TWM622061U - Driving monitoring and warning system for vehicle - Google Patents

Abstract

A driving monitoring and warning system for a vehicle is disclosed. The driving monitoring and warning system includes: a first camera, installed at one side of the vehicle, for capturing a first successive image, the first successive image includes a first side view of the vehicle and a front view of the vehicle; a second camera, installed at the same side of the vehicle as that of the first camera, for capturing a second successive image, the second successive image includes a second side view of the vehicle and a rear view of the vehicle, wherein the first side view of the vehicle partially overlaps the second side view of the vehicle; and a processing device, for analyzing the first successive image and the second successive image to define a monitoring region; determining whether an identified target is within the monitoring region; and generating a warning signal while the identified target is confirmed within the monitoring region.

Description

Video surveillance and warning system for vehicles

The invention relates to the technical field of driving image recognition, in particular to a vehicle image monitoring and warning system.

Today's common blind spot detection (BSD) devices are mainly based on radar detection technology, with indicator lights in the car. When there is an object within the radar detection range, the indicator light will light up to remind the driver, but The number of the object and the relative distance from the vehicle cannot be judged. Or, the blind spot detection device has a single camera installed on the rearview mirror of the vehicle, but mainly only shoots the side of the vehicle and a short distance near the rear of the vehicle.

The purpose of this creation is to provide an image monitoring and warning system for a vehicle, including: a first camera installed on at least one side of a vehicle for capturing a first continuous image, where the first continuous image includes a first vehicle side view angle and the front view angle of the vehicle; the second camera is installed on the same side of the vehicle as the first camera, and is used to collect a second continuous image, the second continuous image includes a second vehicle side view angle and a vehicle rear view angle, wherein the The first vehicle side angle of view and the second vehicle side angle of view are partially overlapped; and a processing unit is used to analyze the first continuous image and the second continuous image to define a monitoring area; determine whether the monitoring area includes Identifying the target; when it is confirmed that the identifying target is included, a warning signal is generated.

According to the inventive concept, the warning signal is at least one of an optical signal, a sound signal, and a vibration signal.

According to this creative concept, the installation height of the first camera is at least 2 meters above the ground. According to the creative concept, the installation height of the first camera is at least 1.25 times the height of the upper edge of the rearview mirror of the vehicle from the ground.

According to the creative concept, the distance between the first camera and the rearview mirror of the vehicle in a direction parallel to the ground is at least 170 cm.

According to the inventive concept, the included angle between the optical axis of the first camera and the side of the vehicle in a direction parallel to the ground is between 95 degrees and 115 degrees.

According to the creative concept, the included angle between the optical axis of the second camera and the side of the vehicle in a direction parallel to the ground is between 20 degrees and 40 degrees.

According to the creative concept, the aspect ratio of the first continuous image is 4:3, and the aspect ratio of the second continuous image is 16:9.

According to the inventive concept, the processing unit continues to issue the warning signal until the identification target is not included in the monitoring area.

This creation has the following advantages: 1. By setting up two cameras with different fields of view and different shooting directions, objects close to the vehicle can be effectively monitored, especially in addition to the range of the side of the vehicle that can be collected, it can also include the front and rear of the vehicle. 2. The artificial intelligence with identifiable images generates a warning signal with a risk level for the identification target close to the vehicle by dividing the monitoring area, so as to reduce the collision of surrounding objects when driving and manipulating the vehicle.

In order to make the purpose, technical solutions and advantages of this creative embodiment clearer, the technical solutions in this creative embodiment will be clearly and completely described below in conjunction with the accompanying drawings in this creative embodiment. Obviously, the described embodiment It is a part of the embodiments of the present creation, but not all of the embodiments. Based on the embodiments in this creation, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of this creation. Accordingly, the following detailed description of the embodiments of the present creations provided in the accompanying drawings are not intended to limit the scope of the claimed inventions, but are merely representative of selected embodiments of the present creations. Based on the embodiments in this creation, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of this creation.

In the description of the present creation, it should be understood that the orientations or positional relationships indicated by the terms "upper", "lower", "left", "right", "inner", "outer", etc. are based on those shown in the accompanying drawings. The orientation or positional relationship is only for the convenience of describing the present creation and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operate in a particular orientation, and therefore should not be construed as a limitation on the present creation.

In the description of the present creation, "plurality" means two or more, unless otherwise expressly and specifically defined.

