Method for estimating the distance between a motor vehicle and an external object, device, computer program and associated motor vehicle

Abstract

Method for estimating the distance between a motor vehicle and an external object, device, computer program, and associated motor vehicle. The invention relates to estimating the distance between a motor vehicle (4) and an external object (8), the vehicle being equipped with at least one camera (26) for capturing digital images within a capture field, the vehicle (4) comprising an on-board computing device (22) adapted to calculate estimated characteristics of at least one external object located within said capture field, comprising, for each external object, a first estimated position information for said object. A parameterized computing engine takes as input the estimated characteristics and provides a second corrected position information for said external object, used to estimate the distance between the motor vehicle and the external object.The values ​​of the calculation engine parameters are obtained in a preliminary learning phase, taking into account, for each external object, the characteristics estimated from digital images and reference points obtained by at least one remote sensing sensor. Figure for the abbreviation: Figure 1.

Description

Title of the invention: Method for estimating a distance between a motor vehicle and an external object, associated device, computer program and motor vehicle

[0001] The present invention relates to a method for estimating a distance between a motor vehicle and an object external to said vehicle, the motor vehicle being equipped with at least one camera configured to capture digital images in a capture field outside the motor vehicle.

[0002] The invention also relates to a device for estimating a distance between a motor vehicle and an object external to said associated vehicle, and an associated computer program.

[0003] The invention further relates to a motor vehicle comprising a device for estimating a distance between the motor vehicle and an external object.

[0004] The invention lies in the field of safe piloting of motor vehicles, and finds applications in particular in the field of automatic piloting of autonomous motor vehicles.

[0005] Indeed, in the field of safe piloting of motor vehicles, and in particular in automatic or semi-automatic piloting, it is necessary to identify and spatially position, over time, any object external to the vehicle in question, also called its own vehicle or "ego-vehicle" in English, so as to avoid any collision.

[0006] In particular, an object external to the vehicle, for example a moving external object, becomes an obstacle if it follows a trajectory likely to cross the trajectory of the motor vehicle in question.

[0007] Such collision risk detection is also useful in driver assistance systems, even for motor vehicles with a driver on board.

[0008] A critical safety issue is the early detection of obstacles in the path of a moving vehicle, allowing corrective action to be taken to prevent the vehicle from hitting those obstacles.

[0009] Motor vehicles are equipped with sensors, in particular image capture sensors such as one or more cameras configured to capture digital images, as well as optionally radar sensors making it possible to detect external objects, potential obstacles, in an external environment of the motor vehicle in question, by radar technology.

[0010] Automobile driving assistance systems, called AD AS systems for “Advanced Driver Assistance Systems”, and identification and obstacle avoidance for autonomous vehicles.

[0011] A system is known for detecting external objects and estimating characteristics of each detected external object, including position information in a given representation plane, from digital images captured by one or more on-board cameras, by applying processing of the captured digital images. However, the positioning reliability obtained by such digital image processing is not always sufficient, which may, in certain cases, prove critical.

[0012] There is a need to improve the accuracy of the positioning of external objects detected relative to the motor vehicle in question, while avoiding a high computational overhead.

[0013] To this end, the invention proposes, according to one aspect, a method for estimating a distance between a motor vehicle and an external object, the motor vehicle being equipped with at least one camera configured to capture digital images in a capture field outside the motor vehicle, the vehicle comprising an on-board computing device adapted to process said captured digital images and calculate estimated characteristics of at least one external object located in said capture field, said estimated characteristics comprising, for each external object, a first item of information on the estimated position of said object in a coordinate system in which said motor vehicle is also positioned. This method comprises the implementation, by a processor of said on-board computing device:

[0014] -for the or each external object, a provision of said characteristics estimated from the digital images captured as input to a parameterized calculation engine, trained by machine learning in a prior learning phase, said calculation engine being configured to provide a second corrected position information of said external object, and

[0015] -an estimation of a distance between the motor vehicle and the external object as a function of a current position of the motor vehicle and said second corrected position information.

