CN117635010A - Vehicle accident identification method and device, electronic equipment and storage medium - Google Patents
Vehicle accident identification method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117635010A CN117635010A CN202311393170.6A CN202311393170A CN117635010A CN 117635010 A CN117635010 A CN 117635010A CN 202311393170 A CN202311393170 A CN 202311393170A CN 117635010 A CN117635010 A CN 117635010A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- transition probability
- determining
- detected
- point
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 230000007704 transition Effects 0.000 claims abstract description 216
- 238000013507 mapping Methods 0.000 claims description 88
- 238000012546 transfer Methods 0.000 claims description 22
- 230000004927 fusion Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 238000005070 sampling Methods 0.000 claims description 6
- 238000013480 data collection Methods 0.000 abstract description 4
- 238000012545 processing Methods 0.000 abstract description 2
- 239000011159 matrix material Substances 0.000 description 10
- 238000004891 communication Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 239000000725 suspension Substances 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 4
- 230000005856 abnormality Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0833—Tracking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
- G06F16/90344—Query processing by using string matching techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/907—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/909—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Remote Sensing (AREA)
- Development Economics (AREA)
- Computational Linguistics (AREA)
- Entrepreneurship & Innovation (AREA)
- Library & Information Science (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a vehicle accident identification method, a device, electronic equipment and a storage medium, belonging to the technical field of data processing, wherein the method comprises the following steps: determining at least one target transition probability value based on the running track data of the vehicle to be detected; the target transition probability value is the probability that the vehicle to be detected transits from a first pause point to a second pause point; determining a transition probability threshold corresponding to the target transition probability value; and determining the accident position of the vehicle to be detected based on the comparison result of the target transition probability value and the transition probability threshold value. According to the invention, the target transition probability value and the transition probability threshold value are determined according to the running track data of the vehicle, so that the types of data collection are simplified; based on the comparison result of the target transition probability value and the transition probability threshold value, the accident position of the vehicle to be detected is obtained, and the comprehensiveness and accuracy of vehicle accident judgment are improved.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a vehicle accident identification method, device, electronic apparatus, and storage medium.
Background
In the field of truck track data analysis, the analysis of the driving behavior of a vehicle and the like is a common direction, and the research of the direction has important supporting values for describing the transportation preference of the truck and grasping the operation rule of the truck, so that basic materials can be provided for the development of the peripheral service of the truck (for example, operators manage the truck, shippers identify vehicles matching own needs through vehicle images, and the safety of the vehicle is evaluated through the operation rule of the truck). However, since the abnormal interference behavior deviating from the normal operation rule of the truck in the real driving process often causes the deviation in analyzing the whole historical data of the truck, the truck accident is one of the abnormal interference behaviors, the truck accident, especially the serious accident, often changes the normal driving mode of the truck in a short period of time, and in a specific analysis scene (especially in the short-term data analysis of a single truck), the generation of the abnormal driving mode brings stronger confusion to the analysis, so that the truck law cannot be summarized, and therefore, the identification and isolation of the truck accident (the period for distinguishing the accident) are very important.
The existing truck accident identification methods are generally divided into three types: (1) screening according to vehicle stay positions; (2) Training a supervised model based on the tag data, and judging whether the truck has an accident or not by using the model; and (3) an anomaly detection method using an isolated forest or the like.
All three methods have respective drawbacks. Based on the screening of the vehicle stay position, depending on the experience judgment of whether the vehicle stay position is normal or not, the application range is greatly limited because the experience judgment is difficult to cover all the situations. The method with the supervision model is more dependent on the accumulation of accident samples, the accident samples are not easy to collect, and the modeling effect is difficult to guarantee under the condition that accidents occur more rarely. The abnormality detection method can identify an abnormality state that occupies a relatively small area, but only focuses on the identification of an abnormality state that deviates from normal during the distinguishing process, and it is difficult to have the ability to merge specific abnormality patterns (e.g., accidents).
In summary, the existing method for identifying the vehicle accident has lower accuracy.
Disclosure of Invention
The invention provides a vehicle accident identification method, a device, electronic equipment and a storage medium, which are used for solving the problem of low accuracy rate of vehicle accident identification in the prior art and realizing accurate identification of the accident position of a vehicle based on single running track data.
In a first aspect, the present invention provides a vehicle accident identification method, including:
determining at least one target transition probability value based on the running track data of the vehicle to be detected; the target transition probability value is the probability that the vehicle to be detected transits from a first pause point to a second pause point;
determining a transition probability threshold corresponding to the target transition probability value;
and determining the accident position of the vehicle to be detected based on the comparison result of the target transition probability value and the transition probability threshold value.
According to the vehicle accident identification method provided by the invention, the determining of at least one target transition probability value based on the running track data of the vehicle to be detected comprises the following steps:
acquiring a stay point and a stay time length of the vehicle to be detected, wherein the speed of the vehicle to be detected is smaller than a first threshold value, and a disconnection point and a disconnection time length of the vehicle to be detected, wherein the signal sampling time interval of the vehicle to be detected is larger than a second threshold value;
determining at least one mapping range of the stay point and the disconnection point;
and determining at least one target transition probability value based on the mapping range, the stay point, the stay time, the disconnection point and the disconnection time.