In this creation, unless otherwise expressly specified and limited, the terms "installation", "connection", "connection", "fixation" and other terms should be understood in a broad sense, for example, it may be a fixed connection or a detachable connection , or integrated; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal connection of the two elements or the interaction relationship between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present creation can be understood according to specific situations.

This creation is described in further detail below in conjunction with the accompanying drawings and specific embodiments:

Please refer to FIG. 1 , the present invention discloses a vehicle image monitoring and warning system 100 including a first camera 101 , a second camera 102 , an image signal receiving module 103 , a processing unit 104 and a warning signal transmission interface 105 .

The first camera 101 and the second camera 102 of the system 100 are mounted on a vehicle, generally on the outside of the vehicle, and their main function is to capture images around the vehicle. Field of View (FOV), that is, including a wider horizontal field of view (Horizontal Field Of View, HFOV) and vertical field of view (Vertical Field Of View, VFOV). In addition to its basic circuit power supply and signal transmission interface, it can also include an Image Signal Processor (ISP) to process image signals, including demosaicing, noise reduction, white balance, exposure correction, sharpening , color conversion, color correction, gamma correction, color space conversion, edge enhancement processing, encoding and other functions. In order to obtain better image quality, these images can be LVDS format signals.

The image signal receiving module 103 is used for acquiring consecutive image frames, especially for acquiring consecutive image frames from the first camera 101 and the second camera 102 . In addition to the image processing function, the image signal receiving module 103 generally has an LVDS (Low Voltage Differential Signaling, low voltage differential signaling) or MIPI CSI transmission interface (not marked).

The processing unit 104 is the main operation unit of the creation, and has the ability of image semantic operation. Usually, the processor of the processing unit 104 is a DSP (digital signal processor). The processing unit 104 has a memory transmission interface and can execute instructions built into the memory. The processing unit 104 also has an image transmission interface (not shown), which is connected with the image signal receiving module 103 to calculate the image signal converted from the image signal receiving module 103 .

The warning signal transmission interface 105 is connected to the processing unit 104, and transmits the signal generated by the processing unit 104 to an external warning device (not shown) through the interface, especially the processing unit 104 generates the warning signal corresponding to the warning device. In addition, the alert signal transmission interface 105 can be used as an interface for general data signal transmission, such as transmitting image signals for display, etc. In addition, the alert signal transmission interface 105 can also be an Ethernet interface or an interface of other high-speed transmission forms.

Please refer to FIG. 2 and an embodiment of the present invention in which the image monitoring and warning system 100 of a vehicle is installed on the vehicle 200 . The first camera 101 and the second camera 102 can be installed in a casing 201 and installed on one side of the vehicle 200 (the right side of the vehicle 200 in the figure), which is relative to the driving position of the vehicle 200 (in the figure). is the opposite side of the left side of the vehicle 200 ), that is, by setting the first camera 101 and the second camera 102 , the image capture is performed for the blind spot on this side caused by the driving angle of view. The housing 201 of this embodiment mainly fixes the first camera 101 and the second camera 102 , and covers the wires or other fixing brackets connected to the first camera 101 and the second camera 102 , while the first camera 101 and the second camera 102 They can also be respectively fixed to the same side of the vehicle 200 , and it is not necessary to assemble through the casing 201 . However, the same multiple cameras as the first camera 101 and the second camera 102 can also be installed on the vehicle body on the same side as the vehicle driving (ie, the left side of the vehicle 200 in the figure) to monitor objects on the left and right sides of the vehicle 200 .

In order to allow the blind spot on the side of the vehicle to have a better image monitoring range, the first camera 101 is mainly set up to collect part of the image on the side of the vehicle and the front image of the vehicle. The two cameras 102 are used to capture another part of the side image and the rear image of the vehicle on the same side as the first camera 101 . The continuous images captured by the first camera 101 and the second camera 102 can cover the field of view of the side of the vehicle, especially the front and rear fields of view near the side of the vehicle 200 .

Please refer to Figure 3 to Figure 4 for the detailed setting method of the camera in this creation. The camera used in this embodiment has the following related setting parameters:

(1) The first camera 101 has an angle θH covered by the horizontal field of view (HFOV) ranging from 120 degrees to 140 degrees, and an angle θV covered by the vertical field of view (VFOV). Between 60 degrees and 80 degrees, the aspect ratio of the image sensing area is mainly 4:3. When the first camera 101 is disposed on the side of the vehicle, the angle θ1 between its optical axis OA1 and the side of the vehicle 200 parallel to the ground is between 95 degrees and 115 degrees, and the optical axis OA1 has a depression angle toward the ground. The range is between 30 degrees and 40 degrees. At the same time, the first camera 101 is centered on the optical axis OA1 and is rotated clockwise by an appropriate angle (between 25 degrees and 35 degrees in this embodiment). After the FOV) is set, the first camera 101 is used to capture a first continuous image, and the first continuous image includes a first vehicle side view angle and a vehicle front view angle.