[0016] In the preliminary learning phase, machine learning of the values ​​of the parameters of said calculation engine is implemented, taking into account, for each external object, the estimated characteristics of said external object from the captured digital images and reference points obtained by at least one remote sensing sensor.

[0017] Advantageously, the method of the invention implements a parameterized calculation engine, configured to calculate corrected position information, this calculation engine being trained by machine learning to provide such information. corrected position, from reference points obtained by at least one on-board remote sensing sensor in addition to the characteristics estimated from digital images.

[0018] The method for estimating a distance between a motor vehicle and an external object according to the invention may also have one or more of the characteristics below, taken independently or in all technically conceivable combinations.

[0019] At least one remote sensing sensor providing said reference points is a LIDAR sensor.

[0020] The motor vehicle is equipped with at least one radar sensor providing instantaneous radar points, said instantaneous radar points being further provided as input to said calculation engine.

[0021] The machine learning of the values ​​of the parameters of the calculation engine further takes into account a speed of movement of said external object, and in which the calculation engine takes as input an instantaneous speed of said external object.

[0022] The instantaneous speed of said external object is calculated from said captured digital images.

[0023] The instantaneous speed of said external object is obtained from radar points provided by at least one on-board radar sensor.

[0024] The estimated characteristics further comprise, for each external object, a classification of said external object in a class of objects among a plurality of predetermined classes, said classification being provided as input to said calculation engine.

[0025] The estimated characteristics comprise, for a detected external object, a rectangular frame in which said external object is located, said first estimated position information comprising coordinates in said coordinate system of at least two corners of said rectangular frame.

[0026] The preliminary learning phase comprises, for at least one vehicle and at least one object external to said vehicle, a reception of learning data comprising estimated characteristics of the external object and of a plurality of points obtained by at least one on-board remote sensing sensor, then an extraction, from the plurality of remote sensing points, of at least one reference point associated with said external object, said reference point being, for a given external object, the closest remote sensing point, according to a chosen metric, to said vehicle and to a corner of the frame representing said external object.

[0027] According to another aspect, the invention relates to a device for estimating a distance between a motor vehicle and an external object, the motor vehicle being equipped with at least one camera configured to capture digital images in a capture field outside the motor vehicle, the vehicle comprising a on-board computing device adapted to process said captured digital images and calculate estimated characteristics of at least one external object located in said capture field, said estimated characteristics comprising, for each external object, first information on the estimated position of said object in a coordinate system in which said motor vehicle is also positioned, the device comprising a processor configured to implement:

[0028] -for the or each external object, a module for providing said characteristics estimated from the digital images captured as input to a parameterized calculation engine, trained by machine learning in a prior learning phase, said calculation engine being configured to provide a second corrected position information of said external object, and

[0029] - a module for estimating a distance between the motor vehicle and the external object as a function of a current position of the motor vehicle and said second corrected position information,

[0030] values ​​of the parameters of said calculation engine being obtained by implementing, in the preliminary learning phase, machine learning of the values ​​of the parameters of said calculation engine taking into account, for each external object, the estimated characteristics of said external object from the captured digital images and reference points obtained by at least one remote sensing sensor.

[0031] The device for estimating a distance between a motor vehicle and an external object is configured to implement the method for estimating a distance between a motor vehicle and an external object as briefly described above, according to all its variants.

[0032] According to another aspect, the invention relates to an information recording medium, on which are stored software instructions for the execution of a method for estimating a distance between a motor vehicle and an external object as briefly described above, when these instructions are executed by a programmable electronic device.

[0033] According to another aspect, the invention also relates to a computer program comprising software instructions which, when executed by a programmable electronic device, implement such a method for estimating a distance between a motor vehicle and an external object as briefly described above.

