JP2021180487A - Operation status monitoring/warning system - Google Patents

Abstract

To provide an operation status monitoring/warning system.SOLUTION: An operation status monitoring/warning system includes: a camera that is installed on one side of a vehicle body and is used to take an image of the surrounding including a visual blind area at the time of driving of the vehicle body and a part of the vehicle body on the one side of the vehicle body; an infrared light source that is installed on the one side of the vehicle body and is used to selectively emit infrared rays to compensate the surrounding image for light, and that does not irradiate the vehicle body with the infrared rays; and a processing module that is electrically connected to the camera to perform image processing on the surrounding image and marks at least one risk object in the surrounding image.SELECTED DRAWING: Figure 1

Description

The present disclosure relates to a driving condition monitoring / warning system, and particularly to a driving condition monitoring / warning system capable of issuing a warning when there is a risk object in a visual blind area during driving.

Blind Spot Detection (BSD) devices are typically mounted on the brackets of the wing mirrors on either side of the vehicle and are moving objects behind the vehicle due to images taken backwards by the Blind Spot Detection camera. Give the driver help to let them know if there is. However, current blind area detectors can only detect vehicles coming from behind and cannot detect moving objects in front of the rearview mirror.

An object of the present disclosure is a camera provided on one side of the vehicle body and used to take an image of the surroundings of the one side of the vehicle body including a visual blind area when the vehicle body is driven and a part of the vehicle body. An infrared light source that is installed on the one side of the vehicle body and is used to selectively emit infrared rays to compensate for the surrounding image, and the infrared light source does not irradiate the vehicle body, and image processing for the surrounding image. It is to provide a driving situation monitoring / warning system equipped with a processing module that is electrically connected to a camera to mark at least one risk object in the surrounding image.

In some embodiments, the camera is a wide-angle camera.

In some embodiments, the assembly position of the camera and the infrared light source is lower than the ceiling of the vehicle body and higher than the vehicle window of the vehicle body.

In some embodiments, the infrared light source is rotatable and its depression angle varies with its mounting height.

In some embodiments, the field of view (FOV) of the infrared light source is between 120 and 160 degrees.

In some embodiments, the surrounding image includes an image of the one side of the front edge of the vehicle body.

In some embodiments, the surrounding image comprises the one-sided image beyond the front edge of the vehicle body.

In some embodiments, the processing module further marks the degree of risk of the risk object in the surrounding image by the distance between the risk object and the vehicle body.

In some embodiments, the processing module identifies whether a risk object belongs to a vehicle or a vulnerable road user by a machine learning method.

In some embodiments, the processing module further marks the degree of risk of the risk object in the surrounding image by the distance between the risk object and the vehicle body and whether the risk object belongs to a vehicle or vulnerable road user.

In order to make the above-mentioned features and merits of the present invention easier to understand, examples will be given below, and the following will be described in detail together with the accompanying drawings.

Hereinafter, the aspects of the present disclosure can be better understood by referring to the accompanying drawings in detail. It should be noted that according to industry standard practice, each feature is not drawn to a certain scale. In essence, the size of each feature can be optionally scaled up or down to make the study clearer.
It is a block diagram which shows the operation condition monitoring / warning system by the Example of this disclosure. It is a front schematic diagram which shows the image | imaging range of the camera of the operation condition monitoring / warning system according to the embodiment of this disclosure. FIG. 3 is a schematic top view showing a shooting range of a camera of an operating condition monitoring / warning system according to an embodiment of the present disclosure. It is an exemplary schematic diagram which shows the degree of risk of a risk object by the Example of this disclosure.

Hereinafter, examples of the present invention will be examined in detail. However, it should be understood that the examples provide many applicable concepts that can be implemented with a variety of specific content. The examples considered and disclosed are not intended to limit the scope of the invention, but merely to explain.