(2) The second camera 102 has an angle θH covered by a horizontal field of view (HFOV) ranging from 90 degrees to 110 degrees, and an angle θV covered by a vertical field of view (VFOV) It is between 45 degrees and 65 degrees, and the aspect ratio of the image sensing area is mainly 16:9. When the second camera 102 is disposed on the side of the vehicle, the angle θ2 between its optical axis OA2 and the side of the vehicle 200 in the direction parallel to the ground is between 20 degrees and 40 degrees, and the depression angle toward the ground is between 50 degrees and 40 degrees. At the same time, the second camera 102 is rotated clockwise by an appropriate angle (between 75 degrees and 85 degrees in this embodiment) with the optical axis OA2 as the center. After the field of view (FOV) of the second camera 102 is set, it is used to capture a second continuous image, where the second continuous image includes a second vehicle side view angle and a vehicle rear view angle.

In this embodiment, the second camera 102 is disposed adjacent to the first camera 101 , the distance between the optical centers OC of the two cameras is not more than 10 cm, and the field of view of the second camera 102 is not blocked by the first camera 101 , In particular, when the first camera 101 is not blocked by the rearview mirror 202 of the vehicle, its installation height is at least 2 meters from the ground. Specifically, the distance between the optical center OC of the first camera 101 and the ground is 2 meters. meter. However, the first vehicle side angle of view and the second vehicle side angle of view partially overlap, which is the result of the specifications of the camera itself, and the image area covered by the overlapping angle of view can determine that this embodiment can cover all vehicles 200 on the same vehicle side. At the same time, the image area covered by the overlapping viewing angle can be used as the marking area for the first camera 101 and the second camera 102 in the image correction of the system 100 .

Referring to FIG. 5 and FIG. 6 at the same time, if the setting of the cameras in this embodiment is blocked by the vehicle rearview mirror 202 for the viewing area, especially the front viewing area of the first camera 101, these blocked viewing areas are If there is an object, it may cause the object not to be detected through the image. Therefore, without changing the setting parameters of the first camera 101 and the second camera 102 in this embodiment, in order to effectively achieve the image capture of the blind spot on the side of the vehicle, this embodiment has the following setting relationship: L: (SD+L)=(H-MH): H L : (SD+L)=(MW-W) : (SW-W) Wherein, L is the distance between the optical center OC of the first camera 101 and the geometric center of the vehicle rearview mirror 202 parallel to the forward direction of the vehicle 200 . SD is the distance between the projection of the shadowed field of view of the first camera 101 between the farthest end of the ground and the geometric center of the rearview mirror 202 of the vehicle, and the two are parallel to the forward direction of the vehicle 200 . H is the height of the optical center OC of the first camera 101 from the ground. MH is the height of the upper edge of the vehicle rearview mirror 202 from the ground. MW is the distance from the edge of the vehicle rearview mirror 202 to the side of the vehicle 200 in a direction perpendicular to the forward direction of the vehicle 200 and parallel to the ground. W is the distance from the optical center OC of the first camera 101 to the side of the vehicle 200 in a direction perpendicular to the forward direction of the vehicle 200 and parallel to the ground. SW is the farthest distance of the shadowed field of view of the first camera 101 projected on the ground at the farthest distance perpendicular to the forward direction of the vehicle 200 and parallel to the ground direction.

Therefore, through the above-mentioned relational expressions and considering the design parameters of the first camera 101 and the second camera 102 of the present embodiment, given W=0.1 (meter), MW=0.25 (meter), SW=0.9 (meter) feet), SD=7 (meters), the best result of this embodiment can be obtained: L≒1.7(meter); H≒1.25MH That is, the distance between the first camera 101 and the rearview mirror 202 of the vehicle in a direction parallel to the ground is at least 170 cm, and the installation height of the first camera 101 is at least 1.25 times the height of the upper edge of the rearview mirror 202 of the vehicle from the ground. . In this way, the occlusion of the front view field of the first camera 101 by the vehicle rearview mirror 202 can be reduced. Even if the camera in this embodiment is set in this way, the vehicle rearview mirror 202 still partially blocks the field of view, but small objects on the road, such as motorcycle riders, cyclists, pedestrians, etc. In the case of occlusion, images of other unoccluded fields of view can still be collected.

