WO2022243337A3 - System for detection and management of uncertainty in perception systems, for new object detection and for situation anticipation - Google Patents

System for detection and management of uncertainty in perception systems, for new object detection and for situation anticipation Download PDF

Info

Publication number
WO2022243337A3
WO2022243337A3 PCT/EP2022/063359 EP2022063359W WO2022243337A3 WO 2022243337 A3 WO2022243337 A3 WO 2022243337A3 EP 2022063359 W EP2022063359 W EP 2022063359W WO 2022243337 A3 WO2022243337 A3 WO 2022243337A3
Authority
WO
WIPO (PCT)
Prior art keywords
uncertainty
detection
map
segment
management
Prior art date
Application number
PCT/EP2022/063359
Other languages
French (fr)
Other versions
WO2022243337A2 (en
WO2022243337A9 (en
Inventor
Ralph Meyfarth
Sven Fuelster
Original Assignee
Deep Safety Gmbh
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Deep Safety Gmbh filed Critical Deep Safety Gmbh
Priority to CN202280050415.2A priority Critical patent/CN117716395A/en
Priority to EP22730378.1A priority patent/EP4341913A2/en
Publication of WO2022243337A2 publication Critical patent/WO2022243337A2/en
Publication of WO2022243337A3 publication Critical patent/WO2022243337A3/en
Publication of WO2022243337A9 publication Critical patent/WO2022243337A9/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Multimedia (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Computing Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Image Analysis (AREA)

Abstract

According to the invention, a perception system is provided that comprises a segmenting neural network (40) and an uncertainty detector (60). The segmenting neural network (40) is configured and trained for segmentation of an input image pixel matrix to thus generate a segment composed of elements that correspond the pixels of the input image pixel matrix. By way of class prediction, each element of the segment map is assigned to one of a plurality of object classes the segmenting neural network is trained for by way of class prediction. Elements being assigned to the same object class form a segment of the segment map. The uncertainty detector (60) is configured to generate an uncertainty score map that is composed of elements that correspond the pixels of the input image pixel matrix. Each element of the uncertainty map has an uncertainty score that is determined by the uncertainty detector and that reflects an amount of uncertainty involved in a class prediction for a corresponding element in the segment map.
PCT/EP2022/063359 2021-05-17 2022-05-17 System for detection and management of uncertainty in perception systems, for new object detection and for situation anticipation WO2022243337A2 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202280050415.2A CN117716395A (en) 2021-05-17 2022-05-17 System for detecting and managing uncertainty, new object detection and situation expectations in a perception system
EP22730378.1A EP4341913A2 (en) 2021-05-17 2022-05-17 System for detection and management of uncertainty in perception systems, for new object detection and for situation anticipation

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
EP21174146 2021-05-17
EP21174146.7 2021-05-17
EP21204038 2021-10-21
EP21204038.0 2021-10-21

Publications (3)

Publication Number Publication Date
WO2022243337A2 WO2022243337A2 (en) 2022-11-24
WO2022243337A3 true WO2022243337A3 (en) 2023-01-12
WO2022243337A9 WO2022243337A9 (en) 2023-03-09

Family

ID=82058472

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2022/063359 WO2022243337A2 (en) 2021-05-17 2022-05-17 System for detection and management of uncertainty in perception systems, for new object detection and for situation anticipation

Country Status (2)

Country Link
EP (1) EP4341913A2 (en)
WO (1) WO2022243337A2 (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7552287B2 (en) * 2020-11-25 2024-09-18 セイコーエプソン株式会社 OBJECT DETECTION METHOD, OBJECT DETECTION DEVICE, AND COMPUTER PROGRAM
CN116935160B (en) * 2023-07-19 2024-05-10 上海交通大学 Training method, sample classification method, electronic equipment and medium
CN117854473B (en) * 2024-01-19 2024-08-06 天津大学 Zero sample speech synthesis method based on local association information

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200033877A1 (en) * 2013-11-27 2020-01-30 Waymo Llc Assisted Perception For Autonomous Vehicles
US20200133281A1 (en) * 2019-12-27 2020-04-30 Intel Corporation Safety system for a vehicle
US10803328B1 (en) * 2017-11-15 2020-10-13 Uatc, Llc Semantic and instance segmentation
WO2020240477A1 (en) * 2019-05-31 2020-12-03 Thales Canada Inc. Method and processing device for training a neural network