According to the vehicle accident identification method provided by the invention, the determining at least one target transition probability value based on the mapping range, the stay point, the stay time, the disconnection point and the disconnection time comprises the following steps:
acquiring at least one first pause point of which the stay time or the disconnection time of the vehicle to be detected under the mapping range exceeds a third threshold value;
determining a first time for transferring the vehicle to be detected at the first pause point under the mapping range;
determining a second number of times that the vehicle to be detected is transferred from the first pause point to the second pause point under the mapping range by taking the stop point or the disconnection point adjacent to the first pause point as the second pause point;
taking the ratio of the second times to the first times as a target transfer probability value of the vehicle to be detected at the first pause point;
at least one of the target transition probability values is determined based on the updated mapping range.
According to the vehicle accident identification method provided by the invention, the stay point or the disconnection point comprises longitude and latitude, and the determining at least one mapping range of the stay point and the disconnection point comprises the following steps:
Mapping the longitude and the latitude of the stay point or the disconnection point into a target character string with a specific bit number based on a preset longitude and latitude mapping rule; the target string represents a mapped range over a geographic location.
According to the vehicle accident identification method provided by the invention, the determining the transition probability threshold value corresponding to the target transition probability value comprises the following steps:
acquiring a first transfer probability value of a historical vehicle at a first pause point based on historical running track data of the historical vehicle;
determining a similar vehicle set of the vehicle to be detected, and acquiring a second transition probability value of the similar vehicle set at the first pause point based on historical running track data of the similar vehicle set;
and determining a fusion coefficient of the first transition probability value and the second transition probability value, and carrying out weighted summation on the first transition probability value and the second transition probability value based on the fusion coefficient to obtain the transition probability threshold.
According to the vehicle accident identification method provided by the invention, the determining the similar vehicle set of the vehicle to be detected comprises the following steps:
determining a first number of identical stay points or identical disconnection points of the vehicle to be detected and any historical vehicle under a mapping range;
Determining a second number of stay points or disconnection points of the vehicle to be detected in the mapping range;
determining a third number of stay points or drop points of any historical vehicle in the mapping range;
determining the similarity of any one of the historical vehicles and the vehicle to be detected based on the first quantity, the second quantity and the third quantity;
and taking the historical vehicles with the similarity larger than a fourth threshold value as the similar vehicle set.
According to the vehicle accident identification method provided by the invention, the accident position of the vehicle to be detected is determined based on the comparison result of the target transition probability value and the transition probability threshold value, and the method comprises the following steps:
and when the target transition probability values are smaller than the transition probability threshold value matched with the target transition probability values, determining a stay point or a disconnection point corresponding to the target transition probability values as the accident position.
In a second aspect, the present invention also provides a vehicle accident identification apparatus, including:
the target transition probability value determining module is used for determining at least one target transition probability value based on the running track data of the vehicle to be detected; the target transition probability value is the probability that the vehicle to be detected transits from a first pause point to a second pause point;
The transition probability threshold determining module is used for determining a transition probability threshold corresponding to the target transition probability value;
and the accident position determining module is used for determining the accident position of the vehicle to be detected based on the comparison result of the target transition probability value and the transition probability threshold value.
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 vehicle accident identification method as described in any one of the preceding claims when the program is executed by the processor.
In a fourth aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of a vehicle accident identification method as described in any one of the above.
According to the vehicle accident identification method, the device, the electronic equipment and the storage medium, at least one target transition probability value is determined based on the running track data of the vehicle to be detected; the target transition probability value is the probability that the vehicle to be detected transits from a first pause point to a second pause point; determining a transition probability threshold corresponding to the target transition probability value; and determining the accident position of the vehicle to be detected based on the comparison result of the target transition probability value and the transition probability threshold value. According to the embodiment of the invention, the target transition probability value and the transition probability threshold value are determined according to the running track data of the vehicle, so that the variety of data collection is simplified; based on the comparison result of the target transition probability value and the transition probability threshold value, the accident position of the vehicle to be detected is obtained, and the comprehensiveness and accuracy of vehicle accident judgment are improved.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a vehicle accident identification method provided by the invention;
FIG. 2 is a second flow chart of the vehicle accident recognition method according to the present invention;
fig. 3 is a schematic structural view of a vehicle accident recognition device provided by the present invention;
fig. 4 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that in the description of embodiments of the present invention, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. The orientation or positional relationship indicated by the terms "upper", "lower", etc. are based on the orientation or positional relationship shown in the drawings, are merely for convenience of description and to simplify the description, and are not indicative or implying that the apparatus or elements in question must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as limiting the present invention. Unless specifically stated or limited otherwise, the terms "mounted," "connected," and "coupled" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
The terms "first," "second," and the like in this specification are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged, as appropriate, such that embodiments of the present invention may be implemented in sequences other than those illustrated or described herein, and that the objects identified by "first," "second," etc. are generally of a type, and are not limited to the number of objects, such as the first object may be one or more. In addition, "and/or" indicates at least one of the connected objects, and the character "/", generally indicates that the associated object is an "or" relationship.
The following describes a vehicle accident recognition method and device provided by the embodiment of the invention with reference to fig. 1 to 4.
Fig. 1 is a schematic flow chart of a vehicle accident recognition method provided by the present invention, as shown in fig. 1, including but not limited to the following steps:
step 100: determining at least one target transition probability value based on the running track data of the vehicle to be detected;
it should be noted that, the execution main body of the task construction method provided by the embodiment of the present invention may be a server, a computer device, such as a mobile phone, a tablet computer, a notebook computer, a palm computer, a vehicle-mounted electronic device, a wearable device, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a netbook, a personal digital assistant (personal digital assistant, PDA), or the like.