[0034] According to another aspect, the invention relates to a motor vehicle equipped with at least one camera configured to capture digital images in a capture field outside the motor vehicle, the vehicle comprising an on-board computing device adapted to process said captured digital images and calculate estimated characteristics of at least one external object located in said capture field. capture, said estimated characteristics comprising, for each external object, first information on the estimated position of said object in a coordinate system in which said motor vehicle is also positioned, and comprising a device for estimating a distance between said motor vehicle and an external object as briefly described above.

[0035] The invention will appear more clearly on reading the description which follows, given solely by way of non-limiting example, and made with reference to the drawings in which:

[0036] [Fig-1] [Fig.l] is a schematic representation of a top view of a motor vehicle equipped with cameras and radar sensors and external objects and radar points detected;

[0037] [Fig.2] [Fig.2] is a schematic representation of a system for estimating a distance between a motor vehicle and an external object;

[0038] [Fig.3] [Fig.3] is a flowchart of the main steps of an estimation process of a distance between a motor vehicle and an external object, in the operating phase, according to one embodiment;

[0039] [Fig.4] [Fig.4] is a flowchart of the main steps of an estimation process of a distance between a motor vehicle and an external object, in the learning phase, according to one embodiment;

[0040] [Fig.5] [Fig.5] is a schematic example of the correction of the position of objects external to a motor vehicle in question.

[0041] The invention applies to any type of motor vehicle, with driver on board, semi-autonomous or autonomous.

[0042] [Fig.l] illustrates a schematic top view 2 of a motor vehicle 4 (which is the vehicle considered or “ego-vehicle” in English), and of a plurality of external objects.

[0043] View 2 is a schematic representation in a representation plane, at a given time instant, it being understood that when the vehicle 4 is moving, a succession of such representations 2 is obtained.

[0044] For example, vehicle 4 is moving along a road, not shown in [Fig.l].

[0045] The motor vehicle 4 is represented schematically by a rectangular frame. The representation plane of [Fig.l] is a plan in top view of the scene.

[0046] Frames 6 are also shown in the figure, these frames being representative of the external objects, the external objects being detected by a detection method and categorized into a plurality of predetermined categories.

[0047] Each frame, sized according to the category of the object, is positioned according to the position and orientation of the detected object, the frame being placed at most close to the contours of the detected object in the representation plane.

[0048] The frames 6 are preferably rectangular in shape. Thus, the position of such a rectangular frame is easy to express, for example via the position of the corners or the position of the geometric center and the dimensions of the sides. The position of a point (eg corner or geometric center) is for example expressed by coordinates in a coordinate system (or reference frame) of the representation plane, for example a scalar coordinate system (O, X, Y) associated with the motor vehicle as shown in [Fig. 1].

[0049] In addition to the frames 6 indicating the estimated position of the external objects, corresponding external objects 8 are represented by hatched areas in [Fig.l]. The hatched areas represent the actual position (or ground truth) of the external objects.

[0050] External objects are, for example, other motor vehicles, bicycles or pedestrians, or fixed roadside objects.

[0051] The motor vehicle 4 is equipped with several sensors, e.g. at least one digital camera, preferably a two-dimensional digital camera configured to capture two-dimensional digital images of the external environment of the vehicle at successive instants in time.

[0052] In the example illustrated, the vehicle 4 is equipped with four cameras 26, positioned respectively at the front, at the rear, on the right side flank and on the left side edge of the vehicle.

[0053] For example, considering that the front of the vehicle 4 is indicated by the X axis, the cameras are monocular cameras, each camera having an associated field of view 10i to 104: 10i is the field of view of the camera 26i located at the front of the vehicle 4, 102 is the field of view of the camera 262 located at the rear of the vehicle 4, 103 is the field of view of the camera 263 located on the right side of the vehicle 4, 104 is the field of view of the camera 264 located on the left side of the vehicle 4.

[0054] In addition, the vehicle 4 is equipped with at least one radar sensor 25, and more particularly with a plurality of radar sensors 25 in the example of [Fig.l], for example four radar sensors located respectively at the front, at the rear and on the lateral sides of the vehicle. Each of the radar sensors 25 has an associated capture field 15. In [Fig.l] a sensor 251 and the associated capture field 15i are shown.

