CN110672335A - Method and device for judging failure of lane keeping auxiliary function - Google Patents
Method and device for judging failure of lane keeping auxiliary function Download PDFInfo
- Publication number
- CN110672335A CN110672335A CN201910872534.6A CN201910872534A CN110672335A CN 110672335 A CN110672335 A CN 110672335A CN 201910872534 A CN201910872534 A CN 201910872534A CN 110672335 A CN110672335 A CN 110672335A
- Authority
- CN
- China
- Prior art keywords
- event
- lane line
- camera
- signal data
- events
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M17/00—Testing of vehicles
- G01M17/007—Wheeled or endless-tracked vehicles
Abstract
The invention relates to a method and a device for judging the failure of a lane keeping auxiliary function, wherein the method comprises the following steps: and acquiring CAN signal data in the camera data. And respectively identifying the lane line event, the camera problem event and the road condition information event from the CAN signal data based on a preset lane line event rule, a preset camera problem event rule and a preset road condition information event rule. And (4) according to the lane line event, the camera problem event and the road condition information event, counting and analyzing the LKA function failure condition. According to the invention, lane line events, camera problem events and road condition information events are extracted from CAN signal data through a pre-designed event rule, and statistics is carried out on the events to analyze the effectiveness of the LKA function. Compared with the prior art, the method has the advantages that the effectiveness of the LKA function is rapidly verified, the time required by LKA function failure verification is greatly shortened, the labor cost is saved, and the efficiency of LKA function failure verification is improved.
Description
Technical Field
The invention relates to the technical field of automobile safety, in particular to a method and a device for judging the failure of a lane keeping auxiliary function.
Background
Lane Keep Assist (LKA), which is one of the core functions in an Automatic Driving Assist System (ADAS), is essential for a road test provided by the Lane Keep Assist (LKA) which is a safe driving assist system capable of helping a vehicle keep driving on a specified Lane, and the LKA function is evaluated by analyzing data collected by a camera in the road test process, thereby helping later-stage system optimization and improvement.
However, in the conventional analysis method for verifying the LKA function, a large amount of manual video playback is needed to locate an event occurrence point, whether the LKA function has a failure state is judged through full visual observation, taking the total time of 4 kilometers and miles as 41178 minutes of road test data as an example, the video visual time of 300 minutes per person per day is normally set, on average, only 291 kilometers of visual tasks can be completed per person per day, and about 137 days is needed for completing all visual tasks per person. Therefore, at present, no effective testing method exists for LKA function failure verification, and a large amount of labor cost is consumed.
Disclosure of Invention
The invention provides a method and a device for judging lane keeping auxiliary function failure, aiming at the technical problems in the prior art, and solving the problems that the conventional LKA function failure verification method depends on manual visual completion and consumes labor cost.
The technical scheme for solving the technical problems is as follows:
in a first aspect, the present invention provides a method for determining a failure of a lane keeping assist function, including:
s1, acquiring CAN signal data in the camera data;
s2, respectively identifying lane line events, camera problem events and road condition information events from the CAN signal data based on preset lane line event rules, camera problem event rules and road condition information event rules;
and S3, performing statistical analysis on LKA function failure conditions according to the lane line events, the camera problem events and the road condition information events identified from the CAN signal data.
Further, after acquiring CAN signal data in the camera data, the method further includes:
and classifying signals related to lane line events, signals related to camera problem events and signals related to road condition information events in the CAN signal data into first CAN signal data, second CAN signal data and third CAN signal data respectively.