The target transition probability value is the probability that the vehicle to be detected transitions from the first suspension point to the second suspension point.
The first pause point is a stop point of which the stop time length of the vehicle to be detected under a specific mapping range exceeds a third threshold value, or a disconnection point of which the disconnection time length exceeds the third threshold value. The second pause point is a stop point or a drop point adjacent to the first pause point. The dwell point is a continuous track point where the speed of the vehicle to be detected is less than a first threshold value. The disconnection point is a track point with a sampling interval of two times before and after being larger than a second threshold value when the vehicle to be detected is sampled.
As shown in fig. 2, the running track data of the vehicle to be detected is acquired, for example, the running track data of the vehicle to be detected 3 hours ago or one day ago is acquired. And sorting the running track data of the vehicle to be detected into a suspension matrix of the vehicle to be detected. The running track data of the vehicle to be detected is expressed as:
wherein,for the running track data of the vehicle to be detected, t ti Is t th i Time of subsampling, lng ti ，lat ti Is t th i Subsampled latitude and longitude points, v ti Is t th i Subsampled velocity values.
And determining the stop points and the disconnection points in the running track data, and further determining all the first stop points and the second stop points in the running track data. And calculating a target transition probability value of the vehicle to be detected from the first pause point to the second pause point according to the running track data.
Further, a mapping range is changed, and a plurality of target transition probability values are obtained.
Step 200: determining a transition probability threshold value corresponding to the target transition probability value;
the transition probability threshold characterizes a probability value of a transition from a first suspension point to a second suspension point when the vehicle is in normal operation.
A set of similar vehicles similar to the trajectory of the vehicle to be detected is determined. A first transition probability value of the historical vehicle is determined based on the travel track data of the historical vehicle. And determining a second transition probability value of the similar vehicle set according to the running track data of the similar vehicle set. And obtaining a transition probability threshold value in the normal running process of the vehicle to be detected based on the learning of the first transition probability value and the second transition probability value.
Further, the mapping range is changed, and a plurality of transition probability thresholds are obtained.
Step 300: and determining the accident position of the vehicle to be detected based on the comparison result of the target transition probability value and the transition probability threshold value.
And comparing the target transition probability value with a transition probability threshold value, and further determining whether the transition of the vehicle to be detected deviates from the driving of the normal vehicle. And when the stopping or the disconnection of the vehicle to be detected at the current first pause point is determined to be abnormal, the first pause point is the accident position of the vehicle to be detected.
According to the vehicle accident identification method provided by the embodiment of the invention, at least one target transition probability value is determined based on the running track data of the vehicle to be detected; the target transition probability value is the probability that the vehicle to be detected transits from the first pause point to the second pause point; determining a transition probability threshold value corresponding to the target transition probability value; and determining the accident position of the vehicle to be detected based on the comparison result of the target transition probability value and the transition probability threshold value. According to the embodiment of the invention, the target transition probability value and the transition probability threshold value are determined according to the running track data of the vehicle, so that the variety of data collection is simplified; based on the comparison result of the target transition probability value and the transition probability threshold value, the accident position of the vehicle to be detected is obtained, and the comprehensiveness and accuracy of vehicle accident judgment are improved.
Based on the above embodiment, determining at least one target transition probability value based on the running track data of the vehicle to be detected includes:
step 110: acquiring a stop point and a stop time length of a vehicle to be detected, the speed of which is smaller than a first threshold value, and a disconnection point and a disconnection time length of which the signal sampling time interval of the vehicle to be detected is larger than a second threshold value from the running track data;
Step 120: determining at least one mapping range of a stay point and a drop point;
step 130: and determining at least one target transfer probability value based on the mapping range, the stay point, the stay time, the disconnection point and the disconnection time.
According to the speed of each time point in the running track data, screening out continuous track points with the speed smaller than a first threshold (for example, the speed is smaller than 1 km/h) as primary stay points, and the expression formula of the stay points is as follows:
wherein,for the stop point of the vehicle to be detected, t si For the start time of the si-th stay, lng si ，lat si For the longitude and latitude point of the si-th stay, dt si The residence time of the first residence.
The calculation formula of the stay time of the first stay is as follows:
dt si ＝t tk -t tq ；
wherein dt is si For the residence time of the si-th residence, t tk For the end time of the si-th dwell, t tq Is the start time of the first stop.
Track points with the sampling interval of two times before and after being larger than a second threshold (for example, 1 hour) are screened out and used as one-time GPS disconnection points, and the expression formula of the disconnection points is as follows:
wherein,to be the disconnection point, t oi For the start time of the first dwell, lng oi ，lat oi For the longitude and latitude point of the oi stay, dt oi And the time length of the disconnection is the time length of the disconnection of the first time.
The calculation formula of the disconnection time length of the disconnection of the first time is as follows:
dt oi ＝t tv -t tp ；
Wherein dt is oi T is the time length of the disconnection of the oi time tv For the end time of the oi-th disconnection, t tp Is the start time of the first drop.
Integrating the stay point, the stay time, the disconnection point and the disconnection time to obtain the running track data of the vehicle to be detected, wherein the expression formula of the running track data is as follows:
wherein,for stay point->Is a drop point.
Expressing the running track data into a pause matrix, wherein the expression formula of the pause matrix is as follows:
wherein,longitude point, i.e. the SOi-th stop point or drop point, < >>Latitude point of stay point or drop point at SOi time, < >>For stay time or drop time.