[0055] More generally, the on-board sensors 25 are remote sensing sensors, in particular radar or LIDAR sensors.

[0056] Points resulting from detection by radar sensors, called radar points, referenced by the reference 12, are also obtained and positioned by their position (eg coordinates in the chosen coordinate system) detected in the representation plane. sensation.

[0057] The method of the invention makes it possible to correct a first piece of information on the estimated position of objects external to the vehicle, from a processing of digital images, for example obtained by on-board monocular cameras, to obtain a second piece of corrected position information, closer to the actual position of the external objects 8.

[0058] Thus, the estimation of the distance between each external object and the vehicle 4 considered is improved in precision, which makes it possible to improve the prevention of collision risk.

[0059] [Fig.2] schematically represents a system for estimating the distance between a motor vehicle and an external object.

[0060] The system is of course applicable for an estimation of distance between the motor vehicle and each external object detected in an environment close to the vehicle, for example within a radius of 80 meters around the vehicle, preferably within a radius of 20 meters.

[0061] The system 20 comprises on the one hand a device 22 for estimating the distance between a motor vehicle 24 and an external object (not shown in [Fig.2]).

[0062] The device 22 is a programmable electronic device, which is a computing device on board the vehicle 24, for example an on-board computer.

[0063] The vehicle 24 further comprises one or more cameras 26, which are for example monocular camera type cameras.

[0064] Optionally, the vehicle 24 carries one or more radar sensors 25.

[0065] The system 20 also comprises an electronic calculation device 30.

[0066] This electronic calculation device 30 is for example located in a calculation center, i.e. it is not embedded.

[0067] The device 22 implements an estimation of distance between the vehicle 24 considered and an external object in an operating phase, implemented in the vehicle 24 in conditions of use of this vehicle, i.e. when it moves between a point A and a point B.

[0068] In the example of [Fig.2], the electronic device 22 for estimating a distance between the vehicle 24 and an external object comprises an information processing unit, formed for example by a processor 32 and an electronic memory unit 34 associated with the processor 32. The electronic device 22 further comprises, as an option, a communication unit 36, configured to communicate according to a chosen communication protocol with a remote device.

[0069] This electronic device 22 comprises a module 38 for processing captured digital images, which provides estimated characteristics of at least one object external to the vehicle 24, these estimated characteristics comprising, for each external object, an estimate of a first estimated position information in a chosen representation plane.

[0070] For example, the chosen representation plane is a top view plane, and the first estimated position information comprises the coordinates of the respective corners of a rectangular frame of the detected external object, in the chosen coordinate system.

[0071] The estimated characteristics also include a classification of the external object among a plurality of predetermined classes.

[0072] For example, the plurality of predetermined classes includes the following classes: {pedestrian, bicycle, motorcycle, car, truck}.

[0073] The electronic device 22 further comprises a module 40 for implementing a parameterized calculation engine 55, trained by machine learning in a prior learning phase. For each external object detected, input data comprising the characteristics estimated by the module 38 are provided as input to the calculation engine, this calculation engine being configured to calculate a second corrected position information of the external object.

[0074] Optionally, the input data includes instantaneous radar points, obtained by the on-board radar sensor(s).

[0075] In addition, in embodiments, the input data comprises an estimated speed of the vehicle 24. The estimated speed is for example calculated from the instantaneous radar points.

[0076] Alternatively, the estimated speed is calculated from successive digital images, by object tracking between successive images.

[0077] The electronic device 22 also comprises a module 42 for estimating the distance between each detected external object and the motor vehicle 24, as a function of a current position of the vehicle and the second corrected position information.

[0078] In one embodiment, the modules 38, 40, 42 are each produced in the form of software, or a software brick, executable by the processor 32.

[0079] The memory 34 of the electronic device 22 is then capable of storing software for processing captured digital images to calculate estimated characteristics of at least one object external to the vehicle 24, software for implementing a calculation engine and software for estimating the distance between each detected external object and the motor vehicle 24.

