WO2018153563A1 - Réseau neuronal artificiel et aéronef sans pilote permettant de détecter un accident de la circulation - Google Patents

Réseau neuronal artificiel et aéronef sans pilote permettant de détecter un accident de la circulation Download PDF

Info

Publication number
WO2018153563A1
WO2018153563A1 PCT/EP2018/050660 EP2018050660W WO2018153563A1 WO 2018153563 A1 WO2018153563 A1 WO 2018153563A1 EP 2018050660 W EP2018050660 W EP 2018050660W WO 2018153563 A1 WO2018153563 A1 WO 2018153563A1
Authority
WO
WIPO (PCT)
Prior art keywords
neural network
unmanned aerial
aerial vehicle
traffic accident
artificial neural
Prior art date
Application number
PCT/EP2018/050660
Other languages
German (de)
English (en)
Inventor
Heiko Freienstein
Henning Hoepfner
Florian Drews
Original Assignee
Robert Bosch 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 Robert Bosch Gmbh filed Critical Robert Bosch Gmbh
Publication of WO2018153563A1 publication Critical patent/WO2018153563A1/fr

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G08G1/095—Traffic lights
    • G08G1/0955—Traffic lights transportable
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/04—Detecting movement of traffic to be counted or controlled using optical or ultrasonic detectors
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/20—Monitoring the location of vehicles belonging to a group, e.g. fleet of vehicles, countable or determined number of vehicles
    • G08G1/205—Indicating the location of the monitored vehicles as destination, e.g. accidents, stolen, rental
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B64—AIRCRAFT; AVIATION; COSMONAUTICS
    • B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
    • B64U2101/00—UAVs specially adapted for particular uses or applications
    • B64U2101/30—UAVs specially adapted for particular uses or applications for imaging, photography or videography
    • B64U2101/31—UAVs specially adapted for particular uses or applications for imaging, photography or videography for surveillance

