CN115092091A - Vehicle and pedestrian protection system and method based on Internet of vehicles - Google Patents
Vehicle and pedestrian protection system and method based on Internet of vehicles Download PDFInfo
- Publication number
- CN115092091A CN115092091A CN202210811804.4A CN202210811804A CN115092091A CN 115092091 A CN115092091 A CN 115092091A CN 202210811804 A CN202210811804 A CN 202210811804A CN 115092091 A CN115092091 A CN 115092091A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- pedestrian
- ecu
- signal
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 19
- 230000007246 mechanism Effects 0.000 claims description 11
- 230000004438 eyesight Effects 0.000 claims description 10
- 230000009471 action Effects 0.000 claims description 9
- 238000012790 confirmation Methods 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 230000016776 visual perception Effects 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims 1
- 238000007405 data analysis Methods 0.000 abstract description 3
- 230000006855 networking Effects 0.000 abstract 1
- 230000008447 perception Effects 0.000 description 15
- 230000036544 posture Effects 0.000 description 8
- 238000012795 verification Methods 0.000 description 8
- 230000000007 visual effect Effects 0.000 description 6
- 230000009977 dual effect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000006872 improvement Effects 0.000 description 4
- 230000006378 damage Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 241001127637 Plantago Species 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000037237 body shape Effects 0.000 description 2
- 208000014674 injury Diseases 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R21/00—Arrangements or fittings on vehicles for protecting or preventing injuries to occupants or pedestrians in case of accidents or other traffic risks
- B60R21/34—Protecting non-occupants of a vehicle, e.g. pedestrians
- B60R21/38—Protecting non-occupants of a vehicle, e.g. pedestrians using means for lifting bonnets
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention relates to the technical field of traffic safety, in particular to a vehicle and pedestrian protection system and a method based on an internet of vehicles, wherein the system comprises an identification module for identifying whether a vehicle is about to collide with a pedestrian or not, a vehicle-end receiving module for sending received identification result information to an engine hood control module through an ECU (electronic control unit), the engine hood control module for sending a corresponding control execution instruction to the engine hood execution module, and the engine hood execution module for controlling the engine hood to bounce and lightening a work indicator lamp on an instrument panel; this scheme combines high in the clouds recognition function and big data analysis technique, discerns through the car networking, controls engine bonnet initiative and bounces when detecting when about to bump, improves the protectiveness to the pedestrian.
Description
Technical Field
The invention relates to the technical field of traffic safety, in particular to a vehicle and pedestrian protection system and method based on the Internet of vehicles.
Background
Along with the gradual improvement of the safety consciousness of people and the continuous improvement of an automobile safety protection system, the automobile safety protection system not only meets the requirement on the safety performance of the automobile, but also pays more and more attention to the protection of pedestrians in the automobile development process. In the event of a collision between a pedestrian and a vehicle, since the time for the head of the pedestrian to contact the hood is very short, more and more technicians are beginning to study how to protect the hood from secondary injury by making the hood top at a height sufficient to protect the pedestrian during such a relatively short time that the head of the pedestrian collides with the body of the pedestrian.
It is known that the time between a collision of a pedestrian with a body and a collision with a head is about 25ms, and on this basis, there are two main methods for protecting pedestrians:
(1) the distance between the engine cover and a hard point in the engine compartment is increased, so that the head is prevented from being damaged by the hard point in the engine compartment, and the purpose of protecting the head of a pedestrian is achieved;
(2) the active engine hood jacking system is installed, so that after collision with a pedestrian occurs, a sensor at the front end of a vehicle can transmit an instruction to the ECU, a jacking device at the lower part of the engine hood is started, the rear part of the engine hood is lifted up, the distance between the engine hood and a hard point in the engine cabin is increased, and the head of the pedestrian is protected.