Further, in step S2, extracting the lane line event from the CAN signal data based on the preset lane line event rule specifically includes:
on the basis of the condition judgment of the abnormal state of the lane line identification, the following lane line event judgment conditions are preset; wherein the lane line event determination condition includes:
a1, in the running process of the vehicle, the absolute value of the distance difference between the current frame and the previous frame of the vehicle and the lane line is in the range of the preset distance threshold;
a2, in the driving process of the vehicle, the absolute value of the difference value of the lane line sight distances of the current frame and the previous frame is greater than the driving distance of the current frame within 1s, and the speed of the current frame is greater than a preset speed threshold;
a3, in the driving process of the vehicle, the lane line sight distance of the current frame is less than the driving distance of the current frame within 0.8 s;
a4, when the lane line type is not the road edge and the lane line type cannot be confirmed, the lane line reliability is a credible state;
a5, the reliability of the lane line of the current frame and the previous frame is more than the middle reliability;
a6, the vehicle is not in the state of crossing the right lane line or the left lane line;
the lane lines are left lane lines or right lane lines, and the lane line events comprise transverse lane line events and longitudinal lane line events;
if the first CAN signal data are judged to simultaneously meet the conditions of a1, a4, a5 and a6, judging that the vehicle has a transverse lane line event;
and if the first CAN signal data are judged to simultaneously meet the conditions of a2, a4, a5 and a6 or the first CAN signal data simultaneously meet the conditions of a3, a4, a5 and a6, judging that the vehicle has a longitudinal lane line event.
Further, in step S2, based on a preset rule of the camera problem event, extracting the camera problem event from the CAN signal data specifically includes:
if the second CAN signal data is judged and obtained to meet at least one of the following camera problem event judgment conditions, judging that the vehicle has a camera problem event;
wherein, camera problem incident decision condition includes: complete blocking of the camera lens, partial blocking, blurred images, glare, icing of the front rail, smudges in the camera, and fogging of the camera.
Further, in step S2, based on the preset traffic information event rule, the extracting the traffic information event from the CAN signal data specifically includes:
presetting the following road condition information event judgment conditions, and positioning the special driving scene of the vehicle; the condition for judging the traffic information event comprises the following steps:
b1, positioning the vehicle at the high speed exit branch position;
b2, the vehicle is driven on a lane close to a high-speed exit;
b3, the vehicle speed is greater than a preset speed threshold;
and if the third CAN signal data are judged to simultaneously meet the conditions of b1, b2 and b3, judging that the vehicle has a road condition information event.
Further, according to the lane line event, the camera problem event and the road condition information event, the LKA function failure condition is statistically analyzed, and the method specifically includes:
when a lane line event or a camera problem event occurs in the vehicle, judging that the LKA function is invalid;
when a road condition information event occurs to the vehicle, extracting a video file corresponding to the current frame from video data collected by a camera, opening the video file, checking video images in the current frame and a plurality of frames adjacent to the current frame, and judging whether the LKA function is invalid or not.
In a second aspect, the present invention provides a lane keeping assist function failure determination device, comprising:
the acquisition module is used for acquiring CAN signal data in the camera data;
the event identification module is used for respectively identifying lane line events, camera problem events and road condition information events from the CAN signal data based on preset lane line event rules, camera problem event rules and road condition information event rules;
and the LKA functional failure analysis module is used for carrying out statistical analysis on LKA functional failure conditions according to the lane line events, the camera problem events and the road condition information events identified from the CAN signal data.
Further, the LKA functional failure analysis is specifically configured to:
when a lane line event or a camera problem event occurs in the vehicle, judging that the LKA function is invalid;
when a road condition information event occurs to the vehicle, extracting a video file corresponding to the current frame from video data collected by a camera, opening the video file, checking video images in the current frame and a plurality of frames adjacent to the current frame, and judging whether the LKA function is invalid or not.
In a third aspect, the present invention provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the method as provided in the first aspect when executing the program.
In a fourth aspect, the invention provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method as provided in the first aspect.
According to the method and the device for judging the failure of the lane keeping auxiliary function, the CAN signals in the sensor are classified according to the LKA function, lane line events, camera problem events and road condition information events are extracted from the CAN signal data collected by the camera through the pre-designed event rules, and the effectiveness of the LKA function is analyzed through statistics of the events. Compared with the prior art that the LKA function is verified by manually replaying videos and visually identifying the abnormal driving state of the vehicle, and a large amount of labor cost is consumed, the method greatly shortens the time required by LKA function failure verification, saves the labor cost, and improves the verification efficiency of LKA function failure.
