Method and device for controlling a vehicle's alert system in the presence of an object on the vehicle's roof
The method uses external cameras and neural networks to detect and alert drivers about roof objects, addressing the challenge of sensor complexity and improving road safety without vehicle modifications.
Patent Information
- Authority / Receiving Office
- FR · FR
- Patent Type
- Applications
- Current Assignee / Owner
- STELLANTIS AUTO SAS
- Filing Date
- 2024-11-20
- Publication Date
- 2026-05-22
AI Technical Summary
Existing vehicle systems struggle to detect objects on the roof without adding sensors, which is complex and not feasible for all vehicles, and some objects are not detected by current sensor technologies, posing risks of accidents and environmental pollution.
A method using external cameras connected to the vehicle, with object detection models like convolutional neural networks, to identify objects on the roof and alert the driver via wireless communication protocols, eliminating the need for additional vehicle sensors.
Enables effective detection and alerting of roof objects, reducing the risk of accidents and environmental pollution by informing drivers to remove the objects before they fall off, enhancing road safety without modifying the vehicle's design.
Smart Images

Figure 00000000_0000_ABST
Abstract
Description
Title of the invention: Method and device for controlling a vehicle's alert system in the presence of an object on the vehicle's roof. Technical field
[0001] The invention relates to methods, devices, and control systems for a vehicle warning system, particularly but not exclusively for a motor vehicle, based on the detection of an object on its roof. The invention also relates to a method and device for controlling a vehicle's driver assistance system based on the presence of an object on its roof. Technological background
[0002] It sometimes happens that an object is left on the roof of a vehicle. For example, during loading, an object is placed on the roof of the vehicle to be installed later. As another example, during a break, a passenger places an object on the roof of the vehicle, which is then being used as a table or counter.
[0003] Such an object is, for example: • a bag, • a mobile phone, • a cardboard box, • a cup, • a bassinet, etc...
[0004] Once the vehicle has been loaded or the break is over, the object placed on the roof is forgotten, and the person to whom the object belongs gets into the vehicle, which then starts moving. The object then travels a certain distance on the roof of the vehicle before falling off, risking breaking, obstructing traffic, causing an accident, or even disappearing along the road and polluting the environment.
[0005] Systems for monitoring the presence of an object on the vehicle's roof consist, for example, of installing sensors in the vehicle's roof bars, as described in document DE 10 2020 004 978 A1 published in 2020. However, adding sensors to a vehicle is complex, and not every vehicle has roof bars or a suitable mounting system for adding sensors. Furthermore, some objects are not detected by certain types of sensors, making the installation of one or more sensors on the vehicle even more complex. Summary of the present invention
[0006] One object of the present invention is to solve at least one of the problems of the technological background described above.
[0007] An object of the present invention is to enable the detection of an object on the roof of a vehicle without requiring the addition of a sensor on board the vehicle.
[0008] According to a first aspect, the present invention relates to a method for controlling a vehicle alert system, the vehicle belonging to a system comprising a set of external cameras connected in communication with the vehicle, the method being implemented by a set of processors of the system and comprising the following steps: - receiving image data representative of an image of the vehicle's roof from at least one camera in the external camera array, - detection of an object on the roof of the vehicle by an object detection model from image data; - emission of alert data representative of a detection result to the vehicle, the result being representative of the presence of an object; - control of the vehicle alert system based on alert data received by the vehicle.
[0009] Such a method makes it possible to alert the vehicle driver to the presence of an object on the vehicle's roof, allowing them to stop and remove the object before it falls off. Once removed, the object no longer poses a danger to other road users.
[0010] According to one variant of the process, the alert data is emitted via a vehicle-type wireless data exchange protocol with everything, called V2X.
[0011] According to another variant of the method, the object detection model is implemented by a convolutional neural network.
[0012] According to yet another variant of the method, the camera assembly comprises: - cameras mounted in other vehicles, and / or - cameras installed on buildings, and / or - cameras installed on road infrastructure.
[0013] According to a further variant of the method, the control of the warning system includes the emission of an audible signal via an audio system on board the vehicle and / or the display of a graphic object on a screen on board the vehicle.
