WO2024056205A1 - Procédé de détection d'un objet à l'aide d'un système mobile - Google Patents
Procédé de détection d'un objet à l'aide d'un système mobile Download PDFInfo
- Publication number
- WO2024056205A1 WO2024056205A1 PCT/EP2023/025369 EP2023025369W WO2024056205A1 WO 2024056205 A1 WO2024056205 A1 WO 2024056205A1 EP 2023025369 W EP2023025369 W EP 2023025369W WO 2024056205 A1 WO2024056205 A1 WO 2024056205A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- sensor
- mobile system
- detected
- assigned
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000001454 recorded image Methods 0.000 claims description 7
- 238000004146 energy storage Methods 0.000 claims description 3
- 238000011161 development Methods 0.000 description 5
- 230000018109 developmental process Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- 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
Definitions
- the invention relates to a method for detecting an object by a mobile system, in particular in a technical system, wherein the mobile system has at least one first sensor and at least one second sensor.
- the technical system is in particular an industrial application, for example a production plant, an industrial hall or a logistics center.
- the mobile system is, for example, an autonomous vehicle.
- the mobile system is used, for example, to transport objects within the technical system. There are also other objects in the technical system.
- the mobile system has a sensor, in particular a laser scanner, for detecting such objects and distances to such objects.
- the mobile system has a first sensor, which is designed as a laser scanner, and a second sensor, which is designed as a monocular camera. By linking the data recorded by the two sensors, objects in the technical system are recognized.
- Objects can be detected from images recorded by a camera.
- Image pyramids are usually created and used for object detection.
- An image pyramid is associated with an object and has multiple scale levels. Each scale level includes an object image of a different size. Each scale level shows the object at a different distance. To find the object in an image, all scaling levels of the pyramid must be processed, each comparing it to the object image at the scaling level. The comparison with the large number of object images is computationally intensive.
- the invention is based on the object of developing a method for detecting an object using a mobile system.
- a method for detecting an object by a mobile system in particular in a technical system, is proposed.
- the mobile system has at least one first sensor, at least one second sensor and at least one image pyramid.
- the at least one image pyramid is assigned to an object and contains several scaling levels, each of which includes an object image.
- the first sensor several points of an object are detected, and distances to the detected points are determined, and a resulting distance to the detected points is determined.
- the second sensor an image containing the object is recorded, and an image of the object is recognized in the recorded image.
- At least one scaling level is selected from the at least one image pyramid, to which the resulting distance is assigned.
- the object image of the at least one selected scaling level is compared with the image recognized in the captured image. If the object image matches the image, the object in the image is detected.
- An object to which an image pyramid is assigned is, for example, a pallet, a forklift or a grid box.
- the first sensor is designed as a laser scanner.
- a laser scanner sends out a laser beam, detects a reflected laser beam and uses this to calculate a distance to a point on an object that reflects the laser beam.
- Laser scanners are already present in well-known mobile systems, so there are no additional costs for installing the first sensor.
- the second sensor is designed as a monocular camera.
- a monocular camera is relatively inexpensive, robust and reliable.
- the resulting distance to the detected points is determined as the arithmetic mean of the determined distances to the detected points.
- the resulting distance therefore corresponds to a distance from the first sensor to a point in the middle of the object.
- the resulting distance to the detected points is determined as the smallest of the determined distances to the detected points.
- the resulting distance therefore corresponds to a distance between the first sensor and a side of the object facing the mobile system.
- the scaling levels of the at least one image pyramid are discrete and each include an object image at exactly one resulting distance. According to an advantageous development of the invention, a range of resulting distances is assigned to each scaling level of the at least one image pyramid. This means that resulting distances that lie between two discrete scaling levels can also be processed.
- the ranges of resulting distances which are assigned to adjacent scaling levels overlap. This allows minor errors and distortions to be compensated for when the image is captured.
- the ranges of resulting distances which are assigned to adjacent scaling levels are separated from one another. This means that each resulting distance is assigned to exactly one scaling level. This further reduces the computing intensity for comparing the image with object images.