[0080] The processor is then able to execute each of the software programs among the software for processing captured digital images to calculate estimated characteristics of at least one object external to the vehicle 24, the software for implementing a calculation engine and the software for estimating the distance between each detected external object and the motor vehicle 24.

[0081] In a variant not shown, the modules 38, 40 and 42 are each produced in the form of a programmable logic component, such as an FPGA (Field Programmable Gate Array) or an integrated circuit, such as an ASIC (Application Specific Integrated Circuit).

[0082] In the embodiment where the modules 38, 40 and 42 are produced in the form of executable software instructions, that is to say in the form of a computer program, also called a computer program product, this program is furthermore capable of being recorded on a medium, not shown, readable by a computer. The computer-readable medium is for example a medium capable of storing electronic instructions and of being coupled to a bus of a computer system. By way of example, the readable medium is an optical disk, a magneto-optical disk, a ROM memory, a RAM memory, any type of non-volatile memory (for example FLASH or NVRAM) or a magnetic card.

[0083] The electronic calculation device 30 implements a preliminary learning phase by machine learning of the parameters of the calculation engine 40.

[0084] Preferably, the calculation engine 40 implements a prediction model trained by the XGBoost (eXtreme Gradient Boosting) machine training method, known in the field of artificial intelligence.

[0085] Machine learning is performed on training input data comprising correction information, in the form of reference points associated with the representative frames of the external objects.

[0086] Thus, in one embodiment, the calculation engine 40 is trained in the learning phase to provide as output second position information corrected as a function of first position information obtained as input, and reference points.

[0087] The electronic device 30 comprises an information processing unit, formed for example by a processor 50 and an electronic memory unit 52 associated with the processor 50. The electronic device 30 further comprises, optionally, a communication unit 54, configured to communicate according to a chosen communication protocol with a remote device.

[0088] This electronic device 30 comprises a module 56 for receiving learning data 58, for example stored in the electronic memory 52.

[0089] Alternatively, the training data 58 are received via the communication unit 54 from one or more external devices.

[0090] The training data 58 are provided for a vehicle and an object external to the vehicle, at successions of time instants in a time interval of processing, and include: estimated characteristics 60 by image processing, including first position information in the coordinate system; radar points 62, obtained by at least one radar sensor on board the vehicle, defined by coordinates in the coordinate system, and remote sensing points 64, obtained by at least one on-board remote sensing sensor, preferably a LIDAR sensor.

[0091] The electronic device 30 also comprises a module 66 for extracting reference points, which are associated with the external object and which are tracked during a time interval, as explained in more detail below.

[0092] Finally, the electronic device 30 comprises a module 68 for machine learning the values ​​of the parameters of the calculation engine 40 to provide corrected positions relative to the estimated positions using the reference points. In particular, the module 68 provides as output values ​​of parameters 55 of the calculation engine 40.

[0093] In one embodiment, the modules 56, 66, 68 are each produced in the form of software, or a software brick, executable by the processor 50.

[0094] The memory 52 of the electronic device 30 is then capable of storing software for receiving learning data, software for extracting, from the plurality of remote sensing points, reference points, which are associated with the external object and which are tracked during a time interval and software for machine learning the values ​​of the parameters of the calculation engine 40. The processor 50 is then capable of executing each of these software programs.

[0095] In a variant not shown, the modules 56, 66, 68 are each produced in the form of a programmable logic component, such as an FPGA (Field Programmable Gate Array) or an integrated circuit, such as an ASIC (Application Specific Integrated Circuit).

[0096] In the embodiment where the modules 56, 66, 68 are produced in the form of executable software instructions, that is to say in the form of a computer program, also called a computer program product, this program is furthermore capable of being recorded on a medium, not shown, readable by a computer. The computer-readable medium is for example a medium capable of storing electronic instructions and of being coupled to a bus of a computer system. By way of example, the readable medium is an optical disk, a magneto-optical disk, a ROM memory, a RAM memory, any type of non-volatile memory (for example FLASH or NVRAM) or a magnetic card.

[0097] [Fig.3] is a synopsis of the main steps of a method for estimating a distance between a motor vehicle and an external object, according to one embodiment, in the operating phase, implemented by an electronic device 22 embedded in a specific motor vehicle, simply called vehicle hereinafter.

[0098] The method comprises a step 70 of capturing digital images and calculating, for each detected external object, estimated characteristics comprising first estimated position information, and optionally a classification of the detected object in a class among a plurality of predetermined classes.

[0099] This step 70 can be implemented, in certain embodiments, by a specific information processing unit, associated with the on-board camera(s).

[0100] For example, step 70 implements image segmentation or any other image processing method for detecting objects in the images.

[0101] The method comprises a step 72, implemented for each detected external object, of providing the estimated characteristics for the external object considered as input to the corrected position calculation engine, previously trained by learning, and of executing this calculation engine.

[0102] At the output of step 72, a second corrected position is obtained for the external object considered, in the chosen coordinate system.

[0103] For example, the chosen coordinate system is a reference frame of the chosen representation plane, which is, for example, a plane parallel to the plane tangent to the route followed by the vehicle.

[0104] For example, the vehicle and the external object are each represented by a rectangular frame in this plane.

[0105] The first position of the external object is defined by the respective positions of the corners of the frame associated with the external object, as shown in [Fig.l].

[0106] In one embodiment, the current position of the vehicle is for example the position (0,0) in the chosen coordinate system, as shown in [Fig.l].

[0107] At the output of step 72 a second corrected position of the external object is provided, the correction consisting for example of a displacement vector and an orientation correction.

[0108] The method then comprises a step 74 of estimating the distance between the external object and the vehicle, as a function of the current position of the vehicle (at the current time t) and the second corrected position of the external object.

[0109] Advantageously, when the reference frame is associated with the vehicle, the distance is obtained directly from the second corrected position in this reference frame.

[0110] According to a variant, the distance between the point of the rectangular frame associated with the external object, according to the second corrected position, closest to the rectangular frame associated with the vehicle is evaluated.

[0111] Steps 70 to 74 are repeated for a succession of instants in a time interval.

[0112] The result of the distance estimation between the vehicle and the external object is provided to an automatic or semi-automatic vehicle guidance application.

[0113] Alternatively, this distance is compared to a proximity threshold, and an alert to the driver is raised if the proximity threshold is reached (audio, visual or other alert).

[0114] According to variants, when the vehicle is equipped with radar sensors, the positions of instantaneous radar points, obtained in real time by the radar sensors, are provided as input to step 72.

[0115] According to variants, the estimated characteristics further comprise an estimated speed of the external object. Taking into account the estimated speed of the external object, previously used in the phase of learning the parameters of the corrected position calculation engine, also makes it possible to improve the accuracy of the second corrected position of the external object. For example, the estimated speed of the external object is calculated from the digital images captured successively or from the instantaneous radar points.

[0116] [Fig.4] is a synopsis of the main stages of a method for estimating a distance between a motor vehicle and an external object, in the learning phase, implemented by an electronic device 30, according to one embodiment.

[0117] The method comprises, for each external object, a step 80 of receiving learning data comprising: estimated characteristics 76 of the external object from the captured digital images, which are for example two-dimensional digital images, of instantaneous radar points 78 obtained by at least one radar sensor; and instantaneous remote sensing points 75, obtained by at least one remote sensing sensor, for example a LIDAR sensor.

[0118] Advantageously, LIDAR technology makes it possible to obtain a large number of points, and consequently good positioning precision.

[0119] The estimated characteristics 76 include the estimated position of the external object, in particular the size and orientation of the frame associated with the object.

[0120] The method comprises a step 82 of extracting reference points from the instantaneous remote sensing points.

[0121] Step 82 comprises, in one embodiment: - A) a grouping, also called clustering, of remote sensing points (eg LIDAR points) to form groups (or clusters) of points. For example, the DBSCAN algorithm (“density-based spatial clustering of applications with noise”) is applied; - B) for each of the clusters, a determination of the end points (top, bottom, right, left). The number of end points is equal to 2 when the points are aligned, but it can be equal to 3 or 4 depending on the cases; - C) for each cluster, an identification of the nearest endpoint of the vehicle; - D) for each external object, determine the corner of the frame representative of the object closest to the vehicle, and associate this corner with the closest end point obtained in step C) as a reference point;

[0122] Proximity is evaluated according to a chosen metric, for example the Euclidean distance.

[0123] Thus, for each external object detected, a reference point is associated with one of the corners of the frame defining the object, which makes it possible to correct by the position of the frame in translation

[0124] In addition, the orientation of the frame defining the detected external object is either obtained from image processing or obtained by implementing motion tracking from the remote sensing points on successive frames, which makes it possible to determine the orientation of the frame.

[0125] According to variants, several reference points are associated with the frame of a detected external object.

[0126] Optionally, the method comprises an estimation 84 of the speed of the external object, making it possible to obtain an estimated speed of the external object.

[0127] According to one embodiment, the estimated speed is obtained from the successive digital images captured by the on-board cameras.

[0128] Alternatively, the estimated speed is obtained from the positions of instantaneous radar points.

[0129] Steps 80 to 84 are iterated for one or more vehicles considered and several external objects, so as to form a learning database 85.

[0130] Then the method comprises an implementation 86 of machine learning of the parameters of the calculation engine 40 from the learning database 85.

[0131] For example, step 86 implements the XGBoost supervised training method on a chosen architecture prediction model.

[0132] [Fig.5] schematically illustrates an application scenario.

[0133] In the left part of the figure is represented, in the representation plane in top view, the own motor vehicle 4, as well as rectangular frames of the external objects detected in their first estimated positions: a frame 6Ai corresponding to a first external vehicle, for example an automobile, located behind the vehicle 4, in the same traffic lane; a frame 6Bi corresponding to a second external vehicle, for example an automobile, located substantially in parallel with the vehicle 4, in a parallel traffic lane; two frames 6Ci, 6Di located in front of the vehicle 4, on the same traffic lane as the second external vehicle detected.

[0134] The first positions of the respective frames for example given by the position in the chosen coordinate system, for example the reference system associated with vehicle 4 as represented in [Fig.l], and the orientation of each frame relative to one of the axes of the coordinate system, considering that the dimensions of length and width are known, for example as a function of the associated class.

[0135] Radar points are also positioned in the representation plane.

[0136] In the right part of the figure is represented, in the representation plane in top view, the own motor vehicle 4, as well as rectangular frames of the external objects detected in their second corrected positions: the frame 6A2 corresponding to the first external vehicle; the frame 6B2 corresponding to the second external vehicle; the frame 6C2 corresponding to a third external vehicle, for example a 2-wheeled vehicle.

[0137] The gray areas 8A, 8B, 8C represented correspond to the “real” vehicles present.

[0138] Thus, we observe on the right part of the figure that the positions of the vehicles 6Ai, 6Bi and 6Ci are corrected in 6A2, 6B2 and 6C2, these corrected positions corresponding more precisely to the real positions 8A, 8B and 8C.

Claims

Claims

1. Method for estimating a distance between a motor vehicle (4, 24) and an external object (8), the motor vehicle (4, 24) being equipped with at least one camera (26) configured to capture digital images in a capture field outside the motor vehicle, the vehicle (4, 24) comprising an on-board computing device (22) adapted to process said captured digital images and calculate estimated characteristics of at least one external object located in said capture field, said estimated characteristics comprising, for each external object, a first item of information on the estimated position of said object in a coordinate system in which said motor vehicle (4, 24) is also positioned, the method being characterized in that it comprises the implementation, by a processor (32) of said on-board computing device (22): -for the or each external object,a supply (72) of said characteristics estimated from the digital images captured as input to a parameterized calculation engine, trained by machine learning in a prior learning phase, said calculation engine being configured to provide a second corrected position information of said external object, and - an estimation (74) of a distance between the motor vehicle and the external object as a function of a current position of the motor vehicle and of said second corrected position information, and in which in the prior learning phase, a machine learning (86) of the values of the parameters of said calculation engine is implemented taking into account, for each external object, the estimated characteristics of said external object from the captured digital images and from reference points obtained by at least one remote sensing sensor.,