[0014] According to another variant, the method further includes a step of checking a vehicle driver assistance system configured to stop the vehicle upon receipt of warning data.
[0015] According to one variant of the method, the detection step is implemented by a processor of the camera or by a processor of a remote server connected in communication with the camera.
[0016] According to a second aspect, the present invention relates to a control system for a vehicle warning system, the control system comprising a memory associated with a processor configured for the implementation of the steps of the process according to the first aspect of the present invention.
[0017] According to one variant, the control system further comprises a vehicle and a set of external cameras connected wirelessly to the vehicle.
[0018] According to a third aspect, the present invention relates to a computer program which includes instructions adapted for the execution of the steps of the process according to the first aspect of the present invention, in particular when the computer program is executed by at least one processor.
[0019] Such a computer program may use any programming language, and be in the form of source code, object code, or an intermediate form between source code and object code, such as in a partially compiled form, or in any other desirable form.
[0020] According to a fourth aspect, the present invention relates to a computer-readable recording medium on which is recorded a computer program comprising instructions for carrying out the steps of the process according to the first aspect of the present invention.
[0021] On the one hand, the recording medium can be any entity or device capable of storing the program. For example, the medium can include a storage means, such as a ROM, a CD-ROM or a microelectronic circuit-type ROM, or a magnetic recording means or a hard disk drive.
[0022] On the other hand, this recording medium can also be a transmissible medium such as an electrical or optical signal, such a signal being able to be transmitted via an electrical or optical cable, by conventional or radio frequency, by self-directing laser beam, or by other means. The computer program according to the present invention can, in particular, be downloaded from an Internet-type network.
[0023] Alternatively, the recording medium may be an integrated circuit in which the computer program is incorporated, the integrated circuit being adapted to execute or to be used in the execution of the process in question. Brief description of the figures
[0024] Other features and advantages of the present invention will become apparent from the description of the particular and non-limiting embodiments of the present invention below, with reference to the attached Figures 1 to 5, in which:
[0025] [Fig-1] schematically illustrates a vehicle with an object on the roof as seen by a on-board camera of another vehicle, according to a first particular embodiment of the present invention;
[0026] [Fig.2] schematically illustrates a vehicle with an object on the roof seen by a camera installed on a road infrastructure, according to a second particular and non-limiting embodiment of the present invention;
[0027] [Fig.3] partially and schematically illustrates a passenger compartment of a vehicle of [Fig.1] and / or [Fig.2], according to a particular and non-limiting embodiment of the present invention;
[0028] [Fig.4] schematically illustrates a system configured for controlling a vehicle warning system of [Fig.3], according to a particular and non-limiting embodiment of the present invention; and
[0029] [Fig.5] illustrates a flowchart of the different stages of a process for controlling the warning system of a vehicle of the [Fig.3], according to a particular and non-limiting example of the present invention. Description of examples of achievements
[0030] A method and a device for controlling a vehicle warning system, and more specifically for controlling based on the presence of an object on the roof of the vehicle, will now be described in what follows with joint reference to Figures 1 to 5. The same elements are identified with the same reference signs throughout the description that follows.
[0031] The terms "first," "second" (or "firsts," "seconds"), etc., are used in this document by arbitrary convention to allow for the identification and distinction of different elements (such as operations, means, etc.) implemented in the embodiments described below. Such elements may be distinct or correspond to a single element, depending on the embodiment.
[0032] Figure 1 schematically illustrates a first road environment in which a vehicle 10 is traveling with an object on its roof. The vehicle 10 corresponds, for example, to a vehicle with an internal combustion engine, an electric motor(s), or a hybrid vehicle with an internal combustion engine and one or more electric motors. The vehicle 10 thus corresponds, for example, to a land vehicle, such as a car, a truck, or a bus.
[0033] According to these first and second examples, vehicle 10 has an object placed on its roof. This object corresponds, for example, to: • a handbag, a backpack, a shopping bag, or • a mobile phone, or • a cardboard box of any size, or • a cup, a bottle, a baguette, or • a toy, a cuddly toy, or • a garment, or • a bassinet.
