CN113370973B - Forward collision early warning algorithm considering prediction of driving intention of front vehicle - Google Patents
Forward collision early warning algorithm considering prediction of driving intention of front vehicle Download PDFInfo
- Publication number
- CN113370973B CN113370973B CN202110619312.0A CN202110619312A CN113370973B CN 113370973 B CN113370973 B CN 113370973B CN 202110619312 A CN202110619312 A CN 202110619312A CN 113370973 B CN113370973 B CN 113370973B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- forward collision
- early warning
- driving intention
- driving
- 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.)
- Active
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
Abstract
The invention relates to a forward collision early warning algorithm, which comprises the following steps: collecting a vehicle-mounted forward camera video; the method comprises the steps of obtaining the running state of a vehicle in front of a vehicle in a video through target detection, and analyzing a forward collision risk scene; determining key indexes and parameters of a forward collision risk scene to obtain the association between the motion state of a forward vehicle in the scene and the running state of the vehicle; dividing a front vehicle state type, a vehicle distance change type and a driving state type of the vehicle, and establishing a front vehicle driving intention prediction model; and the forward collision early warning algorithm is incorporated into the forward collision early warning algorithm by the prediction result of the driving intention of the front vehicle, so that the accuracy of the forward collision early warning algorithm is improved. Compared with the prior art, the early warning accuracy is higher, the calculation steps are simpler, the time consumption is less, and the requirement on hardware is low.
Description
Technical Field
The invention relates to the field of safe driving of automobiles, in particular to a forward collision early warning considering prediction of driving intention of a front automobile.
Background
Among the reasons for the occurrence of rear-end collision accidents, the failure to maintain a safe vehicle distance due to the lack of concentration of the driver's attention, delayed driving reaction, and perceived errors of danger perception is a main factor that ultimately causes the occurrence of collision. It has been studied that 90% of factors causing an accident in a rear-end accident occurrence mechanism are related to drivers. Aiming at rear-end collision accidents, the generation of a forward collision avoidance alarm (ForwardCollisionWarning, FCW) system provides great potential for improving driving safety and relieving and reducing the occurrence of rear-end collision accidents. The FCW system utilizes the sensor to detect the road and the movement condition in front of the vehicle, and gives warning information to the driver at proper time when the potential collision danger exists in front of the vehicle, so that the driver is assisted to avoid collision and accident more effectively.
The development and research of FCW systems is currently attracting worldwide attention, and so far, automobile manufacturers in many countries have developed and tested mature systems. At the same time, the potentially enormous security benefits of FCW systems have also been demonstrated through a number of studies. Internationally, the more attention is paid to active safety systems for vehicles, and developed countries have begun to regulate the installation and configuration of vehicles with respect to FCW systems in a step-by-step manner. In addition, due to the differences of driving behaviors and habits, the FCW system applicable to foreign countries is not necessarily applicable to the chinese driver, but cannot be accepted by the chinese driver.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a forward collision early warning considering the prediction of the driving intention of a front vehicle.
The aim of the invention can be achieved by the following technical scheme:
a forward collision warning considering front vehicle driving intention prediction, the method comprising the steps of:
step S1: acquiring a front vehicle motion video acquired by a front camera of a vehicle;
step S2: analyzing common risk scenes and vehicle driving characteristics in a forward collision scene;
step S3: determining a front vehicle through target detection, and detecting the movement speed, acceleration and vehicle distance change condition of the front vehicle in the video by means of a video identification method;
step S4: establishing a driving intention prediction model in four states of acceleration, deceleration, uniform speed and static state of the front vehicle;
step S5: the driving intention prediction result is integrated into a forward collision early warning algorithm, the forward collision early warning TTC index considering the driving intention prediction result is compared, the forward collision early warning algorithm is optimized, and the forward collision early warning is completed;
the process for predicting the driving intention of the front vehicle comprises the following steps:
step S31: calculating a correlation model corresponding to the change of the driving state of the vehicle under each front driving state, wherein the driving state of the vehicle comprises the change of the vehicle distance and the change of the vehicle speed;
step S32: utilizing a hidden Markov model to establish a driving intention prediction model in four states of acceleration, deceleration, uniform speed and static state of a front vehicle, wherein state variables in the model are front vehicle driving states, and observation variables comprise vehicle distance changes and own vehicle driving states, wherein the vehicle distance changes comprise vehicle distance changes, vehicle distance changes and vehicle distance decreases, and the own vehicle driving states are braked, decelerated and not braked emergently;
step S33: calculating by adopting a test set to obtain a state transition probability matrix A, an observation probability matrix B and an initial state probability vector pi in the driving intention prediction model;
step S34: and predicting the driving intention state by adopting a Viterbi algorithm, obtaining a result of an optimal path, namely the predicted driving intention of the front vehicle, and incorporating the driving intention result into a forward collision early warning algorithm to complete the forward collision early warning algorithm.