FIG. 1 is a block diagram showing an operation status monitoring / warning system 100 according to an embodiment of the present disclosure. The operation status monitoring / warning system 100 includes a camera 110, an infrared light source 120, and a processing module 130.

In the embodiment shown in FIG. 1, the driving condition monitoring / warning system 100 is provided on the right side of the vehicle body 200. However, it is only an example, and substantially, the driving condition monitoring / warning system 100 is provided on both sides of the vehicle body 200 and contributes to monitoring whether or not there are moving objects on both sides of the vehicle body 200. The camera 110 of the driving situation monitoring / warning system 100 is used to take an image of the surroundings on both sides of the vehicle body 200.

In the embodiments of the present disclosure, the processing module 130 is electrically connected to the camera 110 and the infrared light source 120. The processing module 130 controls the infrared light source 120 so as to selectively emit infrared rays to perform light compensation for the surrounding image taken by the camera 110.

As an example, the processing module 130 emits infrared light when it senses that the light rays of a scene taken by the camera 110 are below a certain value (eg, due to a photosensitive element), for example at night or when the light rays are inadequate. Then, the infrared light source 120 can be controlled so as to perform light compensation for the scene taken by the camera 110.

In the embodiments of the present disclosure, the field of view (FOV) of the infrared light source 120 is between 120 and 160 degrees. In the embodiments of the present disclosure, the infrared light source 120 is rotatable, in other words, is provided on the rotation mechanism component so that the depression angle of the infrared light source 120 can be adjusted.

In the embodiment of the present disclosure, the depression angle of the infrared light source 120 varies depending on the mounting height of the infrared light source 120, and further, if the mounting height of the infrared light source 120 is low, the depression angle of the infrared light source 120 is accompanied by it. The smaller and the higher the mounting height of the infrared light source 120, the larger the depression angle of the infrared light source 120. As an example, if the mounting height of the infrared light source 120 is about 250 cm, the depression angle of the infrared light source 120 is about 20 to 30 degrees, and if the mounting height of the infrared light source 120 is about 350 cm, the depression angle of the infrared light source 120 is about 20 to 30 degrees. It will be about 50 to 60 degrees.

In the embodiment of the present disclosure, as shown in FIG. 1, the mounting height of the driving condition monitoring / warning system 100 is lower than the ceiling of the vehicle of the vehicle body 200 and higher than the vehicle window of the vehicle body 200. In the embodiment of the present disclosure, as shown in FIG. 1, the shooting viewing angle of the camera 110 is not the same as the irradiation direction of the infrared light source 120.

In the embodiments of the present disclosure, the shooting viewing angle of the camera 110 may be taken downward, but the present disclosure is not limited to this. The shooting viewing angle of the camera 110 may be taken diagonally downward and backward. In the embodiment of the present disclosure, the irradiation direction of the infrared light source 120 may irradiate backward, but the present disclosure is not limited to this. The irradiation direction of the infrared light source 120 may be taken diagonally backward and downward. However, the shooting viewing angle of the camera 110 and the irradiation direction of the infrared light source 120 are not the same no matter how they are adjusted.

In the embodiment of the present disclosure, since the camera 110 is a wide-angle camera, it has a wide horizontal viewing angle and vertical viewing angle, and captures not only a part of the vehicle body 200 but also moving objects on both sides of the vehicle body 200 as much as possible. be able to. In other words, the surrounding image taken by the camera 110 includes a part of the vehicle body 200.

In the embodiment of the present disclosure, the infrared light source 120 is the vehicle body 200 so as to prevent the surrounding image taken by the camera 110 from being reflected by the infrared light source 120 irradiated to the vehicle body 200 and making subsequent image recognition difficult. Do not irradiate.