[0034] This list is not exhaustive, however, the invention extending to any object of any size, the only constraint being that it is visible and detectable in an image acquired by a camera, this constraint being associated with the definition of the images acquired by this camera and the quality of its optical system.
[0035] According to the first and second embodiments, the vehicle 10 is travelling on a road. According to other embodiments, the vehicle is stopped or parked, for example stopped at an intersection or parked in a parking space.
[0036] According to the first embodiment illustrated in [Fig. 1], vehicle 10 is followed by another vehicle 10a, this other vehicle 10a being equipped with a camera 101. Indeed, many modern vehicles are equipped with Advanced Driver-Assistance Systems (ADAS). Such ADAS systems are passive and active safety systems designed to eliminate the element of human error in driving all types of vehicles. ADAS systems use advanced technologies to assist the driver while driving and thus improve their performance. ADAS systems use a combination of sensor technologies to perceive the environment around a vehicle, then provide information to the driver or act on certain vehicle systems.
[0037] There are several levels of ADAS, such as reversing cameras and blind spot sensors, lane departure warning systems, adaptive cruise control, and automatic parking systems. Such ADAS systems installed in a vehicle are powered by data obtained from one or more on-board sensors, such as cameras. These cameras make it possible, in particular, to detect and locate other road users or any obstacles present around the other vehicle 10a in order, for example: - to adapt the lighting of the other vehicle 10a according to the presence of other road users; - to automatically regulate the speed of the other vehicle 10a; - to act on the braking system of the other vehicle 10a in case of risk of impact with an object.
[0038] According to the first particular embodiment illustrated in [Fig. 1], the vehicle 10 is in the field of vision 102 of the camera 101 mounted in the other vehicle 10a. Camera 101 therefore acquires images including pixels corresponding to vehicle 10 and the object on its roof.
[0039] According to a particular embodiment, the camera 101 includes or is associated with a device comprising a memory and a processor having access to this memory. In a first operation, image data representing an image of the roof of the vehicle 10 and of the object are then received from the camera 101.
[0040] In a second operation, the object on the roof is detected by an object detection model based on the image data. Such an object detection or segmentation model is known to those skilled in the art and corresponds, for example, to one of the following models: • Mask R-CNN®, suitable for object detection with precise contour segmentation. In addition to locating objects with bounding boxes, Mask R-CNN segments objects, making it an excellent choice for applications where the precise shape of the object is important, thus allowing for accurate identification of the type of object present on the roof of the vehicle 10. • YOLO® (from the English “You Only Look Once”), extremely fast and well suited to real-time applications, detects objects in their entirety in a single pass, making it suitable for images captured by cameras in systems requiring a rapid response such as when vehicle 10 and the other vehicle 10a are moving relative to each other. • SSD® (from the English “Single Shot MultiBox Detector” or “single shot multi-box detector” in French), offering a good compromise between speed and accuracy and being similar to YOLO® in terms of speed, it is also designed for real-time processing.
[0041] To detect an object in an image acquired by the camera 101, deep learning techniques are among the most effective and suitable, particularly because of their accuracy and their ability to detect objects in complex scenes, for example when the vehicle 10 is in a city center. Thus, according to this first particular embodiment, the second operation is implemented by a processor of the camera 101 using an object detection model implemented by a convolutional neural network.
[0042] According to another particular embodiment, this second operation is implemented by a processor of a remote server connected in communication with the camera 101 mounted in the other vehicle 10a.
[0043] In a third operation, alert data is transmitted by a communication device onboard the other vehicle 10a to vehicle 10. Vehicles 10a and 10 each advantageously carry a unit of communication, corresponding for example to a communication box of the type telematic control unit TCU (from the English "Telematic Control Unit"), BTA box ("Autonomous Telematic Box") or BSRF box ("Radio Frequency Servicing Box"). Such a unit is advantageously connected to one or more antennas 110 as illustrated in [Fig.2] for example to transmit and / or receive data to and / or from a remote device 112, for example a remote server of the "cloud" 100 (or "cloud" in French), a mobile communication device or another communication unit, via a wireless link, according to OTA technology (from the English "Over The Air" or in French "par voie aérienne") for example.