- the mobile system has several image pyramids, each of which is assigned to an object. A hypothetical object is suggested from the detected points of the object and the distances to the detected points, and the image pyramid that is assigned to the hypothetical object is selected. At least one scaling level is selected from the selected image pyramid, to which the resulting distance is assigned.
- Objects to which an image pyramid is assigned are, for example, a pallet, a forklift or a grid box. It is therefore possible to detect different types of objects. By suggesting the hypothetical object, a pre-selection is made. A comparison with all image pyramids is therefore not necessary. This reduces the computational intensity of comparing the image with object images.
- the mobile system is designed as an autonomously driving vehicle which has a drive device, an electrical energy storage device for supplying the drive device and a control unit for controlling the drive device.
- the drive device includes, for example, an electric motor, a gearbox and drive wheels.
- the mobile system is in particular a driverless transport system for transporting objects within the technical system.
- the mobile system has a position sensor for detecting a position of the mobile system, particularly within the technical system.
- the sensor in question is, for example, a GPS receiver or a SLAM system. Recording the mobile system's own position, especially in the technical system, makes it possible to create a local map, which forms the basis for the autonomous driving of the mobile system.
- a local map is created which has at least one detected object.
- the local map forms the basis for the autonomous driving of the mobile system.
- Figure 1 a schematic side view of a mobile system and an object in a technical system
- Figure 2 a schematic top view of the mobile system and the object in the technical system
- Figure 3 a picture with an image of the object
- Figure 5 an overlay of the image with the recorded points.
- Figure 1 shows a schematic side view of a mobile system 10 and an object 11 in a technical system.
- the object 11 in this case is a pallet.
- the technical system has additional objects 11 not shown here, for example additional pallets, forklifts and mesh boxes.
- the technical system also has other mobile systems 10, not shown here, which are designed in the same way.
- the mobile system 10 is designed as an autonomously driving vehicle and has a drive device, an electrical energy storage device for supplying the drive device and a control unit for controlling the drive device.
- the mobile system 10 also has a position sensor for detecting a position of the mobile system 10 within the technical system.
- the mobile system 10 also includes a communication device for wireless communication over a network.
- the mobile system 10 in the present case has two first sensors 1, which are designed as laser scanners. Each of the first sensors 1 is used to detect objects 11 and to detect distances to detected objects 11. The first sensor 1 detects several points P of the object 11 and determines the distances to the detected points P.
- the mobile system 10 has a second sensor 2, which is designed as a monocular camera. The second sensor 2 is used to record images on which objects 11 in particular are depicted.
- the mobile system 10 is located on a level floor in the technical facility.
- the first sensors 1, designed as laser scanners, are arranged on the mobile system 10 in such a way that the scanning planes of the first sensors 1 are aligned parallel to the floor.
- the second sensor 2, designed as a monocular camera, is arranged on the mobile system 10 in such a way that the optical axis of the second sensor 2 is aligned parallel to the ground.
- FIG 2 shows a schematic top view of the mobile system 10 and the object 11 in the technical system shown in Figure 1.
- the mobile system 10 has an approximately rectangular cross section.
- the first sensors 1, designed as laser scanners, are arranged at opposite corners of the mobile system 10.
- the second sensor 2, designed as a monocular camera, is arranged on a front side of the mobile system 10.
- the geometric arrangement of the first sensors 1 relative to the second sensor 2 on the mobile system 10 can be detected by calibration and is therefore known.
- the geometric arrangement in question is constant and is therefore not changed dynamically.
- a transformation of detected points P and distances to the detected points P into a recorded image can clearly be carried out.
- the mobile system 10 also has several image pyramids. Each image pyramid is assigned to an object. Such objects are, for example, a pallet, a forklift or a wire mesh box. Each image pyramid contains multiple scaling levels. Each scaling level includes an object image. The object images of the scaling levels have different sizes. Each scaling level therefore shows the object at a different distance.
- An image is recorded using the second sensor 2, where the captured image contains the object 11.