As an example, when the infrared light source 120 irradiating the vehicle body 200 reflects light on a part of the vehicle body 200 included in the surrounding image taken by the camera 110, the following may occur. (1) If the dynamic range of the camera 110 is not sufficiently high, the surrounding image is exposed as a whole, and the features in the surrounding image are insufficient and cannot be identified. (2) When the dynamic range of the camera 110 is sufficiently high, the portion where the light is reflected lowers the overall illuminance of the surrounding image, and the features in the surrounding image become insufficient and cannot be identified. (3) The reflected light emitted from the infrared light source 120 to the vehicle body enters the lens of the camera 110 due to refraction and / or reflection and causes scattering, resulting in insufficient features in the surrounding image and making it impossible to identify.

FIG. 2a is a front schematic view showing a shooting range of the camera 110 of the operating condition monitoring / warning system 100 according to the embodiment of the present disclosure. FIG. 2b is a schematic top view showing a shooting range of the camera 110 of the operating condition monitoring / warning system 100 according to the embodiment of the present disclosure.

As shown in FIGS. 2a and 2b, the surrounding image taken by the camera 110 includes at least the images on both sides in front of the wing mirror 210 of the vehicle body 200. In the embodiments of the present disclosure, the surrounding image taken by the camera 110 includes a visual blind area when driving in front of the wing mirror 210 of the vehicle body 200. It should be noted that the conventional blind spot detection device cannot capture the images on both sides in front of the wing mirror 210 because the conventional blind spot detection device shoots the rear by the cameras provided on the brackets of the wing mirrors on both sides of the vehicle.

As shown in FIGS. 2a and 2b, the surrounding image taken by the camera 110 includes at least the images of both the front and rear edges of the vehicle body 200, and more specifically, the surrounding image taken by the camera 110. Includes images on both sides beyond the front and rear edges of the vehicle body 200. It should be noted that the conventional blind spot detection device cannot capture the images on both sides of the front edge of the vehicle body 200 because the conventional blind spot detection device captures the rear by the cameras provided on the brackets of the wing mirrors on both sides of the vehicle.

In the embodiment of the present disclosure, the processing module 130 receives the surrounding image taken by the camera 110, performs image processing on the surrounding image, and performs image processing on the surrounding image, and the risk moving object (risk object in the text) in the surrounding image. Identifies if there is at least one risk object in the surrounding video. As an example, in the embodiments shown in FIGS. 2a and 2b, the processing module 130 is a risk object of the bicycle 300 located in the visual blind area when driving in front of the wing mirror 210 on the right side of the vehicle body 200 in the surrounding image. When it is identified, the bicycle 300 is marked as a risk object (and thus a warning is issued) in the surrounding image, and the driver is careful not to hit the bicycle 300 when the vehicle body turns to the right.

In the embodiments of the present disclosure, the processing module 130 identifies whether the risk object belongs to a vehicle or a vehicle road user by a machine learning method, where the vehicle is a small vehicle (eg, an automobile). Includes heavy vehicles (eg trucks) and vulnerable road users include pedestrians, bicycles and motorcycles. In the embodiments of the present disclosure, the processing module 130 trains pedestrians, bicycles, motorcycles, small vehicles, and large vehicles by deep learning so that the risk objects in the surrounding images belong to the vehicle or fragile road user. Can be identified. As an example, in the embodiment shown in FIGS. 2a and 2b, the processing module 130 identifies the bicycle 300 belonging to the vulnerable road user in the surrounding image. In addition, since objects such as road trees, road construction equipment (for example, triangular cones, etc.), post boxes, street lights, trash cans, etc. are not subject to machine learning training of the processing module 130, the processing module 130 does not define them. It is considered an object (ie, a non-risk object) and is neither identified nor marked.

In the embodiments of the present disclosure, the processing module 130 identifies that the risk object belongs to a vehicle or fragile road user, and then further distances the risk object from the vehicle body 200 and / or the risk object is a vehicle or fragile road user. Depending on whether it belongs to the above, not only the risk object but also the risk degree of the risk object is marked in the surrounding image, and the driver is careful not to hit the risk object when the vehicle body turns.