Drawings
Fig. 1 is a schematic flow chart of a method for determining failure of a lane keeping assist function according to an embodiment of the present invention;
fig. 2 is a block diagram of a device for determining that a lane keeping assist function is disabled according to an embodiment of the present invention;
fig. 3 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In view of the problem that the conventional LKA function failure determination method needs to manually replay videos and visually identify a vehicle driving abnormal state as a basis for determining LKA function failure, which consumes a large amount of labor cost, an embodiment of the present invention provides a method for determining lane keeping assist function failure, fig. 1 is a schematic flow diagram of a method for determining lane keeping assist function failure according to an embodiment of the present invention, and as shown in fig. 1, the method includes:
and S1, acquiring CAN signal data in the camera data.
Specifically, Lane Keeping Assistance (LKA) can monitor the road markings through a camera, so that the vehicle can keep moving in the original Lane, and danger caused by Lane crossing is avoided. In this embodiment, before step S1 is executed, a road test is first performed on LKA function verification, and video data and CAN signal data are collected by a camera of a vehicle during the road test. After the road test is completed, step S1 is executed to obtain the CAN signal data in the camera data. Here, the camera data includes video data and CAN signal data collected by the camera.
And S2, respectively identifying the lane line event, the camera problem event and the road condition information event from the CAN signal data based on the preset lane line event rule, the camera problem event rule and the road condition information event rule.
Specifically, in the road test process aiming at LKA function verification, an LKA function failure event may occur in the vehicle, and the LKA function failure event is divided into 3 types in the embodiment, including a lane line event, a camera problem event, and a road condition information event. The lane line event represents that lane line identification is abnormal, the camera problem event represents that the camera is fuzzy, and the road condition information event represents that the vehicle is positioned in a special scene.
In this embodiment, a determination rule of an LKA function failure event is preset, and a lane line event, a camera problem event, and a road condition information event are identified from the CAN signal data according to the determination rule of the LKA function failure event.
And S3, performing statistical analysis on LKA function failure conditions according to the lane line events, the camera problem events and the road condition information events identified from the CAN signal data.
Specifically, the effectiveness of the LKA function is analyzed and judged through the lane line event, the camera problem event and the road condition information event. When a lane line event or a camera problem event is identified according to the CAN signal data, lane line identification abnormality or the camera is fuzzy is indicated, and the LKA function is invalid at the moment. When a road condition information event occurs to the vehicle, the vehicle is positioned in a special scene, at the moment, a video file corresponding to the current frame is extracted, and whether the LKA function is invalid or not is judged visually.
It should be noted that, in the conventional LKA function failure judgment method, video data in the road test data needs to be manually played back, and the abnormal vehicle driving state is visually identified as an LKA function failure judgment basis, so that a large amount of labor cost is consumed, and the efficiency is low. Taking the road test data of the total duration of 4 kilometers and miles of 41178 minutes as an example, by adopting the traditional LKA functional failure judgment method, under the normal condition, the visual duration of each person is 300 minutes per day, on average, each person can only complete 291 kilometers of visual tasks per day, and the duration of about 137 days is needed for completing all visual tasks for one person. The road test data refers to data collected by a camera in the road test process. The embodiment of the invention extracts CAN signal data acquired by the camera, identifies lane line events, camera problem events and road condition information events from the CAN signal data through a preset LKA function failure event judgment rule, performs statistical analysis on the LKA function failure event, and judges the effectiveness of the LKA function, thereby realizing the quick judgment of the effectiveness of the LKA function. Experiments show that the method for judging LKA functional failure provided by the invention has the advantages that the efficiency of identifying the LKA functional failure event is 1.6 kilokilometers of road test data per person per hour, and the time spent on completely identifying and completing the road test data with the mileage of 4 kilokilometers is about 2.5 hours.
According to the method for judging the failure of the lane keeping auxiliary function, the CAN signals in the sensor are classified according to the LKA function, lane line events, camera problem events and road condition information events are extracted from the CAN signal data collected by the camera through a pre-designed LKA function failure event judgment rule, the events are counted, and the effectiveness of the LKA function is analyzed. Compared with the prior art that video data in a road test process needs to be manually checked to verify the LKA function, and a large amount of labor cost is consumed, the method and the system for verifying the LKA function failure greatly shorten the time required by the LKA function failure verification, save the labor cost and improve the verification efficiency of the LKA function failure.