After the first camera 101 and the second camera 102 respectively capture the images including the first vehicle side view angle and the vehicle front view angle and the continuous images of the second vehicle side view angle and the vehicle rear view angle, the continuous images are sent to these continuous images through the image signal receiving module 103 The image is transmitted to the processing unit 104 . Since the distance of an object to be judged by image vision is limited by the resolution of the camera, internal and external parameters, etc., even if the objects around the vehicle 200 can be captured within the field of view of the camera, the effectiveness of image vision for object detection ( Including object type or object distance) will have a certain range of restrictions. Therefore, in the present invention, a monitoring area 300 is set around the vehicle 200 . The monitoring area 300 can be set by the user through a user interface, or the user can select the corresponding road traffic laws, standards, etc., or the range regulated by the preset road traffic standards. Generally speaking, the monitoring area 300 covers the side area of the vehicle 200 , the partial area in front of the vehicle 200 , and the partial image behind the vehicle 200 . By setting the cameras in this embodiment, the length DL of the monitoring area 300 can be equal to the length DL of the vehicle 200 . The distance between the frontmost edge extending 10 meters forward to the frontmost edge extending 30 meters rearward of the vehicle 200, and the width DW of the monitoring area 300 may be the distance that the side edge of the vehicle 200 extends outwards by 4.5 meters, such that The monitoring area 300 is an effective area that can be monitored by the first camera 101 and the second camera 102 in this embodiment. After the range of the monitoring area 300 is given, the processing unit 104 needs to calculate the coordinate range corresponding to the monitoring area 300 in the continuous images captured by the first camera 101 and the second camera 102 . Specifically, the processing unit 104 analyzes the first continuous image and the second continuous image to define the monitoring area 300 according to the first camera 101 and the second camera 102 set in the previous step S01 .

At the same time, since the processing unit 104 of the present invention has the ability of artificial intelligence to analyze semantics of images, it can identify whether there is an object close to the vehicle 200 in the traveling environment from the continuous images obtained when the vehicle 200 is moving. That is, the object is an identification target that can be identified. Recognition targets can include pedestrians, various vehicles, street signs, signs, telephone poles, lane lines, lane types, sidewalks, parking spaces, etc. The processing unit 104 of the present creation can also identify whether the recognition target can move or not. movement, as well as the distance relative to the host vehicle 200, the movement speed, and the like. In this embodiment, the identification target setting is mainly for pedestrians, cyclists, motorcycle riders, or road users who take other vehicles.

Once the recognition target appears within the field of view of the camera of the vehicle 200 , the processing unit 104 determines whether the monitoring area 300 contains the recognition target, and generates a trigger signal when it is confirmed that the recognition target is included. In detail, the trigger signal is generated by the processing unit 104 and stored in the dynamic memory (not marked) of the system 100 , and the trigger signal may include the relevant actions performed by the processing unit 104 on the system 100 , Such as counting, marking, storing and other signal processing of continuous images collected by the camera, or generating output signals, such as warning signals, indicating signals, etc., and even vehicle control signals, such as acceleration, deceleration, stop, steering, etc.

In this embodiment, the trigger signal is converted into a warning signal, that is, the processing unit 104 can generate a corresponding warning signal according to the trigger signal, which is generally an output electrical signal. The alarm signal converted and generated by the processing unit 104 is transmitted to an alarm device (not shown) through the alarm signal transmission interface 105 of the system 100 . The processing unit 104 continues to generate a warning signal until the monitoring area 300 does not contain any identification targets. Such a warning method is used to remind the driver to pay attention to the control of the vehicle, and it will not stop until the identification targets are far away from the monitoring area 300 close to the vehicle, thereby avoiding collisions. .

Common warning devices can be optical devices (warning lights, display screens), acoustic devices (horns) or vibration devices (vibration motors, piezoelectric oscillators), and these devices can be combined with the existing equipment on the vehicle or It is installed in the car in an external manner to achieve the effect of warning driving. Therefore, according to the form of different warning devices, the processing unit 104 generates a warning signal format that matches the warning device, that is, the warning signal is at least an optical signal, a sound One of signal and vibration signal. For example, when the system 100 detects that the position of an identification target (such as a cyclist) is in the monitoring area 300, it can enable an optical warning device (such as an indicator light installed in the car and close to the A-pillar) to turn on the warning (such as the light signal is turned on), to achieve the warning effect.

