Invention Publication
- Patent Title: LEARNING METHOD AND LEARNING DEVICE FOR HETEROGENEOUS SENSOR FUSION BY USING MERGING NETWORK WHICH LEARNS NON-MAXIMUM SUPPRESSION
-
Application No.: EP20152861.9Application Date: 2020-01-21
-
Publication No.: EP3690723A1Publication Date: 2020-08-05
- Inventor: KIM, Kye-Hyeon , KIM, Yongjoong , KIM, Hak-Kyoung , NAM, Woonhyun , BOO, SukHoon , SUNG, Myungchul , SHIN, Dongsoo , YEO, Donghun , RYU, Wooju , LEE, Myeong-Chun , LEE, Hyungsoo , JANG, Taewoong , JEONG, Kyungjoong , JE, Hongmo , CHO, Hojin
- Applicant: StradVision, Inc.
- Applicant Address: Suite 304-308, 5th Venture-dong 394, Jigok-ro Nam-gu Pohang-si Gyeongsangbuk-do 37668 KR
- Assignee: StradVision, Inc.
- Current Assignee: StradVision, Inc.
- Current Assignee Address: Suite 304-308, 5th Venture-dong 394, Jigok-ro Nam-gu Pohang-si Gyeongsangbuk-do 37668 KR
- Agency: AWA Sweden AB
- Priority: US201962799097P 20190131; US201916724301 20191222
- Main IPC: G06K9/00
- IPC: G06K9/00 ; G06K9/32
Abstract:
A learning method for generating integrated object detection information of an integrated image by integrating first object detection information and second object detection information is provided. The method includes steps of: (a) a learning device, if the first object detection information and the second object detection information is acquired, instructing a concatenating network included in a DNN to generate pair feature vectors including information on pairs of first original ROIs and second original ROIs; (b) the learning device instructing a determining network included in the DNN to apply FC operations to the pair feature vectors, to thereby generate (i) determination vectors and (ii) box regression vectors; (c) the learning device instructing a loss unit to generate an integrated loss, and performing backpropagation processes by using the integrated loss, to thereby learn at least part of parameters included in the DNN.
Information query