Global Patent Index - EP 3782075 A4

EP 3782075 A4 20211229 - SYSTEM FOR REAL-TIME OBJECT DETECTION AND RECOGNITION USING BOTH IMAGE AND SIZE FEATURES

Title (en)

SYSTEM FOR REAL-TIME OBJECT DETECTION AND RECOGNITION USING BOTH IMAGE AND SIZE FEATURES

Title (de)

SYSTEM ZUR ECHTZEIT-OBJEKTDETEKTION UND -ERKENNUNG MIT SOWOHL BILD- ALS AUCH GRÖSSENMERKMALEN

Title (fr)

SYSTÈME DE DÉTECTION ET DE RECONNAISSANCE D'OBJETS EN TEMPS RÉEL À L'AIDE DE CARACTÉRISTIQUES D'IMAGE ET DE TAILLE

Publication

EP 3782075 A4 20211229 (EN)

Application

EP 19789101 A 20190214

Priority

  • US 201862659100 P 20180417
  • US 2019018119 W 20190214

Abstract (en)

[origin: WO2019203921A1] Described is an object recognition system. Using an integral channel features (ICF) detector, the system extracts a candidate target region (having an associated original confidence score representing a candidate object) from an input image of a scene surrounding a platform. A modified confidence score is generated based on a location and height of detection of the candidate object. The candidate target regions are classified based on the modified confidence score using a trained convolutional neural network (CNN) classifier, resulting in classified objects. The classified objects are tracked using a multi-target tracker for final classification of each classified object as a target or non-target. If the classified object is a target, a device can be controlled based on the target.

IPC 8 full level

G06N 3/04 (2006.01); G06N 3/08 (2006.01); G06T 7/11 (2017.01); G06T 7/292 (2017.01); G06V 10/143 (2022.01); G06V 10/145 (2022.01); G06V 10/25 (2022.01); G06V 20/13 (2022.01)

CPC (source: EP US)

G06F 18/24133 (2023.01 - EP); G06F 18/24143 (2023.01 - EP); G06F 18/24323 (2023.01 - EP); G06F 18/254 (2023.01 - EP); G06N 3/045 (2023.01 - EP); G06N 3/047 (2023.01 - EP); G06N 3/08 (2013.01 - EP US); G06V 10/143 (2022.01 - EP US); G06V 10/145 (2022.01 - EP US); G06V 10/25 (2022.01 - EP US); G06V 10/454 (2022.01 - EP US); G06V 10/507 (2022.01 - EP US); G06V 10/82 (2022.01 - EP US); G06V 20/58 (2022.01 - EP US); G06V 20/13 (2022.01 - EP US); G06V 20/52 (2022.01 - EP US)

Citation (search report)

  • [XI] LU KEYU ET AL: "Efficient deep network for vision-based object detection in robotic applications", NEUROCOMPUTING, vol. 245, 1 July 2017 (2017-07-01), pages 31 - 45, XP029978678, ISSN: 0925-2312, DOI: 10.1016/J.NEUCOM.2017.03.050
  • [I] ZONGQING LU ET AL: "Pedestrian detection aided by scale-discriminative network", 2016 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (SSCI), IEEE, 6 December 2016 (2016-12-06), pages 1 - 7, XP033066467, DOI: 10.1109/SSCI.2016.7850112
  • [A] DONG PEILEI ET AL: "Mask-streaming CNN for pedestrian detection", 2017 IEEE VISUAL COMMUNICATIONS AND IMAGE PROCESSING (VCIP), IEEE, 10 December 2017 (2017-12-10), pages 1 - 4, XP033325734, DOI: 10.1109/VCIP.2017.8305054
  • [A] SUDOWE PATRICK ET AL: "Efficient Use of Geometric Constraints for Sliding-Window Object Detection in Video", 20 September 2011, ICIAP: INTERNATIONAL CONFERENCE ON IMAGE ANALYSIS AND PROCESSING, 17TH INTERNATIONAL CONFERENCE, NAPLES, ITALY, SEPTEMBER 9-13, 2013. PROCEEDINGS; [LECTURE NOTES IN COMPUTER SCIENCE; LECT.NOTES COMPUTER], SPRINGER, BERLIN, HEIDELBERG, PAGE(S) 11 - 20, ISBN: 978-3-642-17318-9, XP047370157
  • [A] ZHANG SHANSHAN ET AL: "Towards Reaching Human Performance in Pedestrian Detection", IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, vol. 40, no. 4, 1 April 2018 (2018-04-01), USA, pages 973 - 986, XP055862337, ISSN: 0162-8828, Retrieved from the Internet <URL:https://ieeexplore.ieee.org/ielx7/34/8306529/07917260.pdf?tp=&arnumber=7917260&isnumber=8306529&ref=aHR0cHM6Ly9pZWVleHBsb3JlLmllZWUub3JnL2Fic3RyYWN0L2RvY3VtZW50Lzc5MTcyNjA/Y2FzYV90b2tlbj1Mc0toVFdlUWQwc0FBQUFBOktMNGJnY1lWR052TWlTLXd0aHA4MUQwbHp6NEZFMmZlMVhYM2hZODBEZ2pEYnRwM0ZjdWlnbkppRUN6dTZoYmE4ZFpf> [retrieved on 20211116], DOI: 10.1109/TPAMI.2017.2700460
  • See also references of WO 2019203921A1

Designated contracting state (EPC)

AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

DOCDB simple family (publication)

WO 2019203921 A1 20191024; CN 111801689 A 20201020; EP 3782075 A1 20210224; EP 3782075 A4 20211229

DOCDB simple family (application)

US 2019018119 W 20190214; CN 201980016839 A 20190214; EP 19789101 A 20190214