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200033877A1 (en) * 2013-11-27 2020-01-30 Waymo Llc Assisted Perception For Autonomous Vehicles
US10803328B1 (en) * 2017-11-15 2020-10-13 Uatc, Llc Semantic and instance segmentation
WO2020240477A1 (en) * 2019-05-31 2020-12-03 Thales Canada Inc. Method and processing device for training a neural network
US20200133281A1 (en) * 2019-12-27 2020-04-30 Intel Corporation Safety system for a vehicle

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
CHOI JIWOONG ET AL: "Uncertainty-based Object Detector for Autonomous Driving Embedded Platforms", 2020 2ND IEEE INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE CIRCUITS AND SYSTEMS (AICAS), IEEE, 31 August 2020 (2020-08-31), pages 16 - 20, XP033762494, DOI: 10.1109/AICAS48895.2020.9073907 *
FLORIAN KRAUS ET AL: "Uncertainty Estimation in One-Stage Object Detection", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 10 July 2020 (2020-07-10), XP081703031, DOI: 10.1109/ITSC.2019.8917494 *
GREGORY P MEYER ET AL: "Learning an Uncertainty-Aware Object Detector for Autonomous Driving", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 24 October 2019 (2019-10-24), XP081591118 *
HURTIK PETR ET AL: "Poly-YOLO: higher speed, more precise detection and instance segmentation for YOLOv3", NEURAL COMPUTING AND APPLICATIONS, vol. 34, no. 10, 1 June 2020 (2020-06-01), London, pages 8275 - 8290, XP093014241, ISSN: 0941-0643, Retrieved from the Internet <URL:https://arxiv.org/pdf/2005.13243.pdf> DOI: 10.1007/s00521-021-05978-9 *
LE MICHAEL TRUONG ET AL: "Uncertainty Estimation for Deep Neural Object Detectors in Safety-Critical Applications", 2018 21ST INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC), IEEE, 4 November 2018 (2018-11-04), pages 3873 - 3878, XP033470240, ISBN: 978-1-7281-0321-1, [retrieved on 20181207], DOI: 10.1109/ITSC.2018.8569637 *

Also Published As

Publication number Publication date
EP4341913A2 (en) 2024-03-27
WO2022243337A2 (en) 2022-11-24
WO2022243337A9 (en) 2023-03-09

Similar Documents

Publication Publication Date Title
WO2022243337A9 (en) System for detection and management of uncertainty in perception systems, for new object detection and for situation anticipation
EP3540637B1 (en) Neural network model training method, device and storage medium for image processing
CN107977706B (en) Modular distributed artificial neural network
US20190251433A1 (en) Method and electronic apparatus for adjusting a neural network
DE102015000386A1 (en) Apparatus and method for measuring a three-dimensional shape and non-transitory computer-readable storage medium
WO2019156563A3 (en) Method of and apparatus for analyzing images
JP2018513507A5 (en)
CN106529515B (en) Facial feature library management method and system
DE102013205810A1 (en) SYSTEM AND METHOD FOR ASSESSING AVAILABLE PARKING SPACES FOR PARKING ON THE ROAD WITH SEVERAL PLACES
DE102014222226A1 (en) OBJECT-SIZE CALIBRATION PROCEDURE FOR SUPPORTING VEHICLE RECOGNITION FOR A VIDEO-BASED TECHNOLOGY FOR PARKING ON THE ROAD
CN105828065B (en) A kind of video pictures overexposure detection method and device
CN106327488B (en) Self-adaptive foreground detection method and detection device thereof
JP2018207222A (en) Camera and parameter registration method
US10958832B2 (en) Camera device and method for detecting a surrounding region of a vehicle
KR20170038144A (en) Attention detection apparatus and attention detection method
KR101874461B1 (en) Server, method, wearable device for supporting maintenance of military apparatus based on augmented reality, virtual reality or mixed reality
CN106204551A (en) A kind of image significance detection method and device
KR102291742B1 (en) Smart selective watching control system using camera of artificial intelligence type
EP3765999A1 (en) System for identifying objects by means of distributed neural networks
CN113837928A (en) Object color adjusting method and device, electronic equipment and storage medium
KR20190119626A (en) Frame certainty for automatic content recognition
JPH1115981A (en) Wide area monitoring device and system therefor
CN113132718B (en) Day and night type image pickup device switching abnormality detection method, device, equipment and storage medium
CN113327219B (en) Image processing method and system based on multi-source data fusion
US20200026934A1 (en) Image processing apparatus

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22730378

Country of ref document: EP

Kind code of ref document: A2

WWE Wipo information: entry into national phase

Ref document number: 2022730378

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2022730378

Country of ref document: EP

Effective date: 20231218

WWE Wipo information: entry into national phase

Ref document number: 202280050415.2

Country of ref document: CN