[0044] Wireless communication between vehicle 10 and the other vehicle 10a is established, for example, using a direct communication mode when the other vehicle 10a is at a short distance from vehicle 10 for a sufficient duration to allow such communication, for example, at a distance of less than 10, 20, or 50 meters (ten, twenty, or fifty meters) for several seconds. The wireless link is based, for example, on one or more wireless communication protocols such as: • Bluetooth®, • Wi-Fi® (based on IEEE 802.11), • LTE (Long-Term Evolution), • LTE-Advanced, • 3GPP (3rd Generation Partnership Project), fourth or fifth generation, also known as 3GPP 4G or 5G, or • NFC (from the English “Near Field Communication” or in French “Communication champ proche”).
[0045] According to another example not shown, wireless communication between vehicle 10 and the other vehicle 10a is established using an indirect communication method when the other vehicle 10a is too far from vehicle 10 or is near vehicle 10 for too short a time to allow such communication. The wireless link is based, for example, on a network comprising antennas connected to each other via one or more remote devices.
[0046] Thus, alert data is, for example, transmitted via a vehicle-to-everything (V2X) wireless data exchange protocol. In such a V2X communication system, each vehicle and / or infrastructure communication device carries a node (or wireless communication system / interface) to enable vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication. The English term "vehicle-to-infrastructure") and / or vehicle-to-pedestrian (V2P) communication involves pedestrians equipped with mobile devices (e.g., a smartphone) configured to communicate with vehicles. The alert data transmitted by the other vehicle 10a to vehicle 10 represents the outcome of the second operation, indicating the presence of an object. In other words, the alert data allows the other vehicle 10a to inform vehicle 10 of the presence of an object on its roof.
[0047] According to one variant, this alert data includes a type of object identified during the second operation.
[0048] In a fourth operation, the vehicle alert system of vehicle 10 is controlled from the alert data received by said vehicle 10 in order to alert an occupant of vehicle 10, for example its driver.
[0049] Figure 3 partially illustrates a passenger compartment of the vehicle 10, which, according to the illustrated example, comprises two screens 12 arranged on the dashboard 11 and behind the steering wheel 13, and an audio system comprising speakers 15 arranged in the doors 14 of the vehicle 10. The invention is not limited, however, to this type of arrangement; the alert system thus comprises at least one screen 12 and / or at least one speaker 15. It should be noted that these screens 12 and / or speakers 15 are connected to the communication unit described above and receive the alert data transmitted by the other vehicle 10a.
[0050] A screen 12 is, for example, touch-sensitive and corresponds, for example, to an LCD (Liquid Crystal Display), a TFT (Thin-Film Transistor), or an OLED (Organic Light-Emitting Diode). The screen 12 is, for example, arranged in the center of the dashboard, for example above a central panel. The screen allows content to be displayed for the driver and / or passengers of the vehicle 10. The screen 12 is also configured to allow the driver and / or passengers of the vehicle 10 to interact with one or more systems embedded in the vehicle 10 via a human-machine interface (HMI) displayed on the screen 12.For example, screen 12 allows control of an infotainment system, called IVI (from the English "in-vehicle infotainment" or in French "infodivertissement étoilé") and / or the vehicle alert system 10.
[0051] The screens 12 and / or speakers 15 are controlled, for example, by an IVI computer. The communication unit also includes a computer connected in communication with the IVI computer. These computers then form a multiplexed architecture for providing various services necessary for proper operation. of vehicle 10 and to assist the driver and / or passengers of vehicle 10 in the control of vehicle 10 via the control of the AD AS system(s) on board vehicle 10. The computers communicate and exchange data with each other via one or more computer buses, for example a CAN data bus (from the English "Controller Area Network" or in French "Réseau de contrôlers"), CAN FD (from the English "Controller Area Network Flexible Data-Rate" or in French "Réseau de contrôlers à débit de données flexible"), FlexRay (according to ISO 17458), LIN (from the English "Local Interconnect Network" or in French "Réseau interconnecté local") or Ethernet (according to ISO / IEC 802-3).