Based on the content of the above embodiment, after acquiring CAN signal data in the camera data, the method further includes:
and classifying signals related to lane line events, signals related to camera problem events and signals related to road condition information events in the CAN signal data into first CAN signal data, second CAN signal data and third CAN signal data respectively.
Specifically, after the CAN signal data is acquired in step S1, the CAN signal data needs to be classified based on the LKA function failure event. Signals related to lane line events in the CAN signal data are classified into first CAN signal data, signals related to camera problem events in the CAN signal data are classified into second CAN signal data, and signals related to road condition information events in the CAN signal data are classified into third CAN signal data. For example, the signal data about the vehicle speed, the lane distance and the sight distance in the CAN signal data belong to the signals related to the lane event, and such signals are classified as the first CAN signal data.
Based on any of the above embodiments, in step S2, based on the preset lane line event rule, the extracting the lane line event from the CAN signal data specifically includes:
on the basis of the condition judgment of the abnormal state of the lane line identification, the following lane line event judgment conditions are preset; wherein the lane line event determination condition includes:
a1, during the running of the vehicle, the absolute value of the distance difference between the current frame and the previous frame of the vehicle and the lane line is in the range of the preset distance threshold.
Specifically, under the condition that the LKA function is normal, the vehicle runs at the central position between the two lane lines, and no deviation occurs. When the vehicle deviates, the absolute value of the distance difference between the vehicle and the lane line can be approximately judged to be within the preset distance threshold range. Preferably, the first preset distance threshold is set to be 0.18 to 1.8m, which is not particularly limited in the embodiment of the present invention.
a2, in the driving process of the vehicle, the absolute value of the difference value of the lane line sight distances of the current frame and the previous frame is greater than the driving distance of the current frame within 1s, and the speed of the current frame is greater than the preset speed threshold.
a3, in the driving process of the vehicle, the line-of-sight distance of the current frame is less than the distance driven by the current frame within 0.8 s.
Here, the lane line visual distance is the visual distance of the camera to the lane line in front of the vehicle. The present embodiment sets the conditions of a2 and a3 to determine the abnormal situation of the vertical lane-line sight distance during high-speed running of the vehicle. Preferably, the preset speed threshold is set to 90km/h, which is not particularly limited in the embodiment of the present invention.
a4, when the lane line type is not the road edge and the lane line type cannot be confirmed, the lane line reliability is the credible state.
a5, the reliability of the lane line between the current frame and the previous frame is more than the middle-level reliability. The lane line reliability in the CAN signal data comprises a credible state and an incredible state. The level of reliability includes a low level of confidence, a medium level of confidence and a high level of confidence. The reliability represents the reliability of the camera for accurately identifying the lane line.
a6, the vehicle is not in the state of crossing the right lane line or the left lane line;
in the above-described a1 to a6, the lane line is a left lane line or a right lane line, and the lane line event determination condition for the right lane line is the same as the lane line event determination condition for the left lane line.
The lane line events comprise transverse lane line events and longitudinal lane line events, and if the first CAN signal data are judged to simultaneously meet the conditions of a1, a4, a5 and a6, the vehicle is judged to have the transverse lane line events;
and if the conditions of a2, a4, a5 and a6 are simultaneously met by the first CAN signal data or the conditions of a3, a4, a5 and a6 are simultaneously met by the CAN signal data, judging that the vehicle has a longitudinal lane line event.
Specifically, in the present embodiment, the lane line event is identified based on the first CAN signal data related to the lane line event, and a scene of lane line identification abnormality is searched in the first CAN signal data according to the lane line event determination condition. When the first CAN signal data simultaneously satisfies the conditions of a1, a4, a5 and a6, it CAN be judged that the vehicle has an offset and the vehicle is not running at a central position between two lane lines, at which time it is judged that the vehicle has a lateral lane line event. When the first CAN signal data simultaneously accords with the conditions of a2, a4, a5 and a6 or the CAN signal data simultaneously accords with the conditions of a3, a4, a5 and a6, the fact that the vertical lane line sight distance is abnormal CAN be judged, and at the moment, a vertical lane line event occurs to the vehicle.