Two kinds of pedestrian protection schemes, all after pedestrian and vehicle bump, receive the pedestrian signal of bumping by the sensor, and then bounce engine bonnet, these two kinds of modes are subject to the operating mode difference when pedestrian bumps, the drawback of bringing is exactly that engine bonnet has certain probability and can't bounce before pedestrian bumps, or can't guarantee to bounce to the maximum position before pedestrian bumps, leads to bringing more serious bodily injury for the pedestrian.
In the application CN215097458, "pressure sensing system based on pedestrian protection system", the pressure sensing system uses a pressure sensor to quickly identify the collision of a pedestrian, however, the above-mentioned problems exist in this method, the effect cannot be predicted in advance, and there is a possibility that the response is not timely, and the danger degree is still high.
In the utility model patent publication No. CN 213831608U's utility model patent "a novel active bonnet structure", through set up some at the rear end of bonnet and explode the ware and the connecting rod is exploded to the point, but the front end locking part and the front end cooperation part of the relative slip of the anterior setting of cooperation bonnet simultaneously, the rear end that realizes the bonnet can make progress the rear and remove when the initiative is lifted up, and then is used for sheltering from the structure of vehicle front windshield below, avoids aggravating the damage to the vehicle.
In the above-mentioned solution, a structure capable of springing up the hood upward and forward is proposed, but the design of the structure also depends on a preset sensing system, and no improvement is made in the sensing aspect, and the problem proposed above cannot be solved.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a vehicle and pedestrian protection system and method based on an internet of vehicles, which can automatically bounce an engine hood before a pedestrian collides and further protect the pedestrian and the vehicle.
In order to solve the technical problems, the technical scheme provided by the invention is as follows: the vehicle pedestrian protection system based on the Internet of vehicles comprises an identification module, a vehicle end receiving module, an ECU, an engine cover control module and an engine cover execution module;
the identification module is used for identifying whether the vehicle is about to collide with the pedestrian or not and sending the result information to the vehicle end receiving module when the vehicle is identified as confirmation;
the vehicle-end receiving module sends the received identification result information to the engine hood control module through the ECU;
the engine hood control module sends a corresponding control execution instruction to the engine hood execution module according to the received identification result information sent by the ECU;
and the engine hood execution module controls the engine hood to bounce and lights up a work indicator lamp on the instrument panel according to the received control execution instruction.
In the technical scheme, collision judgment and recognition are carried out through the recognition module, the engine hood is timely bounced through the engine hood execution module, the effect that the engine hood is automatically bounced before colliding with pedestrians is achieved in a pre-known mode, safety performance is improved, the function of lightening the work indicator light can also warn a driver to take braking measures in advance, and pedestrian safety is improved.
Preferably, the recognition module is including setting up at anterior vision perception unit of vehicle and radar perception unit, vision perception unit continuously acquires the vehicle the place ahead image of predetermineeing the within range, and carry out image processing to the place ahead image that obtains and obtain vehicle the place ahead personnel judged result, radar perception unit monitors the vehicle the place ahead information that corresponds predetermineeing the within range, monitoring content includes road conditions data, with plantago pedestrian distance interval data and speed of a motor vehicle data, realized through radar and camera from this whether to the judgement with pedestrian's emergence collision, the precision and the efficiency of judgement can be improved to the mode of dual verification.
Preferably, the visual perception unit uniformly extracts multiple frames of images as key frames according to time, feature extraction and feature normalization are carried out on the human body information of people in each frame of image, including height, posture, upper body images and normal images, meanwhile, features of each frame of image are fused to obtain features of a video level, a feature library is established in the identification module, the visual perception unit compares the fused features with the features in the feature library, if the comparison result is in accordance, it is judged that collision between a vehicle and a pedestrian is about to occur, and therefore the accuracy of collision judgment between the vehicle and the pedestrian is ensured by adopting a model learning mode.
Preferably, the characteristic library stores human body action characteristics of pedestrians under different ages, different statures and different sexes under a plurality of collision situations and collision actions, the human body action characteristics comprise heights, postures and upper half images, and the physical sign information adopted as the parameters can improve the judgment accuracy.
Preferably, the road condition data monitored by the radar sensing unit comprises whether a pedestrian is in front of the vehicle or not, the distance data between the pedestrian and the front of the vehicle is monitored by infrared rays, the vehicle speed data is acquired by the ECU, the pedestrian is monitored by the radar sensing unit, when the distance between the pedestrian and the front of the vehicle is smaller than a preset safety value, the radar sensing unit generates a first signal and sends the first signal to the vehicle-end receiving module, the vehicle-end receiving module sends the first signal to the ECU, the ECU sends a confirmation instruction to the vehicle-end receiving module and the visual sensing unit after receiving the first signal, the visual sensing unit judges whether the pedestrian is about to collide or not after receiving the first signal, if yes, a second signal is generated and sent to the ECU through the vehicle-end receiving module, the ECU sends the instruction to the engine hood control module, and if not, a third signal is generated and sent to the ECU through the vehicle-end receiving module, ECU sends the cancellation instruction and returns to car end receiving module and radar perception unit, has injectd the workflow of two perceptions of radar and camera from this, carries out infrared monitoring judgement by the radar earlier, carries out vision perception verification by the camera afterwards, has ensured the accuracy of judging through the mode of dual verification.
Preferably, the hood actuating module comprises a hood connected with the vehicle body through a hinge and a lifter arranged at the bottom of the hood, and the lifter is in transmission connection with the hinge, so that the hood can be actively bounced under the action of the hinge and the lifter.
The vehicle pedestrian protection method based on the Internet of vehicles comprises the following steps:
(1) sensing and judging whether a pedestrian is in front of the vehicle and whether collision with the pedestrian is about to occur or not through a camera and a radar;
(2) if the judgment result is that collision is about to occur, sending the judgment result information to the ECU;
(3) after receiving the judgment result information, the ECU sends a control execution instruction to a control mechanism of the engine hood;
(4) the control mechanism of the engine cover controls the engine cover to bounce, and lights a corresponding work indicator lamp on the instrument panel to indicate that the engine cover bounces at the moment.
Preferably, in step (1), the camera continuously acquires an image in front of the vehicle within a preset range, and after the image is acquired, the acquired image in front is subjected to image processing to obtain a judgment result of a person in front of the vehicle, where the processing procedure is as follows:
(1.1) uniformly extracting a plurality of frame images as key frames according to time;
(1.2) carrying out feature extraction and feature normalization on the human body information of the person in each frame of image, including the height, the posture, the upper half body image and the normal image;
(1.3) fusing the characteristics of each frame of image to obtain the characteristics of the video level;
and (1.4) comparing the obtained video-level features with the features in the feature library, and if the comparison result is in line, judging that the vehicle and the pedestrian are about to collide.
Preferably, in the step (1), the radar monitors information in front of the vehicle corresponding to a preset range, the monitored content includes road condition data, distance data from pedestrians in front of the vehicle and vehicle speed data, when it is monitored that there is a pedestrian in front of the vehicle and the distance data from the pedestrian is smaller than a preset safety value, the radar generates a first signal and sends the first signal to the ECU, the ECU receives the first signal and sends a confirmation instruction back to the camera, the camera receives the first signal and judges whether collision with the pedestrian is about to occur, if so, a second signal is generated and sent to the ECU, the ECU sends a control execution instruction to a control mechanism of the engine hood, if not, a third signal is generated and sent to the ECU, and the ECU sends a cancellation instruction back to the radar.
Preferably, in the step (4), the engine cover is connected with the vehicle body through a hinge, a lifter is arranged at the bottom of the engine cover, and the engine cover actuating mechanism drives the lifter to drive the engine cover to bounce and reset.
