WO2021175381A1 - Procédé et système de détection améliorée de l'environnement - Google Patents

Procédé et système de détection améliorée de l'environnement Download PDF

Info

Publication number
WO2021175381A1
WO2021175381A1 PCT/DE2021/200016 DE2021200016W WO2021175381A1 WO 2021175381 A1 WO2021175381 A1 WO 2021175381A1 DE 2021200016 W DE2021200016 W DE 2021200016W WO 2021175381 A1 WO2021175381 A1 WO 2021175381A1
Authority
WO
WIPO (PCT)
Prior art keywords
pose
surroundings
person
environment
image
Prior art date
Application number
PCT/DE2021/200016
Other languages
German (de)
English (en)
Inventor
Felix Hachfeld
Stefan Heinrich
Manuel du Bois
Martin PFITZER
Elias Strigel
Original Assignee
Conti Temic Microelectronic 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 Conti Temic Microelectronic Gmbh filed Critical Conti Temic Microelectronic Gmbh
Publication of WO2021175381A1 publication Critical patent/WO2021175381A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/20—Movements or behaviour, e.g. gesture recognition
    • G06V40/23—Recognition of whole body movements, e.g. for sport training
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition

Definitions

  • the invention relates to a method and a system for improved environment recognition based on pose recognition.
  • document EP2580739A2 shows monocular 3D pose assessment and tracking by recognition.
  • Document US2009175540A1 likewise shows a system, a method and a computer program product for assessing a pose of a human upper body.
  • the pose is represented by a skeleton representation.
  • a rectangular bounding box is placed around the recognized pedestrian, since it is difficult to capture the exact contour. This is also shown in the figures of EP2580739A2. This approach is also used for other objects such as vehicles in order to be able to quickly estimate the maximum dimensions of the respective object.
  • the surroundings detection sensor is preferably a mono camera, a stereo camera or a surround view system.
  • the determination of the one or more poses is carried out by means of contour finding (e.g. by means of a keypoint detector). After finding the contour, semantic segmentation can be carried out, for example, in order to be able to better recognize the individual body parts and their alignment.
  • contour finding e.g. by means of a keypoint detector.
  • semantic segmentation can be carried out, for example, in order to be able to better recognize the individual body parts and their alignment.
  • classifying the pose (s) it is preferred to classify according to special poses over time, pose accumulations in the image and / or special pose positions.
  • the entrainment of an object is determined based on specific poses over time.
  • the object carried by a person is particularly preferably determined based on special poses over time.
  • Special postures can be deduced from the special poses over time, which are typical if a person is carrying an object. For example, based on the posture it can be recognized that a person is pushing a stroller or a walker. pulling a suitcase or the like or recognizing a wheelchair. This information can in turn be used to adjust the driving behavior accordingly, e.g. at a zebra crossing. This information is important in order to avoid a collision of the vehicle with the object carried by adapting the driving strategy.
  • the assignment of the poses to the respective objects can be carried out, for example, by means of a recognition system (e.g. neural network, look-up table).
  • a recognition system e.g. neural network, look-up table.
  • the object does not have to be recognized directly.
  • Topographical properties of the vehicle environment are preferably determined based on a special pose position.
  • elevations in the area such as, for example Bridges or houses are meant to be / are recognized.
  • the information that pedestrians usually walk on the ground can be used to estimate the course of the road. If there are deviations, this allows conclusions to be drawn about peculiarities in the course of the road. For example, when a pose is recognized above the vanishing point, it can be concluded that there are bridges or high adjoining houses, when people are recognized at windows. This information about the presence of vertical structures can in turn be helpful in order to start corresponding algorithms, for example extrinsic / intrinsic auto-calibration.
  • certain landmarks in the vehicle environment are determined based on the accumulation of poses. For example, based on accumulation patterns over time, for example, a traffic light or a pedestrian crossing can be inferred. For this purpose, the posture, line of sight or general orientation of the people can be recognized by means of the pose representation. This information can be used, for example, as a landmark for localization. An accumulation a little further away from the road and pointing away from the road could indicate a point of interest. Accumulations next to a stopping point can be an indication of stops, e.g. a bus stop.
  • an accumulation of pedestrians or cyclists who were recognized over time on the basis of the special movement pattern of the pose could indicate paths next to the street (e.g. pedestrian paths or cycle paths). If these accumulations are recognized directly on the road, this can be an indication of a marathon / bike race, a demonstration or a move be. This information can then be used, for example, to optimize route planning.
  • a system for improved environment recognition based on pose recognition comprising at least one environment detection sensor for recording an image of the surroundings or a sequence of images of the surroundings and a data processing device which is designed to analyze the recorded image of the surroundings and to one or more person (s) detect, perform a pose recognition of the person (s), classify the pose and
  • Fig. 2 a schematic representation of the system according to an embodiment of the invention.
  • FIG. 1 shows a schematic flow diagram of an embodiment of the invention.
  • step S1 an image of the surroundings or a sequence of images of the surroundings is recorded by means of at least one surroundings detection sensor of a vehicle.
  • step S2 one or more people are detected in the image of the surroundings or in the sequence of images of the surroundings.
  • step S3 one or more Pose (s) of the one or more person (s) determined.
  • step S4 the pose or the poses of the one or more person (s) are classified.
  • features in the vehicle environment are determined based on the classification of the pose (s).
  • FIG. 2 shows a schematic representation of the system according to an embodiment of the invention.
  • a system 1 for recognizing road users, in particular people in road traffic is shown in a schematic representation.
  • the system 1 comprises at least one environment detection sensor 2 and a data processing device 3.
  • Data processing devices 3 are connected via a data connection D, by means of which image data can be transmitted from the optical sensor 2 to the data processing device. It would be conceivable that the data processing device is connected to one or more actuators which, based on the results of the data processing device, control the vehicle accordingly.
  • the data connection D is preferably designed to be wired. However, wireless connections such as WLAN, Bluetooth, etc. would also be conceivable.
  • the at least one surroundings detection sensor 2 is a mono camera, a stereo camera or a surround view system.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • General Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Health & Medical Sciences (AREA)
  • Social Psychology (AREA)
  • Psychiatry (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Processing (AREA)
  • Traffic Control Systems (AREA)
  • Image Analysis (AREA)