[0052] The control of the alert system then includes the emission of an audible signal via the speakers 15 of the audio system and / or the display of a graphic object on a screen 12. The audio signal corresponds, for example, to a ringtone or a voice message explaining to an occupant of the vehicle 10 that an object is present on the roof of the vehicle 10. The graphic object, for its part, corresponds to a pictogram, an indicator light or a text message displayed on one of the screens 12 mentioned above and also explaining to an occupant of the vehicle 10 that an object is present on the roof of the vehicle 10.
[0053] According to one embodiment, the vehicle 10 is an autonomous vehicle comprising one or more driver assistance systems enabling the vehicle 10 to be driven autonomously, for example, a lane departure warning system and / or a parking assistance system. Indeed, an autonomous vehicle is defined as a vehicle equipped with a sophisticated driver assistance system that ensures control of the vehicle and is capable of operating in its road environment without driver intervention or under the control of a person not involved in driving the autonomous vehicle, except in emergencies, for example. A vehicle enabling such autonomous driving must have a level of autonomous driving capability exceeding a certain level out of a total number of levels.For example, the autonomous vehicle has an autonomy level greater than or equal to 4 out of the 5 levels defined in the classification published by the federal agency responsible for road safety in the USA, or out of the 6 levels defined in the classification published by the international organization of motor vehicle manufacturers, which comprises 6 levels. According to an alternative embodiment, vehicle 10 has an autonomy level greater than or equal to 3 out of the 5 or 6 levels defined in the two classifications mentioned above.
[0054] According to this variant, a fifth operation is implemented to control a vehicle driver assistance system 10 configured to stop the vehicle 10 upon receiving warning data, i.e., to perform a parking maneuver, for example. Thus, the vehicle 10 is stopped to allow one of its occupants to remove the object which is on the roof of the vehicle 10. In order to avoid any untimely control of the vehicle 10, this fifth operation is for example subject to validation by an occupant of the vehicle 10, for example via the HMI including the screen 12 which is touch, the validation of the parking maneuver consisting of a touch press on a graphic object displayed on the screen 12 following the receipt of the alert data.
[0055] According to the second particular embodiment illustrated in [Fig. 2], which depicts a second road environment 1b, the vehicle 10 is within the field of view 102 of a camera 101 installed on a building, for example on a facade, or on road infrastructure, for example on a gantry overlooking the road on which the vehicle 10 is traveling or on a traffic light pole located along that same road. As in the embodiment illustrated in [Fig. 1], the camera 101 acquires images comprising pixels corresponding to the vehicle 10 and the object on its roof.
[0056] According to a particular embodiment, the camera 101 includes or is associated with a device comprising a memory and a processor having access to this memory. In a first operation, image data representing an image of the roof of the vehicle 10 and of the object are received from the camera 101, and in a second operation, the object on the roof is detected by an object detection model from the image data.
[0057] According to another particular embodiment, in a first operation the camera 101 transmits image data to a remote device 111. The image data representing an image of the roof of the vehicle 10 and of the object are then received by the remote device 111 from the camera 101 and in a second operation, the object on the roof is detected by an object detection model from the image data, the object detection model being implemented in the remote device 111. The result of the detection representing the presence of an object on the roof of the vehicle 10 is, for example, recorded on the cloud 100 and is made accessible from a second remote device 112, which is connected in communication with the vehicle 10 via an antenna 110.Thus, camera 101, remote devices 111 and 112, cloud 100 and antenna 110 are, for example, connected by wired links, while antenna 110 and vehicle 10 are connected by a wireless link.
[0058] In a third operation, alert data is transmitted by the remote device 111 or by the remote device 112 to the vehicle 10, the vehicle 10 advantageously comprising a communication unit. Thus, the alert data is transmitted, for example, via the V2X type wireless data exchange protocol.
[0059] In a fourth operation similar to the fourth operation shown with regard to the first particular embodiment, the vehicle alert system of the vehicle 10 is controlled from the received alert data in order to alert an occupant of vehicle 10, for example its driver.