Preferably, the front car driving intention is collected by a vehicle-mounted camera.
Compared with the prior art, the invention has the following advantages:
(1) Compared with the existing forward collision early warning algorithm, the method has the advantages of simpler calculation steps, less time consumption and low requirement on hardware.
(2) The method is a generic algorithm, does not need special instruments or custom hardware, combines traffic engineering theory through a simple video sensor comprising a mobile phone camera, detects and detects the driving intention of the front car, and has practical significance in the aspects of subsequently forming a perfect forward collision early warning system and the like.
Drawings
FIG. 1 is a flow chart of the present invention;
fig. 2 is a vehicle forward video selection.
Detailed Description
The invention will now be described in detail with reference to the drawings and specific examples. The present embodiment is implemented on the premise of the technical scheme of the present invention, and a detailed implementation manner and a specific operation process are given, but the protection scope of the present invention is not limited to the following examples.
Examples
The embodiment provides a forward collision early warning algorithm considering the prediction of the driving intention of a front vehicle, as shown in fig. 1, a forward camera is used for recording the driving video of the front vehicle, and the collision risks of different degrees are subjected to grading early warning, so that the rear-end collision traffic accidents are reduced. The method comprises the following steps:
step S1: acquiring a front vehicle motion video acquired by a front camera of a vehicle;
step S2: analyzing common risk scenes and vehicle driving characteristics in a forward collision scene;
step S3: determining a front vehicle through target detection, and detecting the movement speed, acceleration and vehicle distance change condition of the front vehicle in the video by means of a video identification method;
step S4: establishing a driving intention prediction model in four states of acceleration, deceleration, uniform speed and static state of the front vehicle;
step S5: the driving intention prediction result is integrated into a forward collision early warning algorithm, the forward collision early warning TTC index considering the driving intention prediction result is compared, the forward collision early warning algorithm is optimized, and the forward collision early warning is completed;
the process for predicting the driving intention of the front vehicle comprises the following steps:
step S31: calculating a correlation model corresponding to the change of the driving state of the vehicle under each front driving state, wherein the driving state of the vehicle comprises the change of the vehicle distance and the change of the vehicle speed;
step S32: and establishing a driving intention prediction model in four states of acceleration, deceleration, uniform speed and static of the front vehicle by using the hidden Markov model. The state variables in the model are the running states of the front vehicle, and the observed variables comprise the vehicle distance change (the vehicle distance is increased, the vehicle distance is unchanged and the vehicle distance is reduced) and the running states of the own vehicle (emergency braking, decelerating and non-braking);
step S33: calculating by adopting a test set to obtain a state transition probability matrix A, an observation probability matrix B and an initial state probability vector pi in the driving intention prediction model;
step S34: and predicting the driving intention state by adopting a Viterbi algorithm, obtaining a result of an optimal path, namely the predicted driving intention of the front vehicle, and incorporating the driving intention result into a forward collision early warning algorithm to complete the forward collision early warning algorithm.
The front car driving intention is collected through the vehicle-mounted camera.