Compared with the prior art, the scheme has the remarkable advantages that:
(1) the scheme combines a cloud recognition function and a big data analysis technology, recognition is carried out through the Internet of vehicles, and when collision is detected to happen, the engine hood is controlled to bounce actively, so that the protection of pedestrians is improved;
(2) the scheme combines big data to carry out information acquisition learning on the body shape and posture of the pedestrian, avoids the occurrence of false recognition conditions, combines visual and radar double verification, and ensures the accuracy and the precision of recognition and judgment.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic block diagram of the present invention;
FIG. 2 is a flow chart of the method steps of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings, and it should be understood that the preferred embodiments described herein are merely for purposes of illustration and explanation, and are not intended to limit the present invention.
As shown in FIG. 1, the vehicle pedestrian protection system based on the Internet of vehicles comprises an identification module, a vehicle end receiving module, an ECU, a hood control module and a hood execution module;
the identification module is used for identifying whether the vehicle is about to collide with the pedestrian or not and sending the result information to the vehicle end receiving module when the vehicle is identified as confirmation;
the vehicle-end receiving module sends the received identification result information to the engine hood control module through the ECU;
the engine hood control module sends a corresponding control execution instruction to the engine hood execution module according to the received identification result information sent by the ECU;
and the engine hood execution module controls the engine hood to bounce and lights a work indicator lamp on the instrument panel according to the received control execution instruction.
In above-mentioned technical scheme, carry out collision judgement discernment through the identification module, realize engine bonnet's in time bounce through engine bonnet execution module, realized accomplishing the effect of bouncing engine bonnet before bumping with the pedestrian with the mode of foreseeing in advance from this, improved the security performance, the function of lighting the work pilot lamp also can warn the driver in advance and take braking measure, improves pedestrian's security.
Wherein, identification module is including setting up at anterior vision perception unit of vehicle and radar perception unit, vision perception unit continuously acquires the vehicle the place ahead image of predetermineeing the within range, and carry out image processing to the place ahead image that obtains and obtain vehicle the place ahead personnel judged result, radar perception unit monitors the vehicle the place ahead information that corresponds predetermineeing the within range, monitoring content includes road conditions data, with plantago pedestrian distance interval data and speed of a motor vehicle data, realized through radar and camera from this whether to the judgement with pedestrian's emergence collision, the precision and the efficiency of judgement can be improved to the mode of dual verification.
Furthermore, the visual perception unit uniformly extracts multiple frames of images as key frames according to time, feature extraction and feature normalization are carried out on the human body information of people including the height, the posture, the upper body image and the normal image in each frame of image, meanwhile, the features of each frame of image are fused to obtain features at a video level, a feature library is established in the identification module, the visual perception unit compares the fused features with the features in the feature library, if the comparison result is in accordance, the fact that the vehicle collides with the pedestrian is judged, and therefore the accuracy of collision judgment with the pedestrian is guaranteed in a model learning mode. The characteristic library stores human body action characteristics of pedestrians under different ages, different statures and different sexes under a plurality of collision situations and collision actions, the human body action characteristics comprise heights, postures and upper body images, and the physical sign information adopted as parameters can improve the judgment accuracy.
The road condition data monitored by the radar sensing unit comprises whether pedestrians exist in front of the vehicle or not, the distance data between the pedestrians and the front of the vehicle through infrared monitoring is obtained through the ECU, the vehicle speed data is obtained through the ECU, the pedestrians exist in front of the vehicle when the radar sensing unit monitors that the pedestrians exist in front of the vehicle, and the distance between the pedestrians and the front of the vehicle obtained through infrared monitoring is smaller than a preset safety value, the radar sensing unit generates a first signal and sends the first signal to the vehicle-end receiving module, the vehicle-end receiving module sends the first signal to the ECU, the ECU sends a confirmation instruction to the vehicle-end receiving module and the visual sensing unit after receiving the first signal, the visual sensing unit judges whether the pedestrians are about to collide or not after receiving the first signal, if yes, a second signal is generated and sent to the ECU through the vehicle-end receiving module, the ECU sends the instruction to the engine hood control module, and if not, a third signal is generated and sent to the ECU through the vehicle-end receiving module, ECU sends cancellation instruction and returns to car end receiving module and radar perception unit, has injectd the workflow of two perceptions of radar and camera from this, carries out infrared monitoring and judges by the radar earlier, carries out vision perception verification by the camera afterwards, has ensured the accuracy of judging through the mode of dual verification.
Finally, the engine hood execution module comprises an engine hood connected with the vehicle body through a hinge and a lifter installed at the bottom of the engine hood, and the lifter is in transmission connection with the hinge, so that the engine hood is actively bounced through the action of the hinge and the lifter.
As shown in fig. 2, the vehicle and pedestrian protection method based on internet of vehicles according to the present invention includes the following steps:
(1) whether there is the pedestrian in vehicle the place ahead through camera and radar perception and judgement to and whether be about to collide with the pedestrian, the camera is handled the image after obtaining the image and is obtained vehicle the place ahead personnel's judged result, and the process of handling is:
(1.1) uniformly extracting a plurality of frame images as key frames according to time;
(1.2) performing feature extraction and feature normalization on the person and human body information including the height, the posture, the upper half body image and the normal image in each frame of image;
(1.3) fusing the characteristics of each frame of image to obtain the characteristics of the video level;
and (1.4) comparing the obtained video-level features with the features in the feature library, and if the comparison result is in line, judging that the vehicle and the pedestrian are about to collide.
(2) If the judgment result is that collision is about to occur, sending the judgment result information to the ECU;
(3) after receiving the judgment result information, the ECU sends a control execution instruction to a control mechanism of the engine hood;
(4) the control mechanism of the engine cover controls the engine cover to bounce and lights a corresponding work indicator lamp on the instrument panel to indicate that the engine cover has bounced at the moment.
In addition, in step (1), the radar monitors information in front of the vehicle within a corresponding preset range, the monitored content comprises road condition data, distance data between pedestrians in front of the vehicle and vehicle speed data, when the pedestrians are monitored, and the distance data between the pedestrians and the vehicle is smaller than a preset safety value, the radar generates a first signal and sends the first signal to the ECU, the ECU sends a confirmation instruction to the camera after receiving the first signal, the camera judges whether the pedestrian is about to collide after receiving the first signal, if so, a second signal is generated and sent to the ECU, the ECU sends a control execution instruction to a control mechanism of the engine hood, if not, a third signal is generated and sent to the ECU, and the ECU sends a cancellation instruction to the radar.
In the step (4), the engine cover is connected with the vehicle body through a hinge, a jacking device is arranged at the bottom of the engine cover, and an engine cover actuating mechanism drives the jacking device to drive the engine cover to bounce and reset.
Compared with the prior art, the scheme has the remarkable advantages that:
(1) the scheme combines a cloud recognition function and a big data analysis technology, recognition is carried out through the Internet of vehicles, and when collision is detected to happen, the engine hood is controlled to bounce actively, so that the protection of pedestrians is improved;
(2) the scheme combines big data to carry out information acquisition learning on the body shape and posture of the pedestrian, avoids the occurrence of false recognition conditions, combines visual and radar double verification, and ensures the accuracy and the precision of recognition and judgment.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described above, or equivalents may be substituted for elements thereof. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A vehicle pedestrian protection system based on the Internet of vehicles is characterized by comprising an identification module, a vehicle end receiving module, an ECU, an engine cover control module and an engine cover execution module;
the identification module is used for identifying whether the vehicle is about to collide with the pedestrian or not and sending the result information to the vehicle end receiving module when the vehicle is identified as confirmation;
the vehicle-end receiving module sends the received identification result information to the engine hood control module through the ECU;
the engine hood control module sends a corresponding control execution instruction to the engine hood execution module according to the received identification result information sent by the ECU;
and the engine hood execution module controls the engine hood to bounce and lights a work indicator lamp on the instrument panel according to the received control execution instruction.
2. The vehicle and pedestrian protection system based on the Internet of vehicles as claimed in claim 1, wherein the recognition module comprises a vision sensing unit and a radar sensing unit, the vision sensing unit is arranged at the front of the vehicle and continuously obtains images in front of the vehicle within a preset range, the obtained images in front are subjected to image processing to obtain judgment results of people in front of the vehicle, the radar sensing unit monitors information in front of the vehicle within the corresponding preset range, and monitoring contents comprise road condition data, data of distance between the vehicle and pedestrians in front of the vehicle and vehicle speed data.
3. The vehicle and pedestrian protection system based on the internet of vehicles according to claim 2, wherein the visual perception unit uniformly extracts multiple frames of images according to time to serve as key frames, feature extraction and feature normalization are carried out on the person and body information including height, posture, upper body images and normal images in each frame of image, meanwhile, features of each frame of image are fused to obtain features of a video level, a feature library is built in the identification module, the visual perception unit compares the features obtained through fusion with the features in the feature library, and if the comparison result is that the comparison result is in line, it is judged that the vehicle and the pedestrian are about to collide.
4. The internet-of-vehicles-based vehicle pedestrian protection system of claim 3, wherein the feature library stores human body motion features of pedestrians under different ages, sizes and sexes under a plurality of collision situations and collision actions, and the human body motion features comprise height, posture and upper body images.
5. The vehicle-networking-based vehicle and pedestrian protection system according to claim 2, wherein the road condition data monitored by the radar sensing unit includes whether a pedestrian is in front of the vehicle or not, the data of the distance between the pedestrian and the front of the vehicle is monitored by infrared rays, the vehicle speed data is acquired by the ECU, the pedestrian is monitored by the radar sensing unit in front of the vehicle, and when the distance between the pedestrian and the front of the vehicle, which is obtained by the infrared ray monitoring, is smaller than a preset safety value, the radar sensing unit generates a first signal and sends the first signal to the vehicle-end receiving module, the vehicle-end receiving module sends the first signal to the ECU, the ECU sends a confirmation instruction to return to the vehicle-end receiving module and the vision sensing unit after receiving the first signal, and the vision sensing unit judges whether collision with the pedestrian is about to occur or not after receiving the first signal, if the signal is positive, generating a second signal and sending the second signal to the ECU through the vehicle end receiving module, sending an instruction to the engine hood control module by the ECU, otherwise, generating a third signal and sending the third signal to the ECU through the vehicle end receiving module, and sending a cancellation instruction by the ECU to return to the vehicle end receiving module and the radar sensing unit.
6. The internet-of-vehicles based vehicle pedestrian protection system of claim 1, wherein the hood actuation module includes a hood connected to a vehicle body by a hinge and a lifter mounted to a bottom of the hood, the lifter drivingly connected to the hinge.
7. A vehicle and pedestrian protection method based on the Internet of vehicles is characterized by comprising the following steps:
(1) sensing and judging whether a pedestrian is in front of the vehicle and whether collision with the pedestrian is about to occur or not through a camera and a radar;
(2) if the judgment result is that collision is about to occur, sending the judgment result information to an ECU;
(3) after receiving the judgment result information, the ECU sends a control execution instruction to a control mechanism of the engine hood;
(4) the control mechanism of the engine cover controls the engine cover to bounce and lights a corresponding work indicator lamp on the instrument panel to indicate that the engine cover has bounced at the moment.
8. The vehicle-networking-based vehicle and pedestrian protection method according to claim 7, wherein in the step (1), the camera continuously acquires images in front of the vehicle within a preset range, and after the acquisition, the acquired images in front are subjected to image processing to obtain a judgment result of people in front of the vehicle, and the processing procedure is as follows:
(1.1) uniformly extracting a plurality of frame images as key frames according to time;
(1.2) carrying out feature extraction and feature normalization on the human body information of the person in each frame of image, including the height, the posture, the upper half body image and the normal image;
(1.3) fusing the characteristics of each frame of image to obtain the characteristics of the video level;
and (1.4) comparing the obtained video-level features with the features in the feature library, and if the comparison result is in line, judging that the vehicle and the pedestrian are about to collide.