Definitions

  • the present invention relates to a neural network and an unmanned aerial vehicle configured to detect and classify a traffic accident.
  • the invention relates to a method for detecting the traffic accident and a computer program that performs each step of the method when it runs on a computing device, and a machine-readable storage medium that stores the computer program.
  • the invention relates to an electronic computing device which is set up to carry out the method according to the invention.
  • Vehicle damage and equipment and derived data such as
  • the eCall system makes an emergency call to the responsible rescue service.
  • the eCall system can be operated by a vehicle occupant, usually the driver, on the other hand, the eCall system is automatically activated in a traffic accident when a sensor detects the traffic accident inside or on the motor vehicle.
  • the eCall system is automatically activated in a traffic accident when a sensor detects the traffic accident inside or on the motor vehicle.
  • information such as accident location and time as well as number of vehicle occupants are transmitted to the rescue service.
  • An artificial neural network for detecting and classifying a traffic accident is proposed.
  • Artificial neural networks also called artificial neural network or artifical neural network
  • the artificial neurons are connected to each other through the artificial neural network similar to a biological neural network and can thus represent arbitrarily complex functions, learn tasks and thereby independently solve problems.
  • the basis of the functioning of an artificial neural network is, in addition to a suitable topology, the training of the artificial neural network, in which the artificial neurons and the connections between them are changed and adapted.
  • the artificial neural network is taught in via a database containing at least traffic accident data.
  • a database is for example GIDAS, in which traffic accidents with personal injuries are documented.
  • the traffic accident data include the following information:
  • the artificial neural network is trained on a database that best reflects the location or the area of application of the artificial neural network.
  • An unmanned aerial vehicle - also commonly referred to as a drone and in English as an unmanned aerial vehicle / aircraft (UAV / UA) - communicates with the artificial neural network and transmits environmental data that the unmanned aerial vehicle senses via its sensors to the artificial one neural network.
  • UAV / UA unmanned aerial vehicle / aircraft
  • the artificial neural network can now by means of at least the
  • Time / time, etc. are used - this also applies to the following aspects.
  • Features of the traffic accident can preferably be determined on the basis of image data from the traffic accident data of the database, but also by means of the metadata and applied to the environmental data of the unmanned aerial vehicle in order to detect the traffic accident.
  • all road users involved in the traffic accident can be detected, regardless of whether they have their own system for detecting a traffic accident.
  • it can also be recognized whether personal injury has occurred and, if appropriate, the severity of the injuries sustained are assessed.
  • the artificial neural network can be recognized
  • Road accident data of the database contained information about the
  • the artificial neural network can then classify in traffic accidents, for example, a rear-end collision, a
  • the artificial neural network has at least one, preferably several hidden layers, between an input layer in which artificial neurons receive an input signal and pass it on in a modified version, and an output layer in which further artificial neurons output an output signal, on.
  • the artificial neural network can perform deep learning.
  • this type of learning algorithms are used to capture profound levels of abstraction of features in the data and to classify the features into a hierarchy. This will be high ranking features in Subordinate intermediate levels arranged in which more complex functions are executed, and passed on to higher levels intermediate levels. During training, the abstraction levels can then be separated and the appropriate features selected.
  • the artificial neural network is set up to reconstruct a traffic accident, at least in a simulation, by means of at least the traffic accident data of the database and the environment data of the unmanned aerial vehicle.
  • the unmanned aerial vehicle Preferably, the unmanned aerial vehicle
  • Aircraft when a traffic accident has been detected, approach the scene of the accident and precisely record the accident situation by means of its sensors.
  • the recorded environmental data are compared with the learned traffic accident data and used in a simulation.
  • Preferred for this purpose are the metadata and more preferably those relating to the collision, e.g. the run-in and collision speed, the collision angle and the deformation of the vehicles used for the evaluation.
  • the artificial neural network is set up by means of at least the traffic accident data of the database and the
  • Ambient data of the unmanned aerial vehicle with the help of at least the unmanned aerial vehicle, to secure the traffic accident.
  • the respective environment - determined from the environmental data - and the
  • the artificial neural network can perform measures adapted to the accident situation for protection.
  • the unmanned vehicle can perform measures adapted to the accident situation for protection.
  • aircraft may have facilities for securing the traffic accident, as described below.
  • the unmanned aerial vehicle is on-site earlier than emergency services, so the accident site can be secured immediately. Persons to secure the accident site are not necessary, which reduces the risk potential for the people, especially for the emergency services.
  • the artificial neural network is arranged to handle traffic accidents by means of at least the traffic accident data of the database and the environment data of the unmanned aerial vehicle
  • the accident from the traffic accident data and the current traffic situation can be a probability for the
  • Traffic accident be closed.
  • the current traffic situation in addition to the environmental data on weather data, traffic information,
  • the unmanned aircraft - or if available a variety of such unmanned aerial vehicles - can be positioned and aligned to monitor the confusing and / or dangerous places with high risk of accidents.
  • the artificial neural network can also be set up, in particular if a traffic accident has been detected, to send an emergency call at least to an ambulance service. For this purpose, any kind of
  • the artificial neural network can according to one aspect in one
  • the artificial neural network may be implemented in a central electronic computing device wirelessly in communication with the unmanned aerial vehicle.
  • the central electronic computing device can be unmanned with several such
  • Aircraft allowing them to be controlled simultaneously and to optimize monitoring.