Based on any of the above embodiments, in step S2, based on a preset rule of the camera problem event, the extracting the camera problem event from the CAN signal data specifically includes:
if the second CAN signal data is judged and obtained to meet at least one of the following camera problem event judgment conditions, judging that the vehicle has a camera problem event;
wherein, camera problem incident decision condition includes: complete blocking of the camera lens, partial blocking, blurred images, glare, icing of the front rail, smudges in the camera, and fogging of the camera.
Specifically, the camera problem event judgment conditions are set by considering factors influencing camera imaging, and the camera problem event judgment conditions comprise complete blocking, partial blocking, image blurring, glare, freezing of a front gear, stain on the camera, fog on the camera and the like. And judging the camera problem event according to the signal fluctuation condition of the second CAN signal data.
Based on any of the above embodiments, in step S2, based on the preset traffic information event rule, the extracting the traffic information event from the CAN signal data specifically includes:
presetting the following road condition information event judgment conditions, and positioning the special driving scene of the vehicle; the condition for judging the traffic information event comprises the following steps:
b1, positioning the vehicle at the high speed exit branch position;
b2, the vehicle is driven on a lane close to a high-speed exit;
b3, the vehicle speed is greater than a preset speed threshold; preferably, the preset speed threshold is set to 90km/h, which is not particularly limited in the embodiment of the present invention.
And if the third CAN signal data are judged to simultaneously meet the conditions of b1, b2 and b3, judging that the vehicle has a road condition information event.
Specifically, the special driving scene of the vehicle is positioned by setting the road condition information event rule. The present embodiment considers a scenario in which the vehicle is positioned at an exit of a highway, and a highway passes near the exit of the highway, but does not descend the highway. And if the third CAN signal data are judged and known to meet the conditions of b1, b2 and b3, the vehicle is in the special scene. The embodiment sets the conditions b1, b2 and b3, and positions a special scene that LKA function failure of the vehicle may happen. The invention can also locate other special scenes where the LKA function of the vehicle may fail, such as corners of the vehicle, and the embodiment of the invention is not particularly limited to the type of the special scenes.
Further, after the vehicle is positioned to be in the special scene, the lane line identification state in the special scene is judged.
Based on any of the above embodiments, in step S3, the statistical analysis of LKA function failure conditions according to the lane line event, the camera problem event, and the road condition information event specifically includes:
when a lane line event or a camera problem event occurs in the vehicle, judging that the LKA function is invalid;
when a road condition information event occurs to the vehicle, extracting a video file corresponding to the current frame from video data collected by a camera, opening the video file, checking video images in the current frame and a plurality of frames adjacent to the current frame, and judging whether the LKA function is invalid or not.
Specifically, the effectiveness of the LKA function is analyzed and judged through the lane line event, the camera problem event and the road condition information event. When a lane line event or a camera problem event is identified according to the CAN signal data, lane line identification abnormality or the camera is fuzzy is indicated, and the LKA function is invalid at the moment.
Furthermore, when a road condition information event occurs to the vehicle, the vehicle is positioned in a special scene, at the moment, the video file corresponding to the current frame is extracted, the video image is checked in the current frame and a plurality of frames adjacent to the current frame, and whether the LKA function fails or not is judged by checking the change condition of the lane line in the current frame.
According to the embodiment of the invention, the LKA functional failure scene is divided into three types of LKA functional failure events, a lane line event, a camera problem event and a road condition information event are extracted from CAN signal data collected by a camera through a pre-designed LKA functional failure event judgment rule, the events are counted, and the LKA functional effectiveness is analyzed. The effectiveness of the LKA function can be rapidly verified, the labor cost is saved, and the verification efficiency of LKA function failure is improved.
Fig. 2 is a block diagram of a device for determining a failure of a lane keeping assist function according to an embodiment of the present invention, and as shown in fig. 2, the present invention provides a device for determining a failure of a lane keeping assist function, including:
the acquiring module 201 is used for acquiring CAN signal data in the camera data;
an event identification module 202, configured to identify a lane line event, a camera problem event, and a road condition information event from the CAN signal data based on a preset lane line event rule, a camera problem event rule, and a road condition information event rule, respectively;
and the LKA function failure analysis module 203 is configured to perform statistical analysis on LKA function failure conditions according to the lane line event, the camera problem event, and the road condition information event identified from the CAN signal data.
