US 12,444,236 B2
Deep learning-based abnormal behavior detection system and method using anonymized data
Soo Yeon Han, Seoul (KR)
Assigned to UNIUNI CORPORATION, Seoul (KR)
Appl. No. 18/265,364
Filed by UNIUNI CORPORATION, Seoul (KR)
PCT Filed Aug. 30, 2021, PCT No. PCT/KR2021/011583
§ 371(c)(1), (2) Date Jul. 3, 2023,
PCT Pub. No. WO2022/119080, PCT Pub. Date Jun. 9, 2022.
Claims priority of application No. 10-2020-0168545 (KR), filed on Dec. 4, 2020.
Prior Publication US 2024/0046702 A1, Feb. 8, 2024
Int. Cl. G06V 40/20 (2022.01); G06N 3/0464 (2023.01); G06V 10/40 (2022.01); G06V 10/74 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/52 (2022.01)
CPC G06V 40/20 (2022.01) [G06N 3/0464 (2023.01); G06V 10/40 (2022.01); G06V 10/761 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/52 (2022.01)] 8 Claims
OG exemplary drawing
 
1. A deep learning-based abnormal behavior detection system comprising:
a detection device configured to detect a behavior of a subject within a predetermined area and generate anonymized image data;
a deep learning server configured to:
receive the anonymized image data from the detection device;
extract feature information from the anonymized image data;
output behavior prediction information reflecting temporal changes of the feature information;
compare the behavior prediction information with pre-learned behavior patterns to calculate similarity; and
determine whether the behavior prediction information belongs to a normal behavior type or an abnormal behavior type based on the similarity to determine abnormal behavior; and
a web server configured to receive a result of determining the abnormal behavior from the deep learning server and to generate and transmit to a management server or a terminal a warning signal indicating that the behavior of the subject is an abnormal behavior when the anonymized image data is determined to belong to the abnormal behavior type.