As shown in fig. 2, at least one mapping range of stay points and drop points is determined. And determining the range of the stay point or the disconnection point on the geographic position based on the mapping range, wherein the mapping range can be selected according to the data condition in the actual operation process. According to the selected mapping rule, mapping the determined stay points and the drop points to geographic areas with different mapping ranges to obtain a mapped pause matrix, wherein the expression formula of the mapped pause matrix is as follows:
wherein,for the geohash mapping result under the K mapping range,>and (5) obtaining a geohash mapping result under the P mapping range.
And calculating a target transition probability value of the vehicle to be detected from the first pause point to the second pause point under the mapping range. And changing the mapping range to obtain at least one target transition probability value.
According to the embodiment of the invention, the stay point, the disconnection point, the stay time and the disconnection time of the vehicle to be detected are determined according to the running track data of the vehicle to be detected, so that the target transition probability value of the vehicle to be detected is obtained, the collection type of the original data is simplified, and the comprehensiveness and the accuracy of judging the vehicle accident are improved.
Based on the above embodiment, determining at least one target transition probability value based on the mapping range, the stay point, the stay time length, the drop point, and the drop time length includes:
step 131: acquiring at least one first pause point of which the stay time or the disconnection time of the vehicle to be detected exceeds a third threshold value in a mapping range;
step 132: determining the first times of transferring at a first pause point of a vehicle to be detected under a mapping range;
step 133: taking a stop point or a disconnection point adjacent to the first pause point as a second pause point, and determining a second number of times that the vehicle to be detected is transferred from the first pause point to the second pause point under the mapping range;
Step 134: taking the ratio of the second times to the first times as a target transfer probability value of the vehicle to be detected at the first pause point;
step 135: at least one target transition probability value is determined based on the updated mapping range.
And acquiring at least one pause point of which the stay time or the disconnection time of the vehicle to be detected in a specific mapping range (e.g. the mapping range K) exceeds a third threshold (e.g. th is equal to 0.5h or th is equal to 4 h) according to the mapped pause matrix of the vehicle to be detected. Determining the first times of transferring at a first pause point of a vehicle to be detected under a mapping range; taking a stop point or a disconnection point adjacent to the first pause point as a second pause point, and determining the second times of transferring the vehicle to be detected from the first pause point to the second pause point under the mapping range based on the historical running track data of the vehicle to be detected; taking the ratio of the second times to the first times as a target transfer probability value of the vehicle to be detected at the first pause point; the calculation formula of the target transition probability value is as follows:
wherein,in order to transfer the stay time length or the disconnection time length from the first pause point geoi to the target transfer probability value of stay of the second pause point geoj under the mapping range K; / >A second number of stops for the vehicle to be detected to transition from geoi to geoj under the mapping range K; />For the first number of transfers of the vehicle to be detected in geoi under the map range K.
Changing the mapping range, and redetermining the stay time and the disconnection time of the vehicle to be detectedAccording to the method, the target transfer probability value of the vehicle to be detected is recalculated, and then various target transfer probability values of the vehicle to be detected are obtained.
Adding the target transfer probability value of the vehicle to be detected into a pause matrix, wherein the pause matrix with the target transfer probability value is as follows:
wherein,for a target transition probability value for a vehicle transitioning from geo (ki) to geo (ki+1) with th1 as a third threshold value when the region accuracy is K; />To transfer the vehicle from geo (pi) to the target transfer probability value of geo (pi+1) with th2 as the third threshold value at the region accuracy P.
And->And (5) transferring probability values for different targets at the same first pause point. The stay time of the vehicle to be detected under the mapping range is equal to the sum of stay time of the vehicle to be detected in the stay range. The time length of the disconnection of the vehicle to be detected in the mapping range is equal to the sum of the time length of the disconnection of the vehicle to be detected in the disconnection range.
According to the embodiment of the invention, the first times and the second times of the vehicles to be detected are determined based on the adjacent two stay points or the adjacent drop points, so that the target transfer probability value is determined, the types of calculated data are simplified, and the accuracy of determining the target transfer probability value is improved. The embodiment of the invention focuses on judging whether the vehicle is in the normal running mode from the angle of position transition modes under different time windows, and judging that the vehicle is an accident/suspected accident if the vehicle deviates from the normal running mode.
Based on the above embodiment, the stay point or the drop point includes a longitude and a latitude, and determining at least one mapping range of the stay point and the drop point includes:
step 121: based on a preset longitude and latitude mapping rule, mapping longitudes and latitudes of stay points or drop points into target character strings with different digits; the target string represents a mapped range over the geographic location.
The latitude and longitude mapping rules include a geographic hash (geohash) map. The geohash mapping maps any longitude and latitude point into geohash character strings with different digits, wherein a specific character string represents a specific area, and the digits of the geohash character string represent the mapping area of the longitude and latitude point. For example, a 6-bit geohash string represents approximately a 0.4 square kilometer area. In the embodiment of the invention, the geohashK represents the geohash mapping of K bits. geohashP, a geohash map representing P bits.
According to a preset longitude and latitude mapping rule (for example, the longitude and latitude mapping rule is geohashK), mapping the longitude and latitude of a stay point or a drop point into a target character string with a specific bit number (for example, the specific bit number of the target character string of geohashK is K); the target string represents a mapped range over a geographic location and the particular string represents the area of the mapped range.
According to the embodiment of the invention, the stay point or the disconnection point is mapped to the geographic mapping range with the specific area through the preset latitude and longitude mapping rule, so that the accuracy of determining the stay point or the disconnection point is improved.