Claims (8)
1. A forward collision early warning algorithm considering prediction of a driving intention of a preceding vehicle, characterized in that the algorithm comprises the steps of:
step S1: acquiring a front vehicle motion video acquired by a front camera of a vehicle;
step S2: analyzing common risk scenes and vehicle driving characteristics in a forward collision scene;
step S3: determining a front vehicle through target detection, and detecting the movement speed, acceleration and vehicle distance change condition of the front vehicle in the video by means of a video identification method;
step S4: establishing a driving intention prediction model in four states of acceleration, deceleration, uniform speed and static state of the front vehicle;
step S5: the driving intention prediction result is integrated into a forward collision early warning algorithm, the forward collision early warning TTC index considering the driving intention prediction result is compared, the forward collision early warning algorithm is optimized, and the forward collision early warning is completed;
the process for predicting the driving intention of the front vehicle comprises the following steps:
step S31: calculating a correlation model corresponding to the change of the driving state of the vehicle under each front driving state, wherein the driving state of the vehicle comprises the change of the vehicle distance and the change of the vehicle speed;
step S32: utilizing a hidden Markov model to establish a driving intention prediction model in four states of acceleration, deceleration, uniform speed and static state of a front vehicle; the state variables in the model are front vehicle running states, the observation variables comprise vehicle distance changes and own vehicle running states, wherein the vehicle distance changes comprise vehicle distance changes, vehicle distance is unchanged or vehicle distance is reduced, and the own vehicle running states comprise emergency braking, deceleration or no braking;
step S33: calculating by adopting a test set to obtain a state transition probability matrix A, an observation probability matrix B and an initial state probability vector pi in the driving intention prediction model;
step S34: predicting the driving intention state by adopting a Viterbi algorithm, obtaining the result of an optimal path, namely the predicted driving intention of the front vehicle, and incorporating the driving intention result into a forward collision early warning algorithm to complete the forward collision early warning algorithm;
the three elements of the front car driving intention prediction model are as follows:
π＝[0.1390.1960.3770.288] T 。
2. the forward collision warning algorithm according to claim 1, wherein the front driving intention is collected by an onboard camera.
3. The forward collision warning algorithm according to claim 1, wherein the prediction frequency of the front vehicle driving intention is 10Hz, and the driving intention of the following 1s is predicted from the front 5s front vehicle driving state and the own vehicle driving state.
4. The forward collision warning algorithm according to claim 1, wherein the front driving intention is divided into four driving intentions of acceleration, deceleration, uniform speed and stationary.
5. The forward collision warning algorithm according to claim 1, wherein the observed variables include increase, decrease, and constant of the vehicle distance, and emergency braking, deceleration, and non-braking of the host vehicle.
6. The forward collision warning algorithm according to claim 1, wherein a hidden markov model is used to build a correlation model of a front vehicle driving state and a host vehicle driving state.
7. The forward collision warning algorithm considering the prediction of the driving intention of a preceding vehicle according to claim 1, wherein the optimum path prediction is performed on the driving intention using a viterbi algorithm.
8. The forward collision early warning algorithm considering front driving intention prediction according to claim 1, wherein the headway is >3s, no early warning, headway < = 1s, primary early warning, headway < = 0.6s, constant sound early warning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110619312.0A CN113370973B (en) | 2021-06-03 | 2021-06-03 | Forward collision early warning algorithm considering prediction of driving intention of front vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110619312.0A CN113370973B (en) | 2021-06-03 | 2021-06-03 | Forward collision early warning algorithm considering prediction of driving intention of front vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113370973A CN113370973A (en) | 2021-09-10 |
| CN113370973B true CN113370973B (en) | 2023-07-21 |
Family
ID=77575665