  • an unmanned aerial vehicle having a neural network as described above is proposed.
  • the unmanned aerial vehicle having a neural network as described above is proposed.
  • Aircraft also has a sensor for detecting the
  • the senor preferably optical
  • Detecting means such as e.g. Cameras and laser scanners, includes.
  • the unmanned aerial vehicle forms an autonomous unit after learning the neural network.
  • the unmanned aerial vehicle is then positioned in the area to be monitored and detects the environmental data there.
  • the unmanned aerial vehicle may include an internal combustion engine to increase its range and monitoring duration over currently available drives with regenerative energy sources.
  • the unmanned aerial vehicle also has facilities for securing the accident site. These include bulbs on the unmanned aerial vehicle, which illuminate the accident site large-scale, deductible light elements, such as. Lamps, light strips or LED-based lighting elements, as well as shut-off and marking elements.
  • the unmanned aerial vehicle approaches the scene of the accident and, depending on the nature of the accident, the environment and the time of day / time, places the equipment listed above for securing the scene of the accident.
  • the method for detecting the traffic accident by means of the above-described neural network comprises the following steps: Before use, the artificial neural network is taught by a database which contains at least traffic accident data, preferably deep learning can be used. An unmanned aerial vehicle, which is in communication with the artificial neural network, detects the
  • Ambient data of the unmanned aerial vehicle detected the environmental data recorded by the sensors of the unmanned aerial vehicle can be compared with the learned traffic accidents.
  • the traffic accident can be classified in the method.
  • the accident can be reconstructed. Alternatively, in a process
  • Traffic accidents are predicted by means of at least the traffic accident data of the database and the environmental data of the unmanned aerial vehicle.
  • the unmanned aircraft secure the detected traffic accident.
  • it may preferably use its facilities for securing the accident site, which are described above.
  • the computer program is set up to perform each step of the method, in particular when it is performed on a computing device. It enables the implementation of the method in a conventional electronic computing device, without having to make any structural changes. For this purpose it is stored on the machine-readable storage medium.
  • the electronic computing device is obtained, which is set up to detect a traffic accident.
  • the electronic computing device is the artificial neural network, as described above implemented.
  • the electronic computing device may preferably be the electronic computing device of the unmanned aerial vehicle or the central computing device that is connected to the unmanned aerial vehicle.
  • Figure 1 shows a schematic representation of an unmanned aerial vehicle, with an artificial neural network, which detects a traffic accident, according to an embodiment of the invention.
  • Figure 2 shows a schematic representation of an unmanned aerial vehicle, which is in connection with an artificial neural network, which detects a traffic accident, according to a further embodiment of the invention.
  • Figure 3 shows a schematic representation of an unmanned aerial vehicle, with an artificial neural network, which secures a traffic accident.
  • Figures 1, 2 and 3 each show a schematic representation of an unmanned aerial vehicle 1, which has a sensor 2 for detecting environmental data and an artificial neural network 3, according to embodiments of the invention.
  • the sensor system 2 comprises an optical detection device, such as e.g. a camera, which detects a surveillance area 4.
  • an optical detection device such as e.g. a camera
  • the surveillance area 4 only covers part of a street 5 for better clarity, the surveillance area 4 is significantly larger in practice and covers entire streets or even larger regions simultaneously, due to the altitude of the unmanned aerial vehicle 1.
  • Monitoring area 4 are shown in Figures 1, 2 and 3 by way of example two traffic accidents 6, 7.
  • FIG. 1 shows, in one embodiment of the invention, the unmanned aerial vehicle 1 with an electronic computing device 8, in which an artificial neural network 3 for recognizing and classifying the traffic accident 6, 7 is implemented.
  • the electronic computing device 8, and thus the artificial neural network 3 communicate via a wireless radio link with a database 9 containing traffic accident data.
  • a database 9 containing traffic accident data.
  • An example of such a database 9 in Germany is Gl DAS of the Federal Highway Research Institute and the Klasvelessness Automobiltechnik eV
  • the electronic computing device 8 of the unmanned aerial vehicle 1 is connected via a wireless radio link to a central electronic computing device 10.
  • the central electronic computing device 10 may communicate with and control other unmanned aerial vehicles not shown here.
  • the inventive artificial neural network 3 is implemented in the central electronic computing device 10 in this case.
  • the central electronic computing device 10 and thus the artificial neural network 3 communicate with the database 9 containing traffic accident data.
  • the artificial neural network 3 is learned via the database 9, wherein the artificial neural network 3 receives information about traffic accidents in the form of traffic accident data and corresponding metadata from the database 9. Deep Learning is used to train the traffic accident data along with the metadata. The artificial neural network 3 recognizes by means of at least the traffic accident data of
  • the artificial neural network 3 can thus be recognized
  • the artificial neural network 3 on the one hand because of the position of two vehicles 11, 12, their collision and eventual deformation (not shown) a collision 6, on the other hand due to the position of another vehicle 13 and an obstacle 14, for example a tree to classify a collision 7 with the obstacle 14.
  • FIG. 3 schematically shows devices 15, 16, 17 for securing the accident site.
  • These include lighting means 15 on the unmanned aerial vehicle 1 and deductible lighting elements 16, such as lamps, light strips or LED-based lighting elements, as well as shut-off and marking elements 17 (not all shown).
  • the unmanned aerial vehicle 1 sets, depending on the nature of the traffic accident 6, 7, which is determined by the traffic accident data, the environment of the Environment data is determined, and the time / time of day, the facilities 15, 16, 17 for securing the accident site. For example, at an accident site on a highway at night, other measures and facilities 15, 16, 17 are used to protect the accident site, as for example at an accident site in a well-lit downtown.
  • the distribution of facilities are used to protect the accident site, as for example at an accident site in a well-lit downtown.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Traffic Control Systems (AREA)

Abstract

L'invention concerne un réseau neuronal (3) artificiel qui est formé à l'aide d'une base de données (9), qui contient au moins des données d'accidents de la circulation, et qui est en liaison avec au moins un aéronef sans pilote (1) qui transmet des données d'environnement au réseau neuronal (3). Le réseau neuronal (3) peut détecter et classifier un accident de la circulation (6, 7) au moyen d'au moins les données d'accident de circulation de la base de données (9) et les données d'environnement de l'aéronef sans pilote (1).
PCT/EP2018/050660 2017-02-27 2018-01-11 Réseau neuronal artificiel et aéronef sans pilote permettant de détecter un accident de la circulation WO2018153563A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102017203157.3 2017-02-27
DE102017203157.3A DE102017203157A1 (de) 2017-02-27 2017-02-27 Künstliches neuronales Netz und unbemanntes Luftfahrzeug zum Erkennen eines Verkehrsunfalls

Publications (1)

Publication Number Publication Date
WO2018153563A1 true WO2018153563A1 (fr) 2018-08-30

Family

ID=60957321

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2018/050660 WO2018153563A1 (fr) 2017-02-27 2018-01-11 Réseau neuronal artificiel et aéronef sans pilote permettant de détecter un accident de la circulation

Country Status (2)

Country Link
DE (1) DE102017203157A1 (fr)
WO (1) WO2018153563A1 (fr)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110286677A (zh) * 2019-06-13 2019-09-27 北京理工大学 一种用于数据采集的无人车控制方法和系统
DE102018221997A1 (de) * 2018-12-18 2020-06-18 Audi Ag Verfahren zum Betreiben eines unbemannten Luftfahrzeugs für ein Kraftfahrzeug sowie unbemanntes Luftfahrzeug für ein Kraftfahrzeug
CN114863680A (zh) * 2022-04-27 2022-08-05 腾讯科技（深圳）有限公司 预测处理方法、装置、计算机设备及存储介质

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102019210513A1 (de) * 2019-07-17 2021-01-21 Audi Ag Verfahren zur Unfallassistenz, unbemanntes Luftfahrzeug und Kraftfahrzeug

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150339570A1 (en) * 2014-05-22 2015-11-26 Lee J. Scheffler Methods and systems for neural and cognitive processing
US20160093212A1 (en) * 2014-08-22 2016-03-31 Verizon Patent And Licensing Inc. Using aerial imaging to provide supplemental information about a location
WO2016123424A1 (fr) * 2015-01-29 2016-08-04 Scope Technologies Holdings Limited Surveillance d'accidents à distance et base de données répartie de diagnostic de véhicule
EP3069995A1 (fr) * 2015-03-18 2016-09-21 LG Electronics Inc. Véhicule aérien sans équipage et son procédé de commande
DE102015008768A1 (de) * 2015-07-06 2017-01-12 Audi Ag Verfahren zum Begutachten eines an einem Unfall beteiligten Kraftfahrzeugs und Kraftfahrzeug

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150339570A1 (en) * 2014-05-22 2015-11-26 Lee J. Scheffler Methods and systems for neural and cognitive processing
US20160093212A1 (en) * 2014-08-22 2016-03-31 Verizon Patent And Licensing Inc. Using aerial imaging to provide supplemental information about a location
WO2016123424A1 (fr) * 2015-01-29 2016-08-04 Scope Technologies Holdings Limited Surveillance d'accidents à distance et base de données répartie de diagnostic de véhicule
EP3069995A1 (fr) * 2015-03-18 2016-09-21 LG Electronics Inc. Véhicule aérien sans équipage et son procédé de commande
DE102015008768A1 (de) * 2015-07-06 2017-01-12 Audi Ag Verfahren zum Begutachten eines an einem Unfall beteiligten Kraftfahrzeugs und Kraftfahrzeug