Specifically, the device for determining the failure of the lane keeping assist function according to the embodiment of the present invention is specifically configured to execute the steps of the method for determining the failure of the lane keeping assist function according to the embodiment of the present invention, and since the device for determining the failure of the lane keeping assist function has been described in detail in the embodiment, the function of the device for determining the failure of the lane keeping assist function is not described herein again.
The device for judging the failure of the lane keeping auxiliary function classifies the CAN signals in the sensor according to the LKA function, extracts lane line events, camera problem events and road condition information events from the CAN signal data collected by the camera through the pre-designed LKA function failure event judgment rule, counts the events and analyzes the effectiveness of the LKA function. Compared with the prior art that video data in a road test process needs to be manually checked to verify the LKA function, and a large amount of labor cost is consumed, the method and the system for verifying the LKA function failure greatly shorten the time required by the LKA function failure verification, save the labor cost and improve the verification efficiency of the LKA function failure.
Based on any embodiment above, the apparatus further comprises:
and the signal classification module is used for classifying signals related to lane line events, signals related to camera problem events and signals related to road condition information events in the CAN signal data into first CAN signal data, second CAN signal data and third CAN signal data respectively.
Based on any of the embodiments above, the LKA functional failure analysis is specifically configured to:
when a lane line event or a camera problem event occurs in the vehicle, judging that the LKA function is invalid;
when a road condition information event occurs to the vehicle, extracting a video file corresponding to the current frame from video data collected by a camera, opening the video file, checking video images in the current frame and a plurality of frames adjacent to the current frame, and judging whether the LKA function is invalid or not.
Fig. 3 is a schematic entity structure diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 3, the electronic device may include: a processor (processor)301, a communication Interface (communication Interface)302, a memory (memory)303 and a communication bus 304, wherein the processor 301, the communication Interface 302 and the memory 303 complete communication with each other through the communication bus 304. The processor 301 may call a computer program stored on the memory 303 and operable on the processor 301 to execute the method for determining that the lane keeping assist function is disabled provided by the above embodiments, for example, the method includes: and acquiring CAN signal data in the camera data. And respectively identifying the lane line event, the camera problem event and the road condition information event from the CAN signal data based on a preset lane line event rule, a preset camera problem event rule and a preset road condition information event rule. And according to the lane line event, the camera problem event and the road condition information event identified from the CAN signal data, counting and analyzing the LKA function failure condition.
Embodiments of the present invention further provide a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented to, when executed by a processor, perform the method for determining that the lane keeping assist function provided in the foregoing embodiments is disabled, for example, the method includes: and acquiring CAN signal data in the camera data. And respectively identifying the lane line event, the camera problem event and the road condition information event from the CAN signal data based on a preset lane line event rule, a preset camera problem event rule and a preset road condition information event rule. And according to the lane line event, the camera problem event and the road condition information event identified from the CAN signal data, counting and analyzing the LKA function failure condition.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A method for determining failure of a lane keeping assist function, comprising:
s1, acquiring CAN signal data in the camera data;
s2, respectively identifying lane line events, camera problem events and road condition information events from the CAN signal data based on preset lane line event rules, camera problem event rules and road condition information event rules;
and S3, performing statistical analysis on LKA function failure conditions according to the lane line events, the camera problem events and the road condition information events identified from the CAN signal data.
2. The method for determining a lane keeping assist function failure according to claim 1, wherein after acquiring CAN signal data in camera data, the method further comprises:
and classifying signals related to lane line events, signals related to camera problem events and signals related to road condition information events in the CAN signal data into first CAN signal data, second CAN signal data and third CAN signal data respectively.
3. The method for determining the failure of the lane keeping assist function according to claim 2, wherein the step S2, based on the preset lane line event rule, the step of extracting the lane line event from the CAN signal data specifically includes:
on the basis of the condition judgment of the abnormal state of the lane line identification, the following lane line event judgment conditions are preset; wherein the lane line event determination condition includes:
a1, in the running process of the vehicle, the absolute value of the distance difference between the current frame and the previous frame of the vehicle and the lane line is in the range of the preset distance threshold;
a2, in the driving process of the vehicle, the absolute value of the difference value of the lane line sight distances of the current frame and the previous frame is greater than the driving distance of the current frame within 1s, and the speed of the current frame is greater than a preset speed threshold;
a3, in the driving process of the vehicle, the lane line sight distance of the current frame is less than the driving distance of the current frame within 0.8 s;
a4, when the lane line type is not the road edge and the lane line type cannot be confirmed, the lane line reliability is a credible state;
a5, the reliability of the lane line of the current frame and the previous frame is more than the middle reliability;
a6, the vehicle is not in the state of crossing the right lane line or the left lane line;
the lane lines are left lane lines or right lane lines, and the lane line events comprise transverse lane line events and longitudinal lane line events;
if the first CAN signal data are judged to simultaneously meet the conditions of a1, a4, a5 and a6, judging that the vehicle has a transverse lane line event;
and if the first CAN signal data are judged to simultaneously meet the conditions of a2, a4, a5 and a6 or the first CAN signal data simultaneously meet the conditions of a3, a4, a5 and a6, judging that the vehicle has a longitudinal lane line event.
4. The method for determining the failure of the lane keeping assist function according to claim 3, wherein in step S2, the extracting of the camera problem event from the CAN signal data based on the preset camera problem event rule specifically comprises:
if the second CAN signal data is judged and obtained to meet at least one of the following camera problem event judgment conditions, judging that the vehicle has a camera problem event;
wherein, camera problem incident decision condition includes: complete blocking of the camera lens, partial blocking, blurred images, glare, icing of the front rail, smudges in the camera, and fogging of the camera.
5. The method for determining the failure of the lane keeping assist function according to claim 4, wherein in step S2, the step of extracting the traffic information event from the CAN signal data based on the preset traffic information event rule specifically comprises:
presetting the following road condition information event judgment conditions, and positioning the special driving scene of the vehicle; the condition for judging the traffic information event comprises the following steps:
b1, positioning the vehicle at the high speed exit branch position;
b2, the vehicle is driven on a lane close to a high-speed exit;
b3, the vehicle speed is greater than a preset speed threshold;
and if the third CAN signal data are judged to simultaneously meet the conditions of b1, b2 and b3, judging that the vehicle has a road condition information event.
6. The method for determining the failure of the lane keeping assist function according to claim 5, wherein the statistical analysis of the LKA function failure condition according to the lane line event, the camera problem event and the road condition information event specifically comprises:
when a lane line event or a camera problem event occurs in the vehicle, judging that the LKA function is invalid;
when a road condition information event occurs to the vehicle, extracting a video file corresponding to the current frame from video data collected by a camera, opening the video file, checking video images in the current frame and a plurality of frames adjacent to the current frame, and judging whether the LKA function is invalid or not.
7. A lane keeping assist function failure determination device, comprising:
the acquisition module is used for acquiring CAN signal data in the camera data;
the event identification module is used for respectively identifying lane line events, camera problem events and road condition information events from the CAN signal data based on preset lane line event rules, camera problem event rules and road condition information event rules;
and the LKA functional failure analysis module is used for carrying out statistical analysis on LKA functional failure conditions according to the lane line events, the camera problem events and the road condition information events identified from the CAN signal data.
8. The apparatus for determining a failure of a lane keeping assist function according to claim 7, wherein the LKA failure analysis is specifically configured to:
when a lane line event or a camera problem event occurs in the vehicle, judging that the LKA function is invalid;
when a road condition information event occurs to the vehicle, extracting a video file corresponding to the current frame from video data collected by a camera, opening the video file, checking video images in the current frame and a plurality of frames adjacent to the current frame, and judging whether the LKA function is invalid or not.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method for determining a failure of a lane keeping aid function according to any one of claims 1 to 6 when executing the program.
10. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for determining a lane keeping aid failure according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910872534.6A CN110672335A (en) | 2019-09-16 | 2019-09-16 | Method and device for judging failure of lane keeping auxiliary function |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910872534.6A CN110672335A (en) | 2019-09-16 | 2019-09-16 | Method and device for judging failure of lane keeping auxiliary function |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110672335A true CN110672335A (en) | 2020-01-10 |
Family
ID=69077967
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910872534.6A Pending CN110672335A (en) | 2019-09-16 | 2019-09-16 | Method and device for judging failure of lane keeping auxiliary function |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110672335A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111881735A (en) * | 2020-06-17 | 2020-11-03 | 武汉光庭信息技术股份有限公司 | Event classification extraction method and device for automatic driving video data |
| CN112329564A (en) * | 2020-10-24 | 2021-02-05 | 武汉光庭信息技术股份有限公司 | Lane keeping function failure analysis method, system, electronic device and storage medium |
| CN112346985A (en) * | 2020-11-24 | 2021-02-09 | 武汉光庭信息技术股份有限公司 | ACC function failure determination method, system, device and storage medium |
| CN113276853A (en) * | 2021-05-21 | 2021-08-20 | 武汉光庭信息技术股份有限公司 | LKA control method and system in failure scene |
-
2019
- 2019-09-16 CN CN201910872534.6A patent/CN110672335A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111881735A (en) * | 2020-06-17 | 2020-11-03 | 武汉光庭信息技术股份有限公司 | Event classification extraction method and device for automatic driving video data |
| CN111881735B (en) * | 2020-06-17 | 2022-07-29 | 武汉光庭信息技术股份有限公司 | Event classification extraction method and device for automatic driving video data |
| CN112329564A (en) * | 2020-10-24 | 2021-02-05 | 武汉光庭信息技术股份有限公司 | Lane keeping function failure analysis method, system, electronic device and storage medium |
| CN112346985A (en) * | 2020-11-24 | 2021-02-09 | 武汉光庭信息技术股份有限公司 | ACC function failure determination method, system, device and storage medium |
| CN112346985B (en) * | 2020-11-24 | 2022-05-10 | 武汉光庭信息技术股份有限公司 | ACC function failure determination method, system, device and storage medium |
| CN113276853A (en) * | 2021-05-21 | 2021-08-20 | 武汉光庭信息技术股份有限公司 | LKA control method and system in failure scene |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110672335A (en) | Method and device for judging failure of lane keeping auxiliary function | |
| CN109887281B (en) | Method and system for monitoring traffic incident | |
| CN107967806B (en) | Vehicle fake-license detection method, device, readable storage medium storing program for executing and electronic equipment | |
| US10212397B2 (en) | Abandoned object detection apparatus and method and system | |
| CN110769246B (en) | Method and device for detecting faults of monitoring equipment | |
| CN110619747A (en) | Intelligent monitoring method and system for highway road | |
| US20200380284A1 (en) | Method and Apparatus For License Plate Recognition Using Multiple Fields of View | |
| CN108932849B (en) | Method and device for recording low-speed running illegal behaviors of multiple motor vehicles | |
| CN111325988A (en) | Real-time red light running detection method, device and system based on video and storage medium | |
| CN110032947B (en) | Method and device for monitoring occurrence of event | |
| CN110909692A (en) | Abnormal license plate recognition method and device, computer storage medium and electronic equipment | |
| CN106571040B (en) | Suspicious vehicle confirmation method and equipment | |
| CN113269042B (en) | Intelligent traffic management method and system based on driving vehicle violation identification | |
| CN108932850B (en) | Method and device for recording low-speed driving illegal behaviors of motor vehicle | |
| CN113450578A (en) | Traffic violation event evidence obtaining method, device, equipment and system | |
| KR20190064147A (en) | Vehicle's behavior analyzing system using aerial photo and analyzing method using the same | |
| CN111768630A (en) | Violation waste image detection method and device and electronic equipment | |
| CN115965636A (en) | Vehicle side view generating method and device and terminal equipment | |
| CN114170565A (en) | Image comparison method and device based on unmanned aerial vehicle aerial photography and terminal equipment | |
| CN113920749A (en) | Vehicle following identification method and system for parking lot and related device | |
| CN112597924A (en) | Electric bicycle track tracking method, camera device and server | |
| CN111152785A (en) | Test positioning method and device for lane departure early warning function | |
| CN116740660B (en) | Vehicle data processing method and system based on AI technology | |
| CN113112814B (en) | Snapshot method and device without stopping right turn and computer storage medium | |
| CN115861624B (en) | Method, device, equipment and storage medium for detecting occlusion of camera |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200110 |