2. The method of claim 1, wherein at least one remote sensing sensor providing said reference points is a LIDAR sensor.

3. Method according to claim 1 or 2, the motor vehicle being equipped with at least one radar sensor (25) providing instantaneous radar points, said instantaneous radar points being further provided as input to said calculation engine.

4. Method according to one of claims 1 to 3, in which the machine learning (86) of the values of the parameters of the calculation engine takes into account further takes into account a speed of movement of said external object, and in which the calculation engine takes as input an instantaneous speed of said external object.

5. A method according to claim 4, wherein the instantaneous speed of said external object is calculated from said captured digital images.

6. Method according to claim 4, wherein the instantaneous speed of said external object is obtained from radar points provided by at least one on-board radar sensor.

7. Method according to one of claims 1 to 6, in which said estimated characteristics further comprise, for each external object, a classification of said external object in a class of objects among a plurality of predetermined classes, said classification being provided as input to said calculation engine.

8. Method according to one of claims 1 to 7, wherein the estimated characteristics comprise, for a detected external object, a rectangular frame (6) in which said external object is located, said first estimated position information comprising coordinates in said coordinate system of at least two corners of said rectangular frame.

9. Method according to claim 8, in which the preliminary learning phase comprises, for at least one vehicle and at least one object external to said vehicle, a reception of learning data comprising estimated characteristics of the external object and of a plurality of points obtained by at least one on-board remote sensing sensor, then an extraction, from the plurality of remote sensing points, of at least one reference point associated with said external object, said reference point being, for a given external object, the closest remote sensing point, according to a chosen metric, to said vehicle and to a corner of the frame representing said external object.

10. Device for estimating a distance between a motor vehicle (4, 24) and an external object (8), the motor vehicle (4, 24) being equipped with at least one camera (26) configured to capture digital images in a capture field outside the motor vehicle, the vehicle (4, 24) comprising an on-board computing device (22) adapted to process said captured digital images and calculate estimated characteristics of at least one external object located in said capture field, said estimated characteristics comprising, for each external object, first information on the estimated position of said object in a coordinate system in which said motor vehicle (4, 24) is also positioned, the device comprising a processor (32) configured to implement: - for the or each external object, a module for providing said characteristics estimated from the digital images captured as input to a parameterized calculation engine, trained by machine learning in a prior learning phase, said calculation engine being configured to provide a second corrected position information for said external object, and - a module for estimating a distance between the motor vehicle and the external object as a function of a current position of the motor vehicle and said second corrected position information, values of the parameters of said calculation engine being obtained by implementing, in the preliminary learning phase, machine learning of the values of the parameters of said calculation engine taking into account, for each external object, the estimated characteristics of said external object from the captured digital images and reference points obtained by at least one remote sensing sensor.

11. Motor vehicle equipped with at least one camera (26) configured to capture digital images in a capture field outside the motor vehicle, the vehicle (4, 24) comprising an on-board computing device (22) adapted to process said captured digital images and calculate estimated characteristics of at least one external object located in said capture field, said estimated characteristics comprising, for each external object, a first item of information on the estimated position of said object in a coordinate system in which said motor vehicle (4, 24) is also positioned, and comprising a device for estimating a distance between said motor vehicle (4, 24) and an external object (8) according to claim 10.

12. A computer program comprising software instructions which, when executed by a programmable electronic device, implement a method for estimating a distance between a motor vehicle and an external object according to claims 1 to 9.

Images