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102018221997A1 (de) * 2018-12-18 2020-06-18 Audi Ag Verfahren zum Betreiben eines unbemannten Luftfahrzeugs für ein Kraftfahrzeug sowie unbemanntes Luftfahrzeug für ein Kraftfahrzeug
CN110286677A (zh) * 2019-06-13 2019-09-27 北京理工大学 一种用于数据采集的无人车控制方法和系统
CN110286677B (zh) * 2019-06-13 2021-03-16 北京理工大学 一种用于数据采集的无人车控制方法和系统
CN114863680A (zh) * 2022-04-27 2022-08-05 腾讯科技（深圳）有限公司 预测处理方法、装置、计算机设备及存储介质

Also Published As

Publication number Publication date
DE102017203157A1 (de) 2018-08-30

Similar Documents

Publication Publication Date Title
DE102014008578B4 (de) Verfahren zur Ermittlung von Positionsdaten zur Nutzung beim Betrieb eines Fahrzeugsystems eines Kraftfahrzeugs und Positionsdatenermittlungs- und-verteilssystem
WO2018153563A1 (fr) Réseau neuronal artificiel et aéronef sans pilote permettant de détecter un accident de la circulation
DE102018125763A1 (de) Rettungssystem und Rettungsverfahren und für das Rettungssystem und das Rettungsverfahren verwendeter Server
DE102017217444B4 (de) Verfahren und System zum Aktualisieren eines Steuerungsmodells für eine automatische Steuerung zumindest einer mobilen Einheit
EP3688742A1 (fr) Système pour produire et/ou actualiser un modèle numérique d'une carte numérique
DE102017111468A1 (de) Fahrzeugsystem und Verfahren zum Bestimmen, ob ein Fahrzeuginsasse ein fahrzeugexternes Objekt wahrgenommen hat
DE112015004135T5 (de) Fahrzeugsteuerungsvorrichtung
DE102019209552A1 (de) Verfahren zur Verkehrserfassung
DE102018118233B4 (de) Computerimplementiertes verfahren, softwareprogramm und vorrichtung zur aufforderung einer bildung einer einsatzgasse
DE102015213526A1 (de) Verfahren und System zum Warnen eines Fahrers eines Fahrzeugs
DE102018006949A1 (de) Verfahren zum fahrerlosen Betrieb eines Fahrzeugs
EP3499473A1 (fr) Détection automatisée de situations dangereuses
DE102015004605A1 (de) Verfahren zum Betrieb eines Steuersystems einer Mobileinheit und Mobileinheit
DE102019105044A1 (de) Kollisionsvermeidung basierend auf verbundenen vorrichtungen
DE102014200567A1 (de) Verfahren zur automatischen Übertragung von Bild- und/oder Audiodaten im Zusammenhang mit einem Unfall eines Fahrzeugs
DE102017219292A1 (de) Verfahren und vorrichtung zum erfassen von ereignisbezogenen daten bezüglich eines fahrzeugs
DE102017210394B3 (de) Verfahren zum Betrieb von Kraftfahrzeugen in einer Parkumgebung und Recheneinrichtung
DE102021112804A1 (de) Verfahren, Fahrzeugsteuergerät und Fahrzeug zur vorausschauenden Datenerhebung von vernetzten Verkehrsteilnehmern
DE102015212425A1 (de) Verfahren zum Steuern eines Scheinwerfers eines Fahrzeugs, Verfahren zum Generieren von Positionsdaten zum Steuern eines Scheinwerfers eines Fahrzeugs und Verfahren zum Betreiben einer Lichtanlage eines Fahrzeugs
DE102020203729A1 (de) Verfahren zum Betreiben eines Kraftfahrzeugs
WO2019076695A1 (fr) Procédé d'évaluation de données de trafic, programme informatique, support d'informations lisible par machine et dispositif
DE102018009360A1 (de) Automatisierte Erstellung eines Unfallberichts
DE102017205728A1 (de) Verfahren zum Absetzen eines Notrufs, zum Bestätigen eines Notrufsignals für ein Fahrzeug, Verfahren zum Erkennen einer Notfallsituation, entsprechende Vorrichtungen, Computerprogramm und maschinenlesbare Speichermedien
DE102017200163A1 (de) Verfahren und Vorrichtung zum Überwachen eines abgestellten Kraftfahrzeugs
DE102021207415A1 (de) Verfahren zur Informationsbeschaffung und Assistenzsystem

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: 18700340

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18700340

Country of ref document: EP

Kind code of ref document: A1