Abstract

L'invention concerne un procédé de détection améliorée de l'environnement sur la base d'une reconnaissance de poses, comprenant les étapes suivantes : - enregistrement (S1) d'une image de l'environnement ou d'une suite d'images de l'environnement au moyen d'au moins un capteur de détection de l'environnement (2) d'un véhicule ; - détection (S2) d'une ou plusieurs personne(s) dans l'image de l'environnement ou dans la suite d'images de l'environnement ; - détermination (S3) d'une ou plusieurs pose(s) de l'au moins une personne ; - classification (S4) de la ou des pose(s) de la ou des personne(s) ; - et détermination (S5) de caractéristiques dans l'environnement du véhicule sur la base de la classification de la ou des pose(s).
PCT/DE2021/200016 2020-03-06 2021-02-16 Procédé et système de détection améliorée de l'environnement WO2021175381A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102020202905.9 2020-03-06
DE102020202905.9A DE102020202905A1 (de) 2020-03-06 2020-03-06 Verfahren und ein System zur verbesserten Umgebungserkennung

Publications (1)

Publication Number Publication Date
WO2021175381A1 true WO2021175381A1 (fr) 2021-09-10

Family

ID=74874605

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/DE2021/200016 WO2021175381A1 (fr) 2020-03-06 2021-02-16 Procédé et système de détection améliorée de l'environnement

Country Status (2)

Country Link
DE (1) DE102020202905A1 (fr)
WO (1) WO2021175381A1 (fr)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090175540A1 (en) 2007-12-21 2009-07-09 Honda Motor Co., Ltd. Controlled human pose estimation from depth image streams
DE102011011870A1 (de) * 2010-02-23 2011-08-25 Conti Temic microelectronic GmbH, 90411 Komponenten-basierte Detektion, Klassifikation, Verfolgung und Prädikation von Objekten
EP2580739A2 (fr) 2010-06-12 2013-04-17 Toyota Motor Europe NV/SA Estimation et suivi par détection de poses en trois dimensions (3d) monoculaires
US20170057497A1 (en) * 2015-08-28 2017-03-02 Delphi Technologies, Inc. Pedestrian-intent-detection for automated vehicles