9. The Internet of vehicles based pedestrian protection method of claim 7, in the step (1), the radar monitors the information in front of the vehicle within a corresponding preset range, the monitoring content comprises road condition data, data of the distance between the vehicle and pedestrians in front of the vehicle and vehicle speed data, when a pedestrian is monitored in front of the vehicle and the distance data between the pedestrian and the radar is smaller than a preset safety value, the radar generates a first signal and sends the first signal to the ECU, the ECU sends a confirmation instruction to the camera after receiving the first signal, the camera judges whether collision with the pedestrian is about to occur or not after receiving the first signal, if so, a second signal is generated and sent to the ECU which sends control execution instructions to the hood control mechanism, and if not, a third signal is generated and sent to the ECU which sends a cancellation command feedback to the radar.
10. The vehicle-networking-based vehicle and pedestrian protection method according to claim 7, wherein in the step (4), the hood is connected with the vehicle body through a hinge, a lifter is arranged at the bottom of the hood, and the hood actuator drives the lifter to drive the hood to pop up and reset.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210811804.4A CN115092091A (en) | 2022-07-11 | 2022-07-11 | Vehicle and pedestrian protection system and method based on Internet of vehicles |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210811804.4A CN115092091A (en) | 2022-07-11 | 2022-07-11 | Vehicle and pedestrian protection system and method based on Internet of vehicles |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115092091A true CN115092091A (en) | 2022-09-23 |
Family
ID=83297843
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210811804.4A Pending CN115092091A (en) | 2022-07-11 | 2022-07-11 | Vehicle and pedestrian protection system and method based on Internet of vehicles |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115092091A (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040258279A1 (en) * | 2003-06-13 | 2004-12-23 | Sarnoff Corporation | Method and apparatus for pedestrian detection |
| JP2005297755A (en) * | 2004-04-12 | 2005-10-27 | Toyota Motor Corp | Vehicular hood flip-up device |
| JP2008126760A (en) * | 2006-11-17 | 2008-06-05 | Toyota Motor Corp | Vehicular hood tip-up device |
| WO2016185653A1 (en) * | 2015-05-19 | 2016-11-24 | 株式会社デンソー | Protection control apparatus |
| KR20170044349A (en) * | 2015-10-15 | 2017-04-25 | 현대자동차주식회사 | vehicles active hood system and operate method |
| CN107444256A (en) * | 2017-07-31 | 2017-12-08 | 合肥光照信息科技有限公司 | A kind of automobile omnibearing collision avoidance system and its method |
| US20180186368A1 (en) * | 2016-12-30 | 2018-07-05 | Hyundai Motor Company | Posture information based pedestrian detection and pedestrian collision prevention apparatus and method |
| CN108275148A (en) * | 2016-12-30 | 2018-07-13 | 现代自动车株式会社 | Device and method for alleviating pedestrian impact |
| CN108830246A (en) * | 2018-06-25 | 2018-11-16 | 中南大学 | A kind of traffic environment pedestrian multi-dimensional movement characteristic visual extracting method |
| CN110843720A (en) * | 2018-08-21 | 2020-02-28 | 本田技研工业株式会社 | Vehicle protection device and vehicle with same |
| CN111959429A (en) * | 2020-07-21 | 2020-11-20 | 恒大新能源汽车投资控股集团有限公司 | Front cover control method and system and vehicle |
| CN112277869A (en) * | 2019-07-26 | 2021-01-29 | 浙江吉利汽车研究院有限公司 | Pedestrian protection system and method and vehicle |
| CN113627218A (en) * | 2020-05-08 | 2021-11-09 | 北京邮电大学 | Figure identification method and device based on video data |
-
2022
- 2022-07-11 CN CN202210811804.4A patent/CN115092091A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040258279A1 (en) * | 2003-06-13 | 2004-12-23 | Sarnoff Corporation | Method and apparatus for pedestrian detection |