FIG. 3 is an exemplary schematic diagram showing the degree of risk of a risk object according to the embodiment of the present disclosure. In the embodiment shown in FIG. 3, if the distance between the risk object and the vehicle body 200 is short, the degree of risk is high, and the degree of risk is high risk, medium risk, and low risk, respectively, in descending order. In the embodiment shown in FIG. 3, when the risk object belongs to the vehicle, the degree of risk is not severe, and when the risk object belongs to the vulnerable road user, the degree of risk is severe. As an example, in the embodiment shown in FIG. 3, when the distance to the vehicle body 200 is the same, if the risk object belongs to the vehicle 400, the degree of risk is considered to be medium risk, but the risk object is a vulnerable road user (bicycle). If it belongs to 300), the degree of risk is considered to be high risk.

In the embodiment of the present disclosure, the risk object is surrounded by a square frame in the surrounding image, and the degree of risk of the risk object is displayed by different frame line colors. As an example, a red frameline can display a high-risk risk object, a yellow frameline can display a medium-risk risk object, and a gray frameline can display a low-risk risk object.

In short, the present disclosure detects a risk object in front of the wing mirror of the vehicle body so that the risk object does not hit the risk object when the vehicle body bends when the risk object is in the visual blind area during driving. Issue a warning and submit a driving status monitoring / warning system that pays attention to the driver.

Having described the features of the plurality of examples above, those skilled in the art can better understand the aspects of the present disclosure. One of ordinary skill in the art should understand that this disclosure can be used as a basis for easily designing or modifying other processes and structures, thereby achieving the same goals and / or the same advantages as those described herein. be. It will also be appreciated by those skilled in the art that these equivalent structures do not deviate from the spirit and scope of the present disclosure and may make various modifications, substitutions and modifications without departing from the spirit and scope of the present disclosure. ..

100: Driving status monitoring / warning system 110: Camera 120: Infrared light source 130: Processing module 200: Body 210: Wing mirror 300: Bicycle 400: Vehicle

Claims (10)

A camera provided on one side of the vehicle body and used to capture an image of the surroundings of the one side of the vehicle body including a visual blind area when the vehicle body is driven and a part of the vehicle body.
An infrared light source provided on the one side of the vehicle body, which is used to selectively emit infrared rays to perform light compensation for the surrounding image, and the infrared rays do not irradiate the vehicle body.
A processing module that is electrically connected to the camera to perform image processing on the surrounding image and marks at least one risk object in the surrounding image.
Operation status monitoring / warning system equipped with. The operating condition monitoring / warning system according to claim 1, wherein the camera is a wide-angle camera. The driving condition monitoring / warning system according to claim 1, wherein the mounting height of the camera and the infrared light source is lower than the ceiling of the vehicle of the vehicle body and higher than the vehicle window of the vehicle body. The operating condition monitoring / warning system according to claim 1, wherein the infrared light source is convertible and its depression angle changes depending on the mounting height thereof. The operating condition monitoring / warning system according to claim 1, wherein the horizontal field of view (FOV) of the infrared light source is between 120 degrees and 160 degrees. The driving condition monitoring / warning system according to claim 1, wherein the surrounding image includes an image of the one side of the frontmost edge of the vehicle body. The driving condition monitoring / warning system according to claim 1, wherein the surrounding image includes an image of the one side exceeding the front edge of the vehicle body. The driving condition monitoring / warning system according to claim 1, wherein the processing module marks the degree of risk of the risk object in the surrounding image by the distance between the risk object and the vehicle body. The driving condition monitoring / warning system according to claim 1, wherein the processing module further identifies whether the risk object belongs to a vehicle or a vulnerable road user by a machine learning method. A claim that the processing module further marks the degree of risk of the risk object in the surrounding image depending on the distance between the risk object and the vehicle body and whether the risk object belongs to a vehicle or a fragile road user. The operating condition monitoring / warning system according to 8.

Images