- An image A of the object 11 is recognized in the captured image.
- Figure 3 shows an image with the image A of the object 11 shown in Figure 1.
- the object 11 is, as already mentioned, a pallet.
- the image A corresponds to a perspective representation of the object 11.
- FIG. 4 shows the detected points P of the object 11 shown in FIG. 1. From the distances of the mobile system 10 to the detected points P, a resulting distance of the mobile system 10 to the detected points P is determined.
- the resulting distance to the detected points P is determined, for example, as the arithmetic mean of the determined distances to the detected points P. Alternatively, the resulting distance to the detected points P is determined as the smallest of the determined distances to the detected points P.
- a hypothetical object is proposed from the detected points P of the object 11 and the distances of the mobile system 10 to the detected points P. Based on the position and orientation of the points P, a pallet is proposed as a hypothetical object.
- the image pyramid that is assigned to the hypothetical object is now selected.
- a scaling level is then selected from the selected image pyramid, to which the previously determined resulting distance is assigned.
- the object image of the selected scaling level is then compared with the image A recognized in the captured image. If the object image matches image A, the object, in this case the pallet, is detected in the image.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
L'invention concerne un procédé de détection d'un objet à l'aide d'un système mobile (10), en particulier dans un système technique, le système mobile (10) comprenant au moins un premier capteur (1), au moins un second capteur (2) et au moins une pyramide d'images qui est associée à un objet et contient de multiples niveaux de mise à l'échelle, comprenant chacun une image d'objet. Au moyen du premier capteur (1), de multiples points (P) d'un objet (11) sont détectés, et des distances par rapport aux points détectés (P) sont déterminées, et une distance résultante par rapport aux points détectés (P) est établie ; au moyen du second capteur (2), une image contenant l'objet (11) est capturée, et une représentation (A) de l'objet (11) est identifiée dans l'image capturée ; au moins un niveau de mise à l'échelle associé à la distance résultante est sélectionné parmi l'au moins une pyramide d'images ; l'image d'objet de l'au moins un niveau de mise à l'échelle sélectionné est comparée à la représentation (A) identifiée dans l'image capturée ; et l'objet est détecté dans l'image s'il existe une correspondance entre l'image d'objet et la représentation (A).
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
DE102022003372 | 2022-09-13 | ||
DE102022003372.0 | 2022-09-13 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2024056205A1 true WO2024056205A1 (fr) | 2024-03-21 |
Family
ID=87571777
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/EP2023/025369 WO2024056205A1 (fr) | 2022-09-13 | 2023-08-07 | Procédé de détection d'un objet à l'aide d'un système mobile |
Country Status (2)
Country | Link |
---|---|
DE (1) | DE102023003260A1 (fr) |
WO (1) | WO2024056205A1 (fr) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007072665A (ja) * | 2005-09-06 | 2007-03-22 | Fujitsu Ten Ltd | 物体判別装置、物体判別方法および物体判別プログラム |
US20080164985A1 (en) * | 2007-01-10 | 2008-07-10 | Omron Corporation | Detection device, method and program thereof |
US20130073194A1 (en) * | 2011-09-15 | 2013-03-21 | Clarion Co., Ltd. | Vehicle systems, devices, and methods for recognizing external worlds |
DE102021001282A1 (de) | 2020-04-01 | 2021-10-07 | Sew-Eurodrive Gmbh & Co Kg | Mobiles System und Verfahren zum Betreiben eines mobilen Systems |
-
2023
- 2023-08-07 WO PCT/EP2023/025369 patent/WO2024056205A1/fr unknown