Based on the above embodiment, determining a transition probability threshold corresponding to the target transition probability value includes:
step 210: acquiring a first transfer probability value of the historical vehicle at a first pause point based on the historical running track data of the historical vehicle;
step 220: determining a similar vehicle set of the vehicle to be detected, and acquiring a second transition probability value of the similar vehicle set at a first pause point based on historical running track data of the similar vehicle set;
step 230: and determining a fusion coefficient of the first transition probability value and the second transition probability value, and carrying out weighted summation on the first transition probability value and the second transition probability value based on the fusion coefficient to obtain a transition probability threshold.
Based on the method, rootAccording to the historical running track data of the historical vehicle and the mapping rule, obtaining a pause matrix of the historical vehicle in a specific mapping range (x), and further determining a first transition probability value for transitioning from a first pause point (geoi) to a second pause point (geoj) when the stay time or the disconnection time of the historical vehicle is greater than a third threshold (th)
Based on the method, according to the historical running track data and the mapping rule of the similar vehicle set, obtaining a pause matrix of the similar vehicle set in a specific mapping range (x), and further determining a first transition probability value for transitioning from a first pause point (geoi) to a second pause point (geoj) when the stay time or the disconnection time of the similar vehicle set is greater than a third threshold (th)
And determining a fusion coefficient of the first transition probability value and the second transition probability value, and carrying out weighted summation on the first transition probability value and the second transition probability value based on the fusion coefficient to obtain a transition probability threshold. The calculation formula of the transition probability threshold value is as follows:
wherein,a second transition probability value for a similar vehicle set at the first pause point, alpha being a fusion coefficient,/->For a first transition probability value of the history vehicle at a first pause point, < >>Is a transition probability threshold.
And changing the mapping range to obtain transition probability thresholds of different types.
Alternatively, a variety of transition probability thresholds are empirically set.
According to the embodiment of the invention, the first transition probability value of the historical vehicle and the second transition probability value of the similar vehicle set are weighted and summed to obtain the transition probability threshold, so that the transition probability threshold can be determined according to the actual condition of the vehicle to be detected, and the accuracy of determining the transition probability threshold is improved. The embodiment of the invention learns the normal mode of vehicle operation by mining the accumulated track data of the total quantity of vehicles, and provides a basis for identifying vehicle accidents.
Based on the above embodiment, determining a set of similar vehicles of the vehicles to be detected includes:
step 221: determining the first number of identical stay points or identical disconnection points of the vehicle to be detected and any historical vehicle in a mapping range;
step 222: determining a second number of stay points or disconnection points of the vehicle to be detected in the mapping range;
step 223: determining a third number of stay points or drop points of any historical vehicle in the mapping range;
step 224: determining the similarity of any historical vehicle and the vehicle to be detected based on the first quantity, the second quantity and the third quantity;
step 225: and taking the historical vehicles with the similarity larger than the fourth threshold value as a similar vehicle set.
In order to fully embody the individuation rule of the stay/drop mode of the vehicle to be detected, a similar vehicle set of the vehicle to be detected is determined to acquire a second transition probability value of the similar vehicle set at the first pause point.
The similarity between the historical vehicle and the vehicle to be detected is determined, and the calculation formula of the similarity is as follows:
wherein,the similarity between the historical vehicle i and the vehicle j to be detected is obtained; />For a third number of stay points or drop points of the history vehicle i under the map range, +. >For a second number of stop points or drop points of the vehicle j to be detected in the map range,/-, for example>For a first number of identical stay points or identical drop points of the vehicle j to be detected and the history vehicle i under the mapping range.
And taking the historical vehicles with the similarity larger than the fourth threshold value as a similar vehicle set.
According to the method and the device for determining the similarity between the historical vehicle and the vehicle to be detected, the similarity between the historical vehicle and the vehicle to be detected is determined according to the number of the stay points or the disconnection points in the running tracks of the historical vehicle and the vehicle to be detected, and then the similar vehicle set is determined, so that accuracy of determining the similar vehicle set is improved.
Based on the above embodiment, determining the accident position of the vehicle to be detected based on the comparison result of the target transition probability value and the transition probability threshold value includes:
and when the target transition probability values are smaller than the transition probability threshold value matched with the target transition probability values, determining the stay points or the disconnection points corresponding to the target transition probability values as accident positions.
And comparing each target transition probability value with a transition probability threshold matched with the target transition probability value. When all of the target transition probability values (e.g.,and->) Determining the destination when the transition probability thresholds are smaller than the transition probability threshold matched with the transition probability thresholdsAnd marking the stay point or the disconnection point corresponding to the transition probability value as the accident position, thereby obtaining the accident time.
According to the embodiment of the invention, the stay points or the disconnection points corresponding to the transition probability threshold values which are matched with the target transition probability values are used as the accident positions, so that the accuracy of determining the accident positions is improved.
The embodiment of the invention also provides a vehicle accident identification device, as shown in fig. 3, and fig. 3 is a schematic structural diagram of the vehicle accident identification device. It should be noted that, in the vehicle accident identification apparatus provided in the embodiment of the present invention, the vehicle accident identification method described in any one of the above embodiments may be executed during specific operation, and this embodiment will not be described in detail.