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110619312.0A Active CN113370973B (en) | 2021-06-03 | 2021-06-03 | Forward collision early warning algorithm considering prediction of driving intention of front vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113370973B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114093187B (en) * | 2021-11-26 | 2023-02-24 | 交通运输部公路科学研究所 | Risk early warning control method for automatic driving vehicle and intelligent network system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2208654A1 (en) * | 2009-01-15 | 2010-07-21 | Ford Global Technologies, LLC | Method and system for avoiding host vehicle collisions with a target |
| CN205910865U (en) * | 2016-06-08 | 2017-01-25 | 吉林大学 | Urgent collision avoidance system of no signal lamp intersection car |
| CN108860148A (en) * | 2018-06-13 | 2018-11-23 | 吉林大学 | Self-adapting cruise control method based on driver's follow the bus characteristic Safety distance model |
| CN110164183A (en) * | 2019-05-17 | 2019-08-23 | 武汉理工大学 | A kind of safety assistant driving method for early warning considering his vehicle driving intention under the conditions of truck traffic |
| CN112078576A (en) * | 2020-09-25 | 2020-12-15 | 英博超算(南京)科技有限公司 | Adaptive cruise control method for simulating driver characteristics based on fuzzy control |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9177477B2 (en) * | 2010-07-19 | 2015-11-03 | Honda Motor Co., Ltd. | Collision warning system using driver intention estimator |
-
2021
- 2021-06-03 CN CN202110619312.0A patent/CN113370973B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2208654A1 (en) * | 2009-01-15 | 2010-07-21 | Ford Global Technologies, LLC | Method and system for avoiding host vehicle collisions with a target |
| CN205910865U (en) * | 2016-06-08 | 2017-01-25 | 吉林大学 | Urgent collision avoidance system of no signal lamp intersection car |
| CN108860148A (en) * | 2018-06-13 | 2018-11-23 | 吉林大学 | Self-adapting cruise control method based on driver's follow the bus characteristic Safety distance model |
| CN110164183A (en) * | 2019-05-17 | 2019-08-23 | 武汉理工大学 | A kind of safety assistant driving method for early warning considering his vehicle driving intention under the conditions of truck traffic |
| CN112078576A (en) * | 2020-09-25 | 2020-12-15 | 英博超算(南京)科技有限公司 | Adaptive cruise control method for simulating driver characteristics based on fuzzy control |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113370973A (en) | 2021-09-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7263233B2 (en) | Method, system and program for detecting vehicle collision | |
| US20220083056A1 (en) | Alerting predicted accidents between driverless cars | |
| US9841762B2 (en) | Alerting predicted accidents between driverless cars | |
| CN110155046B (en) | Automatic emergency braking hierarchical control method and system | |
| US10026320B2 (en) | Vehicle and method for supporting driving safety thereof | |
| CN111137284B (en) | Early warning method and early warning device based on driving distraction state | |
| CN102656613B (en) | A predictive human-machine interface using eye gaze technology, blind spot indicators and driver experience | |
| US8330620B2 (en) | Method for producing a localized warning of dangerous situations for vehicles | |
| Coelingh et al. | Collision warning with auto brake: a real-life safety perspective | |
| US20130024075A1 (en) | Object identification and active safety control for vehicles | |
| CN112590801B (en) | Front collision early warning control method based on fatigue degree of driver | |
| CN105644567A (en) | Driving assistant system based on advanced driver assistant system (ADAS) | |
| CN112026761A (en) | Automobile auxiliary driving method based on data sharing | |
| CN111169462B (en) | Safe distance calculation module and calculation method thereof | |
| CN102963298A (en) | Abnormal behavior monitoring method based on sight detection | |
| CN113370973B (en) | Forward collision early warning algorithm considering prediction of driving intention of front vehicle | |
| CN115158304B (en) | Automatic emergency braking control system and method | |
| CN116630891A (en) | Traffic abnormal event detection system and method | |
| CN115892024A (en) | Automobile driving scene recognition control system, method and storage medium | |
| CN111391855A (en) | Auxiliary control method and device for vehicle | |
| Ruan et al. | A novel scoring method for pedestrian automatic emergency braking systems | |
| US20230045706A1 (en) | System for displaying attention to nearby vehicles and method for providing an alarm using the same | |
| CN115639562B (en) | Commercial vehicle blind spot detection system, braking method, commercial vehicle and storage medium | |
| CN117079495A (en) | Forward collision early warning system and method based on macro-micro mixed traffic flow information | |
| Berdich et al. | Cyberattacks on Adaptive Cruise Controls and Emergency Braking Systems: Adversary Models, Impact Assessment, and Countermeasures |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |