FR3032930A1 - METHOD AND DEVICE FOR AIDING THE DRIVING OF A MOTOR VEHICLE - Google Patents

Abstract

The invention relates to a method of assisting the driving of a motor vehicle subject to climatic conditions comprising static conditions associated with the vehicle and dynamic conditions associated with the environment of the vehicle. The method comprises acquiring (EO) at least one image by a camera, computing (E1) at least one fuzziness level of at least one group of pixels of said image, determining (E2) d at least one value of at least one parameter of said group of pixels relating to the dynamic climatic conditions, the comparison (E3a, E3b, E3c) between said fuzziness level and said parameter value, the determination (E4) of the static nature or dynamic climatic conditions from said comparison to assist the driver in his driving.

Description

The present invention relates to the field of the automobile and relates more particularly to a method and a device for assisting the driving of a motor vehicle, and a motor vehicle comprising such a device. Nowadays, it is known to equip a motor vehicle with a driver assistance system 5 commonly called ADAS (Advanced Driver Assistance System in English). Such a system comprises in known manner a camera, mounted on the windshield of the vehicle, which generates a stream of images representing the environment of said vehicle. These images are used by a system processing unit to assist the driver, for example by detecting an obstacle 10 or crossing a white line. The information given by the images captured by the camera must be sufficiently reliable and relevant to enable the system to effectively assist the driver of the vehicle. However, certain weather conditions can degrade the visibility and therefore the quality of the images captured by the camera. By way of example, a low external temperature combined with the lack of air circulation in the vehicle can generate condensation on the camera sensor and / or the vehicle windshield, which degrades the quality of the vehicles. images. Likewise, fog, ice, snow, rain or light rays can degrade the quality of the images captured by the camera. The lack of visibility caused by some of these weather conditions can be improved by activating certain functions of the vehicle such as, for example, wipers or heating of the vehicle interior. Today, the analysis of these conditions and the activation of the appropriate functions of the vehicle must be carried out by the driver while he is driving the vehicle. However, such maneuvers can be dangerous and compromise the safety of the vehicle. In addition, the driver does not always know the optimum function to be activated according to the climatic conditions, his field of vision being reduced. Existing solutions detect the presence of fog, rain, glare or condensation from images captured by the camera of the vehicle. However, each of these methods does not necessarily make it possible to differentiate between the different climatic conditions, and especially between the static climatic conditions, such as condensation or snow present on the windshield of the vehicle, for which it is recommended to activate the heating in the vehicle, and the dynamic climatic conditions of the vehicle environment such as rain, sun or fog for which it is not necessary to activate the heating in the vehicle. The aim of the present invention is to overcome at least part of these disadvantages by making it possible to distinguish static climatic conditions from dynamic climatic conditions in a simple, reliable and efficient manner, in particular in order to activate an adequate function of the vehicle.

For this purpose, the subject of the invention is a method for assisting the driving of a motor vehicle subjected to climatic conditions, said climatic conditions comprising static conditions associated with the vehicle and dynamic conditions associated with the vehicle environment. , the vehicle comprising a windshield on which a camera is mounted, said method being remarkable in that it comprises the steps of: - acquisition of at least one image by the camera, - calculation of at least one level of blur of at least one group of pixels of said image, - determination of at least one value of at least one parameter of said group of pixels relating to the dynamic climatic conditions, - comparison between said level of blur and said parameter value, - determining the static or dynamic nature of the climatic conditions from said comparison in order to assist the driver in his driving.

The term "static conditions associated with the vehicle" means climatic conditions generating the persistent presence of material on a part of the vehicle such as, for example, condensation on the sensor of the camera or on the windshield of the vehicle , snow on the windshield, etc. for which it is recommended to activate the heating in the vehicle, and dynamic conditions associated with the vehicle environment such as rain, sun or fog for which it is not necessary to activate the heating in the vehicle. vehicle. The determination of the static or dynamic nature of the climatic conditions makes it possible in particular to detect an anomaly and to assist in the diagnosis of said anomaly, for example when the assistance functions of the ADAS system are regularly unavailable for a given vehicle. Preferably, the method comprises a step of activating at least one function of the vehicle according to the static or dynamic nature of the climatic conditions determined. Such an activation may correspond to setting up a different activation strategy of a vehicle function depending on the static or dynamic nature. More preferably, the activation of a function of the vehicle corresponds to the activation of the heating when the climatic conditions are static in nature and to the sending of an information message to the driver when the climatic conditions are of dynamic nature. According to one aspect of the invention, the parameter of the image relating to the dynamic climatic conditions is the variation of the level of blur in a series of consecutive images captured by the camera. Thus, when the level of blur varies, for example by more than 15%, on the series of consecutive images then the climatic conditions are of a dynamic nature and correspond in particular to rain or hail. According to another aspect of the invention, the parameter of the image relating to the dynamic climatic conditions is the variation of the level of blur with the distance of the objects represented in the image. Thus, when the blur level varies exponentially with the distance on the image then the climatic conditions are dynamic in nature and correspond in particular to fog. According to another aspect of the invention, the parameter of the image relating to the dynamic climatic conditions is the variation of the level of blur with the intensity of the pixels of the group of pixels. Thus, when the level of blur increases with the intensity of the pixels of the group then the climatic conditions are dynamic in nature and correspond to glare caused by light rays. The invention also relates to a device for assisting the driving of a motor vehicle subjected to climatic conditions, said climatic conditions comprising static conditions associated with the vehicle and dynamic conditions associated with the environment of the vehicle, said device being remarkable in that it comprises: a camera, mounted on the windshield of the vehicle, configured to acquire a plurality of images, a calculation unit of at least one level of blur of at least one group; pixels of said image, - a first unit for determining at least one value of at least one parameter of said group of pixels relating to dynamic climatic conditions, - a comparison unit between said level of blur and said parameter value, a second unit for determining the static or dynamic nature of the climatic conditions from said comparison in order to assist the driver in his driving in depending on the static or dynamic nature of the climatic conditions determined.

Preferably, the device further comprises a unit for activating at least one function of the vehicle according to the determined static or dynamic nature of the climatic conditions. The invention also relates to a vehicle comprising a device as previously described. Other features and advantages of the invention will become apparent from the following description given with reference to the appended figures given as non-limiting examples and in which identical references are given to similar objects: FIG. an embodiment of the device according to the invention. FIG. 2 illustrates a mode of implementation of the method according to the invention. The device according to the invention is intended to be mounted in a motor vehicle to assist the driver of said vehicle in its driving. As is known, the vehicle is subjected to climatic conditions which are both static and dynamic. The static conditions are associated with the vehicle and generate the persistent presence of material on a part of the vehicle such as, for example, condensation on the sensor of the camera or on the windshield of the vehicle, snow on the screen. Such static conditions preferentially require the heating of the vehicle to be used to evacuate the condensation or to melt the snow. Dynamic conditions are associated with the vehicle environment and may, for example, be rain, sun or fog. In contrast to static conditions, these dynamic conditions do not require activation of the vehicle heater. With reference to FIG. 1, the device 1 comprises a camera 10, a calculation unit 20, a first determination unit 30, a comparison unit 40, a second determination unit 50 and an activation unit 60. camera 10 is mounted at the top of the windshield of the vehicle and is configured to acquire a plurality of images representing the environment of the vehicle.

The computing unit 20 is configured to calculate at least one fuzziness level of at least one pixel group of an image acquired by the camera 10. The first determining unit 30 is configured to determine at least one f-value. at least one parameter of a group of pixels of an image acquired by the camera 10, said parameter being relative to dynamic climatic conditions.

The comparison unit 40 is configured to compare a fuzziness level calculated by the computing unit 20 with a parameter value determined by the first determining unit 30.

The second determining unit 50 is configured to determine the static or dynamic nature of the climatic conditions from a comparison made by the comparison unit 40. Finally, the activation unit 60 is configured to activate a function. of the vehicle in order to assist the driver in his driving according to the static or dynamic nature of the climatic conditions determined, for example to activate the heating of the vehicle, send a message to the driver or store a message for a subsequent diagnosis of maintenance. The invention will now be described in its implementation.

In a step E0, the camera 10 acquires one or more images of the environment of the vehicle. Each image is divided into a plurality of equal portions, for example 5 x 5 rectangular portions. Each image portion is divided into a plurality of pixel portions, for example groups of 16 x 16 pixels. Then, the calculation unit 20 calculates, in a step E1, at least one level of blur for each group of pixels of each portion of each image acquired by the camera 10. In a preferred embodiment, three parameters Dynamic weather conditions are determined in a step E2 to be used: the time, the distance of the objects in an image and the intensity of the pixels of an image. With regard to the time parameter, the variation of the level of blur in a series of consecutive images captured by the camera is analyzed in a step E3a. One way of determining the level of blur is to estimate a blocking probability for each group of pixels of each portion of an image acquired by the camera 10. Thus, for example, for each 16 x 16 pixel group, can determine a Haar transform contour, for example by applying three filters of three different resolutions, and then deduce a classification of the contour on the group of 30 pixels (for example, a Dirac). A contour corresponds to a notable difference in level of blur between pixels of the same portion of the image. Then, according to the distribution of the classified contours, we deduce a blocking probability of said group of pixels. An example of a Haar transform and classification is given in the document "Blur detection for digital images using wavelet transform. (Hanghang Tong, Mingjing Li, Hongjiang Zhang, Changshui Zhang, IEEE International Conference on Multimedia, June 2004) incorporated herein by reference.

3032930 6 When the level of blur does not vary or varies little, for example less than 15%, on the series of consecutive images then the climatic conditions are determined, in a step E4, as being static in nature and may for example correspond to condensation on the camera or the windshield or snow on the windshield. In this case, the heating of the vehicle can be activated in a step E5a. When the level of blur varies, for example by more than 15%, and / or the average blur level is greater than 50% on the series of consecutive images, then the climatic conditions are determined, in a step E4, as being of a dynamic nature and correspond in particular to rain or hail. In this case, an information message may be sent to the driver in a step E5b. With regard to the distance parameter, the variation of the level of blur with the distance of the objects represented in the image is analyzed in a step E3b. One way to determine the variation of the blur level with the distance is to estimate the contrast which changes inversely proportional to the level of blur for each group of pixels, for example 12 x 12 pixels, of each portion of a pixel. image acquired by the camera 10. By way of example, it is possible to establish the ratio between the maximum difference between two adjacent pixels (in line or in column) and the difference between the maximum intensity and the minimum intensity. Thus, for example, when the level of blur increases with the distance in the image then the climatic conditions are determined, in a step E4, as dynamic in nature and correspond in particular to fog. In this case, an information message may be sent to the driver in a step E5b. With regard to the intensity parameter, the variation of the level of blur with the intensity of the pixels of each group of pixels of an image is analyzed in a step E3c. As explained above, one way to determine the level of blur is to estimate a blocking probability, for example as described above for each group of pixels, for example 5 x 5 pixels, of each portion of an image acquired by the camera 10.

The pixel cluster intensity estimate can be made by averaging for each portion of each 16 x 6 block that is not considered as edges. Thus, when the level of blur increases with the intensity of the pixels of the group then the climatic conditions are determined, in a step E4, as being dynamic nature and correspond to glare caused by light rays. In this case, an information message may be sent to the driver in a step E5b.

It will be noted that it is not necessary to activate a function of the vehicle when the climatic conditions are dynamic in nature, the sending of a message being optional but preferential. The method according to the invention advantageously enables the driver to be assisted in his driving by quickly and reliably determining the nature of the climatic conditions associated with the vehicle and its environment. A determination can be used, for example, to activate one or more functions of the vehicle or to perform a diagnosis relating to an anomaly. Finally, it should be noted that the present invention is not limited to the examples described above and is capable of numerous variants accessible to those skilled in the art.

Claims (9)

REVENDICATIONS1. A method of assisting driving of a motor vehicle subject to climatic conditions, said climatic conditions comprising static conditions associated with the vehicle and dynamic conditions associated with the environment of the vehicle, the vehicle comprising a windshield on which is mounted on a camera, said method being characterized in that it comprises the steps of: - acquiring (E0) at least one image by the camera, - calculating (El) at least one level of blur. at least one group of pixels of said image, of determining (E2) at least one value of at least one parameter of said group of pixels relative to the dynamic climatic conditions, of comparison (E3a, E3b, E3c) between said blur level and said parameter value, - determining (E4) the static or dynamic nature of the climatic conditions from said comparison in order to assist the driver in his driving. 2. Method according to claim 1, characterized in that it comprises the activation (E5a, E5b) of at least one function of the vehicle according to the static or dynamic nature of the climatic conditions determined. 3. Method according to claim 2, characterized in that the activation of a function of the vehicle corresponds to the activation of the heating (E5a) when the climatic conditions are of a static nature and to the sending of a message. information to the driver (E5b) when the weather conditions are dynamic in nature. 4. A method according to any one of claims 1 to 3, characterized in that the parameter of the image relating to the dynamic climatic conditions is the variation of the level of blur in a series of consecutive images captured by the camera (10). ). 5. Method according to any one of claims 1 to 3, characterized in that the parameter of the image relating to the dynamic climatic conditions is the variation of the level of blur with the distance of the objects represented in the image. 6. A method according to any one of claims 1 to 3, characterized in that the parameter of the image relating to the dynamic climatic conditions is the variation of the level of blur with the intensity of the pixels of the group of pixels. 3032930 9 7. Device (1) for assisting the driving of a motor vehicle subjected to climatic conditions, said climatic conditions comprising static conditions associated with the vehicle and dynamic conditions associated with the environment of the vehicle, said device being characterized by what it includes: - a camera (10), mounted on the windshield of the vehicle, configured to acquire a plurality of images, - a unit (20) for calculating at least one level of blur of at least one group of pixels of said image, - a first unit (30) for determining at least one value of at least one parameter of said group of pixels relating to dynamic climatic conditions, - a unit (40) for comparison between said level of blur and said parameter value, - a second unit (50) for determining the static or dynamic nature of the climatic conditions from said comparison in order to assist the driver in his driving. 8. Device (1) according to the preceding claim, characterized in that it further comprises a unit (60) for activating at least one function of the vehicle according to the static or dynamic nature of the climatic conditions determined. 9. Vehicle comprising a device (1) according to one of claims 7 or 8.