Referring to fig. 3, an embodiment of the present invention provides a vehicle accident recognition apparatus including:
a target transition probability value determining module 301, configured to determine at least one target transition probability value based on the running track data of the vehicle to be detected; the target transition probability value is the probability that the vehicle to be detected transits from the first pause point to the second pause point;
a transition probability threshold determining module 302, configured to determine a transition probability threshold corresponding to the target transition probability value;
the accident position determining module 303 is configured to determine an accident position of the vehicle to be detected based on a comparison result of the target transition probability value and the transition probability threshold value.
The vehicle accident identification device provided by the embodiment of the invention determines at least one target transition probability value based on the running track data of the vehicle to be detected; the target transition probability value is the probability that the vehicle to be detected transits from the first pause point to the second pause point; determining a transition probability threshold value corresponding to the target transition probability value; and determining the accident position of the vehicle to be detected based on the comparison result of the target transition probability value and the transition probability threshold value. According to the embodiment of the invention, the target transition probability value and the transition probability threshold value are determined according to the running track data of the vehicle, so that the variety of data collection is simplified; based on the comparison result of the target transition probability value and the transition probability threshold value, the accident position of the vehicle to be detected is obtained, and the comprehensiveness and accuracy of vehicle accident judgment are improved.
In one embodiment, the target-transition-probability-value determining module 301 is configured to: acquiring a stop point and a stop time length of a vehicle to be detected, the speed of which is smaller than a first threshold value, and a disconnection point and a disconnection time length of which the signal sampling time interval of the vehicle to be detected is larger than a second threshold value from the running track data; determining at least one mapping range of a stay point and a drop point; and determining at least one target transfer probability value based on the mapping range, the stay point, the stay time, the disconnection point and the disconnection time.
In one embodiment, the target-transition-probability-value determining module 301 is configured to: acquiring at least one first pause point of which the stay time or the disconnection time of the vehicle to be detected exceeds a third threshold value in a mapping range; determining the first times of transferring at a first pause point of a vehicle to be detected under a mapping range; taking a stop point or a disconnection point adjacent to the first pause point as a second pause point, and determining a second number of times that the vehicle to be detected is transferred from the first pause point to the second pause point under the mapping range; taking the ratio of the second times to the first times as a target transfer probability value of the vehicle to be detected at the first pause point; at least one target transition probability value is determined based on the updated mapping range.
In one embodiment, the target-transition-probability-value determining module 301 is configured to: based on a preset longitude and latitude mapping rule, mapping longitudes and latitudes of stay points or drop points into target character strings with specific digits; the target string represents a mapped range over the geographic location.
In one embodiment, the transition probability threshold determination module 302 is configured to: acquiring a first transfer probability value of the historical vehicle at a first pause point based on the historical running track data of the historical vehicle; determining a similar vehicle set of the vehicle to be detected, and acquiring a second transition probability value of the similar vehicle set at a first pause point based on historical running track data of the similar vehicle set; and determining a fusion coefficient of the first transition probability value and the second transition probability value, and carrying out weighted summation on the first transition probability value and the second transition probability value based on the fusion coefficient to obtain a transition probability threshold.
In one embodiment, the transition probability threshold determination module 302 is configured to: determining the first number of identical stay points or identical disconnection points of the vehicle to be detected and any historical vehicle in a mapping range; determining a second number of stay points or disconnection points of the vehicle to be detected in the mapping range; determining a third number of stay points or drop points of any historical vehicle in the mapping range; determining the similarity of any historical vehicle and the vehicle to be detected based on the first quantity, the second quantity and the third quantity; and taking the historical vehicles with the similarity larger than the fourth threshold value as a similar vehicle set.
In one embodiment, the accident location determination module 303 is configured to: and when the target transition probability values are smaller than the transition probability threshold value matched with the target transition probability values, determining the stay points or the disconnection points corresponding to the target transition probability values as accident positions.
Fig. 4 is a schematic structural diagram of an electronic device according to the present invention, as shown in fig. 4, the electronic device may include: processor 410, communication interface (Communications Interface) 420, memory 430 and communication bus 440, wherein processor 410, communication interface 420 and memory 430 communicate with each other via communication bus 440. The processor 410 may invoke logic instructions in the memory 430 to perform a vehicle accident identification method comprising:
Determining at least one target transition probability value based on the running track data of the vehicle to be detected; the target transition probability value is the probability that the vehicle to be detected transits from the first pause point to the second pause point; determining a transition probability threshold value corresponding to the target transition probability value; and determining the accident position of the vehicle to be detected based on the comparison result of the target transition probability value and the transition probability threshold value.
Further, the logic instructions in the memory 430 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, are capable of performing the vehicle accident identification method provided by the above embodiments, the method comprising:
determining at least one target transition probability value based on the running track data of the vehicle to be detected; the target transition probability value is the probability that the vehicle to be detected transits from the first pause point to the second pause point; determining a transition probability threshold value corresponding to the target transition probability value; and determining the accident position of the vehicle to be detected based on the comparison result of the target transition probability value and the transition probability threshold value.
In yet another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the vehicle accident identification method provided by the above embodiments, the method comprising:
determining at least one target transition probability value based on the running track data of the vehicle to be detected; the target transition probability value is the probability that the vehicle to be detected transits from the first pause point to the second pause point; determining a transition probability threshold value corresponding to the target transition probability value; and determining the accident position of the vehicle to be detected based on the comparison result of the target transition probability value and the transition probability threshold value.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A vehicle accident identification method, characterized by comprising:
determining at least one target transition probability value based on the running track data of the vehicle to be detected; the target transition probability value is the probability that the vehicle to be detected transits from a first pause point to a second pause point;
determining a transition probability threshold corresponding to the target transition probability value;
and determining the accident position of the vehicle to be detected based on the comparison result of the target transition probability value and the transition probability threshold value.
