NEAR-FUTURE OBJECT POSITION PREDICTION SYSTEM

Title:

NEAR-FUTURE OBJECT POSITION PREDICTION SYSTEM

Document Type and Number:

WIPO Patent Application WO/2022/146000

Kind Code:

A1

Abstract:

The present invention relates to a near-future object position prediction system which learns a current time image, captured by a camera, on the basis of artificial intelligence to sample a model estimating the position of a dynamic object, and predicts a near-future position of the dynamic object by learning to change the dynamic object position estimation model to a probabilistic model using historical data.

More Like This:

WO/2023/036334	METHODS AND SYSTEMS FOR IMAGE PROCESSING
WO/2022/198010	BRAIN IMAGE SEGMENTATION USING TRAINED CONVOLUTIONAL NEURAL NETWORKS
WO/2022/181879	DEEP LEARNING MODEL-BASED TUMOR-STROMA RATIO PREDICTION METHOD AND ANALYSIS DEVICE

Inventors:

KIM JIN HYUCK (KR)
LIM JIN WOOK (KR)

Application Number:

PCT/KR2021/020095

Publication Date:

July 07, 2022

Filing Date:

December 28, 2021

Export Citation:

Click for automatic bibliography generation Help

Assignee:

AIMATICS CO LTD (KR)

International Classes:

G06N3/08; G06N3/04; G06T3/40; G06T7/11; G06T7/136; G06T7/20

Foreign References:

JP2019207220A	2019-12-05
US20200401821A1	2020-12-24
US20190094875A1	2019-03-28
US20180075303A1	2018-03-15
KR20200136905A	2020-12-08

Attorney, Agent or Firm:

INNOLAW PATENT FIRM (KR)

Download PDF:

View/Download PDF PDF Help

Previous Patent: ARTIFICIAL-INTELLIGENCE-BASED CERVICAL CANCER SCREENING SERVICE SYSTEM

Next Patent: METHOD AND DEVICE FOR DETECTING MISFIRING CYLINDER OF RECIPROCATING INTERNAL-COMBUSTION ENGINE BY US...