[0060] Similarly, the variant in which vehicle 10 is an autonomous vehicle and includes the fifth operation is applicable to the second particular embodiment where appropriate.
[0061] It should be noted that the first and second specific embodiments are combinable, as the presence of an object on the roof of the vehicle 10 can be detected both by cameras 101 mounted in other vehicles 10a and by cameras 101 installed on buildings and road infrastructure. Thus, the cameras 101 belong to a set of external cameras connected in communication with the vehicle 10 and constitute a system. The processors or computers of this system, as well as the memories of this system, then constitute a control system configured to control the warning system of the vehicle 10.
[0062] According to a more general example, the control system further includes the vehicle 10 and the set of external cameras connected wirelessly to the vehicle 10.
[0063] Such a control system makes it possible to use images acquired by cameras external to the vehicle to monitor and alert a vehicle occupant to the presence of an object on the vehicle's roof. This eliminates the need to add any additional sensors or devices to the vehicle, simplifying the implementation of this solution and avoiding complicating vehicle design while still providing this new functionality.
[0064] Thanks to the vehicle's on-board alert system, a vehicle occupant is quickly informed of the presence of an object on the roof and is thus able to stop and retrieve the detected object. The risk of the object left on the roof falling and posing a danger to other road users is therefore greatly reduced; this on-board alert system thus contributes to improved road safety by preventing this risk.
[0065] Figure 4 illustrates a system configured for controlling a vehicle warning system, for example, the vehicle in Figure 3, according to a particular, non-limiting embodiment of the present invention. System 4 corresponds, for example, to an amalgamation of devices belonging to the control system defined above.
[0066] System 4 is, for example, configured to carry out the operations described opposite Figures 1 to 3 and / or the steps of the process described opposite [Fig. 5]. Examples of such a system 4 include, but are not limited to, embedded electronic equipment such as a vehicle's on-board computer, an electronic control unit such as an ECU (Electronic Control Unit), a A TCU (Transmission Control Unit) can be a controller, a computer, or a mobile communication device (e.g., one installed in a vehicle and connected to that vehicle via wired or wireless communication). The elements of System 4, individually or in combination, can be integrated into a single integrated circuit, multiple integrated circuits, and / or discrete components. System 4 can be implemented as electronic circuits, software (or computer) modules, or a combination of electronic circuits and software modules.
[0067] The system 4 comprises several processors 40 configured to execute instructions for carrying out the steps of the process and / or for executing instructions from the software embedded in the system 4. These processors correspond to the computers of the vehicle 10, the computers of the other vehicle 10a, the camera 101, and / or the remote device 111 and / or 112. Each processor 40 may include integrated memory, an input / output interface, and various circuits known to those skilled in the art. The system 4 further comprises at least one memory 41, corresponding, for example, to volatile and / or non-volatile memory, and / or includes a memory storage device that may include volatile and / or non-volatile memory, such as EEPROM, ROM, PROM, RAM, DRAM, SRAM, flash, magnetic disk, or optical disk.
[0068] The computer code of the software embedded or installed in these processors includes the instructions to be loaded and executed by each processor and is, for example, stored in memory 41, which can be distributed among the different devices of system 4.
[0069] According to various particular and non-limiting embodiments, the system 4 is coupled in communication with other similar devices or systems and / or with communication devices, for example a TCU (Telematic Control Unit), for example via a communication bus or through dedicated input / output ports.
[0070] According to a particular and non-limiting embodiment, the system 4 includes a block 42 of interface elements for communicating with external devices. The interface elements of block 42 include one or more of the following interfaces: - radio frequency (RF) interface, for example, Wi-Fi® type (according to IEEE 802.11), for example in the 2.4 or 5 GHz frequency bands, or Bluetooth® type (according to IEEE 802.15.1), in the 2.4 GHz frequency band, or Sigfox® type using UBN (Ultra Narrow Band) radio technology, or LoRa in the 868 MHz frequency band, LTE (Long- Long-term Evolution” or in French “Long-term Evolution”), LTE-Advanced (or in French LTE-advanced); - USB interface (from the English "Universal Serial Bus" or "Universal Serial Bus" in French); - HDMI interface (from the English "High Definition Multimedia Interface", or "High Definition Multimedia Interface" in French); - LIN interface (from the English "Local Interconnect Network", or in French "Réseau interconnecté local").