2. The vehicle accident identification method according to claim 1, wherein the determining at least one target transition probability value based on the running track data of the vehicle to be detected includes:
Acquiring a stay point and a stay time length of the vehicle to be detected, wherein the speed of the vehicle to be detected is smaller than a first threshold value, and a disconnection point and a disconnection time length of the vehicle to be detected, wherein the signal sampling time interval of the vehicle to be detected is larger than a second threshold value;
determining at least one mapping range of the stay point and the disconnection point;
and determining at least one target transition probability value based on the mapping range, the stay point, the stay time, the disconnection point and the disconnection time.
3. The vehicle accident identification method according to claim 2, wherein the determining at least one of the target transition probability values based on the map range, the stay point, the stay period, the drop point, and the drop period includes:
acquiring at least one first pause point of which the stay time or the disconnection time of the vehicle to be detected under the mapping range exceeds a third threshold value;
determining a first time for transferring the vehicle to be detected at the first pause point under the mapping range;
determining a second number of times that the vehicle to be detected is transferred from the first pause point to the second pause point under the mapping range by taking the stop point or the disconnection point adjacent to the first pause point as the second pause point;
Taking the ratio of the second times to the first times as a target transfer probability value of the vehicle to be detected at the first pause point;
at least one of the target transition probability values is determined based on the updated mapping range.
4. The vehicle accident identification method according to claim 2, wherein the stay point or the drop point includes a longitude and a latitude, and the determining at least one mapping range of the stay point and the drop point includes:
mapping the longitude and the latitude of the stay point or the disconnection point into a target character string with a specific bit number based on a preset longitude and latitude mapping rule; the target string represents a mapped range over a geographic location.
5. The vehicle accident identification method according to claim 1, wherein the determining the transition probability threshold value to which the target transition probability value corresponds includes:
acquiring a first transfer probability value of a historical vehicle at a first pause point based on historical running track data of the historical vehicle;
determining a similar vehicle set of the vehicle to be detected, and acquiring a second transition probability value of the similar vehicle set at the first pause point based on historical running track data of the similar vehicle set;
And determining a fusion coefficient of the first transition probability value and the second transition probability value, and carrying out weighted summation on the first transition probability value and the second transition probability value based on the fusion coefficient to obtain the transition probability threshold.
6. The vehicle accident identification method of claim 5, wherein the determining the set of similar vehicles for the vehicle to be detected comprises:
determining a first number of identical stay points or identical disconnection points of the vehicle to be detected and any historical vehicle under a mapping range;
determining a second number of stay points or disconnection points of the vehicle to be detected in the mapping range;
determining a third number of stay points or drop points of any historical vehicle in the mapping range;
determining the similarity of any one of the historical vehicles and the vehicle to be detected based on the first quantity, the second quantity and the third quantity;
and taking the historical vehicles with the similarity larger than a fourth threshold value as the similar vehicle set.
7. The vehicle accident identification method according to claim 1, wherein the determining the accident position of the vehicle to be detected based on the comparison result of the target transition probability value and the transition probability threshold value includes:
And when the target transition probability values are smaller than the transition probability threshold value matched with the target transition probability values, determining a stay point or a disconnection point corresponding to the target transition probability values as the accident position.
8. A vehicle accident recognition apparatus, characterized by comprising:
the target transition probability value determining module is used for determining at least one target transition probability value based on the running track data of the vehicle to be detected; the target transition probability value is the probability that the vehicle to be detected transits from a first pause point to a second pause point;
the transition probability threshold determining module is used for determining a transition probability threshold corresponding to the target transition probability value;
and the accident position determining module is used for determining the accident position of the vehicle to be detected based on the comparison result of the target transition probability value and the transition probability threshold value.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the vehicle accident identification method according to any one of claims 1 to 7 when the computer program is executed.
10. A non-transitory computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when executed by a processor, implements the steps of the vehicle accident identification method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311393170.6A CN117635010B (en) | 2023-10-25 | 2023-10-25 | Vehicle accident identification method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311393170.6A CN117635010B (en) | 2023-10-25 | 2023-10-25 | Vehicle accident identification method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117635010A true CN117635010A (en) | 2024-03-01 |
| CN117635010B CN117635010B (en) | 2024-07-30 |
Family
ID=90026032
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311393170.6A Active CN117635010B (en) | 2023-10-25 | 2023-10-25 | Vehicle accident identification method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117635010B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010108168A (en) * | 2008-10-29 | 2010-05-13 | Toyota Motor Corp | Collision prediction device |
| JP2015072650A (en) * | 2013-10-04 | 2015-04-16 | 株式会社デンソーアイティーラボラトリ | Route calculation device, vehicle control device, vehicle driving support device, vehicle, route calculation program, and route calculation method |
| CN108182801A (en) * | 2017-12-21 | 2018-06-19 | 北京中交兴路信源科技有限公司 | A kind of dwell point real-time detection method and system based on track of vehicle |
| US20190095809A1 (en) * | 2017-09-26 | 2019-03-28 | Samsung Electronics Co., Ltd. | Vehicle movement prediction method and apparatus |
| US20210044930A1 (en) * | 2019-08-07 | 2021-02-11 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method, apparatus, computer device and storage medium for stay point recognition |
| US20210236024A1 (en) * | 2018-04-27 | 2021-08-05 | Caroline BONO | System for capturing person-related accident data in a vehicle |
| JP2021160714A (en) * | 2020-03-30 | 2021-10-11 | 本田技研工業株式会社 | Vehicle control device and vehicle control method |
| CN113581101A (en) * | 2021-08-31 | 2021-11-02 | 三一专用汽车有限责任公司 | Engineering vehicle accident detection processing method and device |
| CN114519255A (en) * | 2022-01-11 | 2022-05-20 | 深圳技术大学 | Vehicle track prediction method, device and storage medium |
| CN115436972A (en) * | 2022-08-31 | 2022-12-06 | 湖南省交通科学研究院有限公司 | Method, system and medium for identifying stop point based on heavy-duty truck GPS track |
| US20230164513A1 (en) * | 2021-06-04 | 2023-05-25 | Here Global B.V. | Method, apparatus, and computer program product for anonymizing trajectories and stay points |
| CN116434529A (en) * | 2022-12-12 | 2023-07-14 | 交通运输部规划研究院 | Inter-city highway freight characteristic analysis method and device and electronic equipment |
-
2023
- 2023-10-25 CN CN202311393170.6A patent/CN117635010B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010108168A (en) * | 2008-10-29 | 2010-05-13 | Toyota Motor Corp | Collision prediction device |
| JP2015072650A (en) * | 2013-10-04 | 2015-04-16 | 株式会社デンソーアイティーラボラトリ | Route calculation device, vehicle control device, vehicle driving support device, vehicle, route calculation program, and route calculation method |
| US20190095809A1 (en) * | 2017-09-26 | 2019-03-28 | Samsung Electronics Co., Ltd. | Vehicle movement prediction method and apparatus |
| CN108182801A (en) * | 2017-12-21 | 2018-06-19 | 北京中交兴路信源科技有限公司 | A kind of dwell point real-time detection method and system based on track of vehicle |
| US20210236024A1 (en) * | 2018-04-27 | 2021-08-05 | Caroline BONO | System for capturing person-related accident data in a vehicle |
| US20210044930A1 (en) * | 2019-08-07 | 2021-02-11 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method, apparatus, computer device and storage medium for stay point recognition |
| JP2021160714A (en) * | 2020-03-30 | 2021-10-11 | 本田技研工業株式会社 | Vehicle control device and vehicle control method |
| US20230164513A1 (en) * | 2021-06-04 | 2023-05-25 | Here Global B.V. | Method, apparatus, and computer program product for anonymizing trajectories and stay points |
| CN113581101A (en) * | 2021-08-31 | 2021-11-02 | 三一专用汽车有限责任公司 | Engineering vehicle accident detection processing method and device |
| CN114519255A (en) * | 2022-01-11 | 2022-05-20 | 深圳技术大学 | Vehicle track prediction method, device and storage medium |
| CN115436972A (en) * | 2022-08-31 | 2022-12-06 | 湖南省交通科学研究院有限公司 | Method, system and medium for identifying stop point based on heavy-duty truck GPS track |
| CN116434529A (en) * | 2022-12-12 | 2023-07-14 | 交通运输部规划研究院 | Inter-city highway freight characteristic analysis method and device and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 张国政;王梦;朱群;: "复杂道路场景下的车辆碰撞特征检测分析", 软件, no. 08, 15 August 2020 (2020-08-15) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117635010B (en) | 2024-07-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10728708B2 (en) | Verifying sensor data using embeddings | |
| US11664043B2 (en) | Real-time verbal harassment detection system | |
| EP2260458B1 (en) | Learning transportation modes from raw gps data | |
| CN108319909B (en) | Driving behavior analysis method and system | |
| CN111415533B (en) | Bend safety early warning monitoring method, device and system | |
| CN115050214B (en) | AIS data-based ship collision risk prediction method | |
| CN108120991A (en) | A kind of wheelpath optimization method | |
| CN116108397B (en) | Electric power field operation violation identification method integrating multi-mode data analysis | |
| CN115410420B (en) | Ship safe navigation management method and system | |
| CN111435088A (en) | Road matching method and device, electronic equipment and storage medium | |
| CN111829548A (en) | Dangerous road segment detection method and device, readable storage medium and electronic equipment | |
| CN117133099A (en) | Automatic monitoring system for disaster of expressway high slope | |
| CN112633557A (en) | Road safety early warning method and device based on big data, electronic equipment and storage medium | |
| CN115880928A (en) | Real-time updating method, device and equipment for automatic driving high-precision map and storage medium | |
| CN116150618A (en) | Fishing boat operation type identification method based on deep learning neural network | |
| CN113870620B (en) | Ship identification method for simultaneously opening multiple AIS devices | |
| CN112926630B (en) | Route planning method, route planning device, electronic equipment and computer readable medium | |
| CN117635010B (en) | Vehicle accident identification method and device, electronic equipment and storage medium | |
| KR20180058090A (en) | Service and System for downloading learned data of road condition and obstructions associated to the route in real time | |
| CN110647877B (en) | Three-dimensional traffic facility positioning and deviation rectifying method and device based on neural network | |
| Bonham et al. | Analysing port and shipping operations using big data | |
| Das et al. | Why slammed the brakes on? auto-annotating driving behaviors from adaptive causal modeling | |
| CN111832365A (en) | Lane mark determination method and device | |
| CN113793031B (en) | Submarine pipeline risk prediction method and device | |
| CN105118289A (en) | Traffic situation assessment method |
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 |