| JP2005297755A (en) * | 2004-04-12 | 2005-10-27 | Toyota Motor Corp | Vehicular hood flip-up device |
| JP2008126760A (en) * | 2006-11-17 | 2008-06-05 | Toyota Motor Corp | Vehicular hood tip-up device |
| WO2016185653A1 (en) * | 2015-05-19 | 2016-11-24 | 株式会社デンソー | Protection control apparatus |
| KR20170044349A (en) * | 2015-10-15 | 2017-04-25 | 현대자동차주식회사 | vehicles active hood system and operate method |
| US20180186368A1 (en) * | 2016-12-30 | 2018-07-05 | Hyundai Motor Company | Posture information based pedestrian detection and pedestrian collision prevention apparatus and method |
| CN108275148A (en) * | 2016-12-30 | 2018-07-13 | 现代自动车株式会社 | Device and method for alleviating pedestrian impact |
| CN107444256A (en) * | 2017-07-31 | 2017-12-08 | 合肥光照信息科技有限公司 | A kind of automobile omnibearing collision avoidance system and its method |
| CN108830246A (en) * | 2018-06-25 | 2018-11-16 | 中南大学 | A kind of traffic environment pedestrian multi-dimensional movement characteristic visual extracting method |
| CN110843720A (en) * | 2018-08-21 | 2020-02-28 | 本田技研工业株式会社 | Vehicle protection device and vehicle with same |
| CN112277869A (en) * | 2019-07-26 | 2021-01-29 | 浙江吉利汽车研究院有限公司 | Pedestrian protection system and method and vehicle |
| CN113627218A (en) * | 2020-05-08 | 2021-11-09 | 北京邮电大学 | Figure identification method and device based on video data |
| CN111959429A (en) * | 2020-07-21 | 2020-11-20 | 恒大新能源汽车投资控股集团有限公司 | Front cover control method and system and vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN208344074U (en) | A kind of comprehensive DAS (Driver Assistant System) of the automobile based on machine vision | |
| EP3348446B1 (en) | Posture information based pedestrian detection and pedestrian collision prevention apparatus and method | |
| CN203228734U (en) | Intelligent active safety forewarning system of automobile | |
| JP4760715B2 (en) | Vehicle motion control device | |
| CN109466488B (en) | Automatic vehicle collision rescue alarm system | |
| CN107585160B (en) | Vehicle danger warning intervention system | |
| CN106080609A (en) | A kind of method and system of safe driving based on ADAS module | |
| CN109455139B (en) | Warning protection device based on car is opened door | |
| US8140226B2 (en) | Security system and a method to derive a security signal | |
| CN104627076A (en) | Automobile and anti-collision pre-warning system for same | |
| CN106864437A (en) | A kind of emergency brake of vehicle system and its control method | |
| CN112977253B (en) | Two-way safety auxiliary system for vehicle | |
| CN204526997U (en) | A kind of vehicle anti-collision early warning system and automobile | |
| CN113276673B (en) | Driver accelerator mistaken stepping prevention control system and control method thereof | |
| CN115257614B (en) | Whole-process collision safety control system of intelligent automobile and automobile | |
| CN106696929A (en) | Method and system for fulfilling automatic emergency braking function on manual transmission car | |
| CN110077356A (en) | A kind of method, apparatus that actively protecting pedestrian, system, memory and terminal | |
| CN103144597B (en) | For running method and the motor vehicles of motor vehicles | |
| JP4751894B2 (en) | A system to detect obstacles in front of a car | |
| CN112339699B (en) | Side-impact prevention system | |
| CN115092091A (en) | Vehicle and pedestrian protection system and method based on Internet of vehicles | |
| CN110203293B (en) | Collision accident detection method, device and system and vehicle | |
| Hattori et al. | Development of forward collision warning system using the driver behavioral information | |
| CN110745093A (en) | Method and system for intelligently identifying vehicle collision event, storage medium and vehicle | |
| CN110182211A (en) | Vehicular intelligent hedging control method based on driver status monitoring system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |