOMING; GU, LI; JIAO, YITAO
To: NUCTECH COMPANY LIMITED; TSINGHUA UNIVERSITY; BEIJING SHENMUTEK COMPANY LIMITED
Reel/Frame 074398/0219 →
Priority Claims (1)
CN 202111617954.3 · Dec 27, 2021 · national
Continuity (1)
Related Publication 20230206463A1 · Jun 29, 2023
References Cited (28)
US 8670595B2 · Satoh · 2014 [cited by applicant]
US 9965687B2 · Loce · 2018 [cited by examiner]
US 10157317B2 · Chen · 2018 [cited by examiner]
US 10896327B1 · Lablans · 2021 [cited by examiner]
US 20040124982A1 · Kovach · 2004 [cited by applicant]
US 20120128214A1 · Satoh · 2012 [cited by applicant]
US 20180216957A1 · Bekkerman et al. · 2018 [cited by applicant]
US 20190180398A1 · Chen et al. · 2019 [cited by applicant]
US 20190333233A1 · Hu · 2019 [cited by examiner]
US 20210082130A1 · Crain · 2021 [cited by examiner]
US 20210287503A1 · Tarui · 2021 [cited by examiner]
CN 102479436A · 2012 [cited by applicant]
CN 109725010A · 2019 [cited by applicant]
CN 109725011A · 2019 [cited by examiner]
CN 110309717A · 2019 [cited by applicant]
CN 111601076A · 2020 [cited by examiner]
CN 111783915A · 2020 [cited by examiner]
CN 111899258A · 2020 [cited by examiner]
CN 112015931A · 2020 [cited by applicant]
CN 112100196A · 2020 [cited by applicant]
CN 112131919A · 2020 [cited by examiner]
CN 112182270A · 2021 [cited by applicant]
CN 112948615A · 2021 [cited by applicant]
CN 112949577A · 2021 [cited by applicant]
CN 113408405A · 2021 [cited by applicant]
CN 113850990A · 2021 [cited by applicant]
Office Action dated Oct. 10, 2025 for corresponding Chinese Application No. 202111617954.3 (20 pages including English Translation). [cited by applicant]
English Translation of International Search Report of corresponding PCT Application No. PCT/CN2022/127688 dated Jan. 17, 2023 (2 pages). [cited by applicant]