- 2023-08-07 DE DE102023003260.3A patent/DE102023003260A1/de active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007072665A (ja) * | 2005-09-06 | 2007-03-22 | Fujitsu Ten Ltd | 物体判別装置、物体判別方法および物体判別プログラム |
US20080164985A1 (en) * | 2007-01-10 | 2008-07-10 | Omron Corporation | Detection device, method and program thereof |
US20130073194A1 (en) * | 2011-09-15 | 2013-03-21 | Clarion Co., Ltd. | Vehicle systems, devices, and methods for recognizing external worlds |
DE102021001282A1 (de) | 2020-04-01 | 2021-10-07 | Sew-Eurodrive Gmbh & Co Kg | Mobiles System und Verfahren zum Betreiben eines mobilen Systems |
Non-Patent Citations (1)
Title |
---|
X. ZHAOP. SUNZ. XUH. MINH. YU: "LIDAR and Camera Data for Object Detection in Autonomous Vehicle Applications", IEEE SENSORS JOURNAL, vol. 20, no. 9, 1 May 2020 (2020-05-01), pages 4901 - 4913, XP011781784, DOI: 10.1109/JSEN.2020.2966034 |
Also Published As
Publication number | Publication date |
---|---|
DE102023003260A1 (de) | 2024-03-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP3497476B1 (fr) | Véhicule à moteur et procédé de perception de l'environnement à 360° | |
WO2004055548A1 (fr) | Procede pour identifier et suivre des objets | |
EP2439487B1 (fr) | Dispositif de mesure de volume pour objets mobiles | |
EP2275990B1 (fr) | Capteur 3D | |
EP3053133B1 (fr) | Procédé et dispositif pour afficher l'environnement d'un véhicule et système d'assitance au conducteur | |
EP2767925A2 (fr) | Procédé de détection d'objets dans un entrepôt et/ou d'orientation spatiale dans un entrepôt | |
DE102011111440A1 (de) | Verfahren zur Umgebungsrepräsentation | |
WO2013178407A1 (fr) | Procédé et dispositif pour traiter des données stéréoscopiques | |
WO1996007959A1 (fr) | Procede de determination de la position d'un point de repere dans la carte de l'environnement d'une unite automobile qui determine dynamiquement la distance qui la separe du point de repere | |
EP1419402B1 (fr) | Procede de reconnaissance et de poursuite d'objets | |
DE102017223160A1 (de) | Verfahren zum Erkennen von zumindest einem an einem Kraftfahrzeug anliegenden Objekt sowie Steuervorrichtung und Kraftfahrzeug | |
EP4128017A1 (fr) | Système mobile et procédé de fonctionnement d'un système mobile | |
WO2022078799A1 (fr) | Procédé de détection permettant la détection d'objets statiques | |
DE102020120887B4 (de) | Verfahren zum erfassen einer einhängeposition eines auflagestegs und flachbettwerkzeugmaschine | |
WO2024056205A1 (fr) | Procédé de détection d'un objet à l'aide d'un système mobile | |
DE102020211596A1 (de) | Verfahren zum Generieren eines trainierten neuronalen Faltungs-Netzwerks mit invarianter Integrationsschicht zum Klassifizieren von Objekten | |
DE102019219247A1 (de) | Verfahren zur Umfelderfassung, Datenverarbeitungseinheit | |
WO2020160861A1 (fr) | Étalonnage d'un capteur pour un véhicule sur la base d'indices d'identification côté objet et côté image d'un objet de référence | |
DE102019210129A1 (de) | Verfahren zum Überprüfen einer Kalibrierung mehrerer Sensoren und Kraftfahrzeug mit mehreren Sensoren | |
DE102019124498A1 (de) | Verfahren zum Komprimieren von 3D-Punktdaten in einer mittels eines Detektionssystems eines Fahrzeugs erzeugten 3D-Punktwolke | |
EP4249957A1 (fr) | Étalonnage d'un système de capteur combiné pour un véhicule | |
WO2024028003A1 (fr) | Surveillance de l'orientation d'un dispositif de balayage laser | |
WO2023151856A1 (fr) | Appareil de surveillance pour une zone de stockage, agencement intralogistique doté de l'appareil de surveillance, et procédé de surveillance | |
DE202021004345U1 (de) | Fahrerloses Transportfahrzeug | |
WO2023104767A1 (fr) | Procédé et dispositif de détection d'objets au niveau d'un poste de travail industriel |
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: 23754704 Country of ref document: EP Kind code of ref document: A1 |