[0071] According to another particular and non-limiting embodiment, the system 4 includes a communication interface 43 which enables communication with other devices (such as other computers in the vehicle's on-board system) via a communication channel 430. The communication interface 43 corresponds, for example, to a transmitter configured to transmit and receive information and / or data via the communication channel 430. The communication interface 43 corresponds, for example, to a wired network of the CAN (Controller Area Network), CAN FD (Controller Area Network Flexible Data-Rate), FlexRay (standardized by ISO 17458) or Ethernet (standardized by ISO / IEC 802-3) type.
[0072] According to a particular and non-limiting embodiment, the system 4 can provide output signals to one or more external devices, such as a display screen 440 and / or 12, touch or non-touch, one or more speakers 450 and / or 15 and / or other peripherals 460 (projection system) via output interfaces 44, 45 and 46 respectively. According to a variant, one or more of the external devices is integrated into the system 4.
[0073] Figure 5 illustrates a flowchart of the various steps in a method for controlling a vehicle's warning system, for example, the vehicle in Figure 3, according to a particular and non-limiting embodiment of the present invention. The method is implemented, for example, by a set of processors or devices in a system comprising a set of external cameras connected in communication with a vehicle, or by system 4 in Figure 4.
[0074] In a first step 51, image data is received from at least one camera of an array of external cameras. This image data is representative of an image of a vehicle roof.
[0075] In a second step 52, an object is detected on the roof of the vehicle by an object detection model from image data.
[0076] In a third step 53, alert data is sent to the vehicle, this alert data being representative of a result of the detection, this result being representative of the presence of an object on the roof.
[0077] In a fourth step 54, a vehicle alert system is controlled from the alert data received by the vehicle.
[0078] According to one variant, the variants and examples of the operations described in relation to Figures 1 to 3 apply to the steps of the process in [Fig. 5].
Claims
Demands
1. A method for controlling a vehicle (10) warning system, said vehicle (10) belonging to a system comprising a set of external cameras connected in communication with said vehicle (10), said method being characterized in that it is implemented by a set of processors of said system and comprises the following steps: - receiving (51) image data representative of an image of a roof of the vehicle (10) from at least one camera (101) of said set of external cameras, - detecting (52) an object on said roof by an object detection model from said image data; - transmitting (53) warning data representative of a result of said detection to said vehicle (10), said result being representative of the presence of an object; - controlling (54) the vehicle warning system from said warning data received by said vehicle (10).
2. A method according to claim 1, wherein the alert data is transmitted via a vehicle-type wireless data exchange protocol with anything, referred to as V2X.
3. A method according to claim 2, wherein the object detection model is implemented by a convolutional neural network.
4. A method according to any one of claims 1 to 3, wherein the camera array comprises: - cameras mounted in other vehicles, and / or - cameras installed on buildings, and / or - cameras installed on road infrastructure.
5. A method according to any one of claims 1 to 4, wherein the control of the warning system includes the emission of an audible signal via an audio system (15) mounted in the vehicle (10) and / or the display of a graphic object on a screen (12) mounted in the vehicle (10).
6. A method according to any one of claims 1 to 5, further comprising a step of controlling a vehicle driver assistance system (10) configured to stop the vehicle (10) upon receipt of warning data.
7. A method according to any one of claims 1 to 6, wherein the detection step (52) is implemented by a processor of said camera (101) or by a processor of a remote server (111) connected in communication with said camera (101).
8. Computer program comprising instructions for carrying out the method according to any one of claims 1 to 7, when such instructions are executed by at least one processor.
9. Control system (4) for a vehicle (10) warning system, said control system (4) comprising a memory (41) associated with a set of processors (40) configured for carrying out the steps of the method according to any one of claims 1 to 7
10. / . Control system (4) according to claim 9 further comprising a vehicle (10) and a set of external cameras connected in wireless communication with said vehicle (10).