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090175540A1 (en) 2007-12-21 2009-07-09 Honda Motor Co., Ltd. Controlled human pose estimation from depth image streams
DE102011011870A1 (de) * 2010-02-23 2011-08-25 Conti Temic microelectronic GmbH, 90411 Komponenten-basierte Detektion, Klassifikation, Verfolgung und Prädikation von Objekten
EP2580739A2 (fr) 2010-06-12 2013-04-17 Toyota Motor Europe NV/SA Estimation et suivi par détection de poses en trois dimensions (3d) monoculaires
US20170057497A1 (en) * 2015-08-28 2017-03-02 Delphi Technologies, Inc. Pedestrian-intent-detection for automated vehicles

Also Published As

Publication number Publication date
DE102020202905A1 (de) 2021-09-09

Similar Documents

Publication Publication Date Title
Low et al. Simple robust road lane detection algorithm
DE102015203016B4 (de) Verfahren und Vorrichtung zur optischen Selbstlokalisation eines Kraftfahrzeugs in einem Umfeld
WO2016026568A1 (fr) Procédé et dispositif de comptage sans contact d'essieux d'un véhicule et système de comptage d'essieux pour trafic routier
DE112013001424T5 (de) Objekterkennungsvorrichtung
DE102007013023A1 (de) Probabilistische Rasterkarte
CN105956608A (zh) 一种基于深度学习的目标定位、分类算法
DE102018104270A1 (de) Verfahren zum Vorhersagen des Verhaltens mindestens eines Fußgängers
DE102018133441A1 (de) Verfahren und System zum Bestimmen von Landmarken in einer Umgebung eines Fahrzeugs
DE102016226204B4 (de) Erfassungssystem für ein zielobjekt und ein verfahren zur erfassung eines zielobjekts
EP2116958B1 (fr) Procédé et dispositif de détermination du déroulement de voie dans la zone devant un véhicule
DE102011109569A1 (de) Verfahren zur Fahrspurerkennung mittels einer Kamera
DE102017106535A1 (de) Strassenoberflächenzustand-Erkennung mit Multi-Scale Fusion
DE102016210534A1 (de) Verfahren zum Klassifizieren einer Umgebung eines Fahrzeugs
DE102014221803A1 (de) Verfahren und Vorrichtung zum Bestimmen einer momentan vorliegenden Fahrsituation
EP3520023B1 (fr) Détection et validation d'objets provenant d'images séquentielles d'une caméra
WO2020104551A1 (fr) Reconnaissance d'objets au moyen d'un système de détection de véhicules
EP3520020B1 (fr) Classification de signaux routiers dans une zone environnante d'un véhicule automobile
DE102021003567A1 (de) Verfahren zur Erkennung von Objektbeziehungen und Attributierungen aus Sensordaten
CN105718908A (zh) 一种基于衣帽特征与姿态检测的交警检测方法和系统
DE102015006569A1 (de) Verfahren zur bildbasierten Erkennung des Straßentyps
EP3704631A2 (fr) Procédé de calcul d'un éloignement entre un véhicule automobile et un objet
WO2021175381A1 (fr) Procédé et système de détection améliorée de l'environnement
WO2019057252A1 (fr) Procédé et dispositif de détection de voies de circulation, système d'aide à la conduite et véhicule
DE102015204529A1 (de) Verfahren und Vorrichtung zur Objekterkennung in einem Fortbewegungsmittel
DE102018109680A1 (de) Verfahren zum Unterscheiden von Fahrbahnmarkierungen und Bordsteinen durch parallele zweidimensionale und dreidimensionale Auswertung; Steuereinrichtung; Fahrassistenzsystem; sowie Computerprogrammprodukt

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: 21712034

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 21712034

Country of ref document: EP

Kind code of ref document: A1