For users who use this system to monitor the blind spot caused by the driving angle of view, by setting up two cameras with different fields of view and different shooting directions, objects close to the vehicle can be effectively monitored, especially the range other than the side of the vehicle can be collected. In addition to the images, the front and rear view images of the vehicle can also be included. At the same time, this embodiment has artificial intelligence that can recognize images, and generates warning signals for specific recognition targets close to the vehicle, thereby reducing collisions with surrounding objects when driving and manipulating the vehicle.

The above is only a preferred embodiment of this creation, and does not limit this creation in any form. Although this creation has been disclosed as a preferred embodiment as above, it is not intended to limit this creation. Anyone familiar with this professional technology Personnel, without departing from the scope of the technical solution of this creation, can make some changes or modifications to equivalent examples of equivalent changes by using the methods and technical contents disclosed above, but any content that does not depart from the technical solution of this creation shall be The technical essence of the creation Any simple modifications, equivalent changes and modifications made to the above embodiments still fall within the scope of the technical solution of the creation.

100: Monitoring and warning systems for vehicles 101: The first camera 102: Second Camera 103: Video signal receiving module 104: Processing unit 105: Warning signal transmission interface 200: Vehicle 201: Shell 202: Vehicle rear view mirror 300: Surveillance area

1 is a schematic structural diagram of an image monitoring and warning system for a vehicle of the present invention; Fig. 2 is the camera installation schematic diagram of the image monitoring and warning system of a kind of vehicle of the present creation; FIG. 3 is a schematic diagram illustrating the field of view of a camera of a vehicle image monitoring and warning system of the present invention; 4 is a schematic top view of a camera field of view of a vehicle image monitoring and warning system of the present invention; 5 is a schematic diagram of a camera and a vehicle rearview mirror of a vehicle image monitoring and warning system of the present invention being installed in a vehicle; 6 is a schematic top view of a camera and a vehicle rearview mirror of a vehicle image monitoring and warning system of the present invention installed in a vehicle; FIG. 7 is a schematic diagram of a monitoring area of a vehicle image monitoring and warning system of the present invention.

100: Monitoring and warning systems for vehicles

101: The first camera

102: Second Camera

103: Video signal receiving module

104: Processing unit

105: Warning signal transmission interface

Claims (8)

An image monitoring and warning system for a vehicle, comprising: a first camera mounted on at least one side of a vehicle for collecting a first continuous image, the first continuous image including a first vehicle side view angle and a vehicle front view angle a second camera, mounted on the same side of the vehicle as the first camera, for capturing a second continuous image, the second continuous image including a second vehicle side view angle and a vehicle rear view angle, wherein the first vehicle side view The viewing angle partially overlaps with the second vehicle side viewing angle; an image signal receiving module is connected to the first camera and the second camera for acquiring the first continuous image from the first camera and the The second continuous image of the second camera; the processing unit, connected to the image signal receiving module, is used to analyze the first continuous image and the second continuous image to define a monitoring area; determine whether the monitoring area is It includes an identification target; when it is confirmed that the identification target is included, a warning signal is generated; and a warning signal transmission interface is connected with the processing unit to transmit the warning signal generated by the processing unit to an external warning device. The image monitoring and warning system for a vehicle as described in claim 1, wherein the warning signal is at least one of an optical signal, a sound signal, and a vibration signal. The image monitoring and warning system for a vehicle according to claim 1 of the scope of the application is characterized in that the installation height of the first camera is at least 2 meters above the ground. The image monitoring and warning system for a vehicle according to claim 1, wherein the installation height of the first camera is at least 1.25 times the height of the upper edge of the rearview mirror of the vehicle from the ground. The image monitoring and warning system for a vehicle according to claim 4 of the scope of the application is characterized in that the distance between the first camera and the rearview mirror of the vehicle in a direction parallel to the ground is at least 170 cm. The image monitoring and warning system for a vehicle according to claim 1, wherein the angle between the optical axis of the first camera and the side of the vehicle in a direction parallel to the ground is between 95 degrees and 115 degrees. between degrees. The image monitoring and warning system for a vehicle according to claim 1, wherein the angle between the optical axis of the second camera and the side of the vehicle in a direction parallel to the ground is between 20 degrees and 40 degrees. between degrees. The image monitoring and warning system for a vehicle according to claim 1, wherein the aspect ratio of the first continuous image is 4:3, and the aspect ratio of the second continuous image is 16: 9.

Images