TW202008322A - Behavior analysis system and method of vehicle - Google Patents

Abstract

A behavior analysis system and method of vehicle are provided. In the method, eTag information of vehicles is detected on lanes, and images including license plates are captured. Identification information detected on lanes at multiple time intervals is obtained. For each time interval, the detected eTag information and license plates on the same lance are paired, to generate multiple pair combination, where each pair combination records all detected eTag information and license plates on the same lance within a certain time interval. The pair combinations at different time intervals are compared, to determine whether the identification information is conformed to an identification modification behavior. Accordingly, functions of automatic vehicle identification recognition and behavior analysis are provided.

Description

Vehicle behavior analysis system and method

The invention relates to a vehicle identification and analysis technology, and in particular to a vehicle behavior analysis system and method.

Since the cancellation of national toll collection, the eTag (or Radio Frequency Identification (RFID)) mounting rate on vehicles has been quite high. According to statistics from the Ministry of Transport, more than 80% of vehicles have eTags installed. On the other hand, since the law requires vehicles to mount license plates before they are allowed to go on the road, normal users will install license plates on their vehicles. However, there are still some users who fail to abide by traffic laws and normally hang legal license plates or change license plates. License plates and eTags are important identification information used to identify vehicles, but eTags and license plates are personal data and are protected by personal laws. Unless there is a necessary reason, you cannot directly query the user's license plate through eTag. In addition, at present, the way to inquire about some abnormal behaviors (for example, changing license plates by yourself, forging license plates, etc.) is usually that the traffic police first discover the abnormal behavior of passers-by (for example, racing, refitting, speeding and other violations of traffic rules ), and then connect to the database of the supervisory authority through the handheld device to know whether the query vehicle has abnormal behavior. In other words, the existing vehicle identification information query methods are all manual, and there is no automated mechanism.

In view of this, the present invention provides a vehicle behavior analysis system and method, which provides an automatic dual recognition mechanism and judges the recognition change behavior based on the information obtained by the recognition.

In the vehicle behavior analysis system of the present invention, the identification information of each vehicle includes eTag and license plate. The behavior analysis system includes a front-end identification system and a back-end identification system. The front-end identification system shoots at one or more lanes of a road segment, and includes an eTag reader and an image capture unit. The eTag reader detects the eTag information of the passing vehicle through the connected eTag antenna, and each eTag antenna corresponds to a lane. Each image capturing unit corresponds to one lane, and captures images including license plates of traveling vehicles. The back-end identification system obtains identification information of the vehicles detected in those lanes in several time intervals. For each time interval, the back-end identification system pairs the eTag information detected on the same lane with the license plate detected on the same lane to generate multiple sets of pairing combinations. Each pairing combination records all detected eTag information and license plates on the same lane within a certain time interval. The back-end identification system compares the pairing combinations of different time intervals to determine whether the identification information of each vehicle conforms to the identification change behavior, and this identification change behavior is that the pairing combinations of different time intervals do not match.

In the vehicle behavior analysis method of the present invention, the identification information of each vehicle includes eTag and license plate. And this behavior analysis method includes the following steps. Detect eTag information of vehicles passing by one or more lanes. Capture images of license plates including passing vehicles. Obtain the identification information of the vehicles detected in those lanes in several time intervals. For each time interval, the eTag information detected on the same lane is paired with the license plate detected on the same lane to generate multiple sets of pairing combinations. Each pairing combination records all detected eTag information and license plates on the same lane within a certain time interval. The pairing combinations in different time intervals are compared to determine whether the identification information of each vehicle conforms to the recognition change behavior, and this recognition change behavior is that the pairing combinations in different time intervals do not match.

Based on the above, the vehicle behavior analysis system and method of the embodiments of the present invention are based on the pairing of eTag and license plate identification, through a large number of combinations of license plates and eTag, a set of learning mechanisms is generated, and the user's behavior is automatically judged based on this So that the behavior judgment result can be used as a reference basis for the supervision station, traffic brigade, or criminal police team.

In order to make the above-mentioned features and advantages of the present invention more obvious and understandable, the embodiments are specifically described below in conjunction with the accompanying drawings for detailed description as follows.

FIG. 1 is a block diagram of components of a behavior analysis system 1 according to an embodiment of the invention. Referring to FIG. 1, the behavior analysis system 1 includes a front-end identification system 10 and a back-end identification system 50.

The front-end identification system 10 includes at least, but not limited to, a communication transceiver 11, one or more eTag antennas 13, one or more eTag readers 14, an image recognition device 15, and a processor 19.

The communication transceiver 11 can be a third-generation (3G), fourth-generation (4G) or later generation mobile communication, Ethernet or optical fiber modem or other network access device to communicate with the outside world communication.

The eTag (or RFID) reader 14 detects the eTag information of the passing vehicle through the connected eTag antenna 13, and each eTag antenna 13 corresponds to a lane.

The image recognition device 15 includes one or several image capture units 151 and a license plate recognition module 153. Each image capturing unit 151 includes elements such as a lens and an image sensor, and is, for example, a camera, a camera, and other devices, and is used to capture an image of a lane. The license plate recognition module 153 may be an image recognition chip, a processor or a circuit, and is used to recognize the license plate in the image.

The processor 19 is coupled to the communication transceiver 11, the eTag reader 14, and the image recognition device 15. The processor 19 may be a central processing unit (CPU), a microcontroller, a programmable controller, or a special application integrated circuit ( Application Specific Integrated Circuit (ASIC) or other similar elements or a combination of the above elements.

Please refer to FIG. 2, which is a schematic diagram of a front-end recognition system 1 according to an embodiment of the present invention. The front-end identification system 1 is installed on a certain road section. This section includes lanes L1, L2, the eTag antenna 13a and the image capturing unit 151a correspond to the lane L1, and the eTag antenna 13b and the image capturing unit 151b correspond to the lane L2. That is, vehicle identification information (including eTag information and license plate) passing through the lane L1 can be detected by the eTag antenna 13a and the image capturing unit 151a, and vehicle identification information passing through the lane L2 can be captured by the eTag antenna 13b and the image Unit 151b detects. It should be noted that, as shown in FIG. 2, the installation position and number of each component and lane can be adjusted according to requirements, and the embodiment of the present invention is not limited.

It is worth noting that the reading range of the eTag antennas 13a, 13b is different from the image capturing unit 151 and generally forms a fan-shaped reading range. In most multi-lane application scenarios, the eTag antenna 13 may read the eTag of adjacent lanes or vehicles in front and behind, and the pairing error rate may be greatly increased. However, the embodiment of the present invention will improve the pairing success rate through a large amount of data analysis, to be detailed in subsequent embodiments.

The back-end identification system 50 includes at least but not limited to the communication transceiver 51, the storage 57 and the processor 59. The back-end identification system 50 may be a desktop computer, a server, or a workstation.

The communication transceiver 51 may be 3G, 4G or later generation mobile communication, Ethernet or optical fiber modem or other network access device to communicate with the outside world.

The memory 57 can be any type of fixed or removable random access memory (Radom Access Memory, RAM), read only memory (Read Only Memory, ROM), flash memory (flash memory), traditional hard drive (hard disk drive, HDD), solid-state drive (SSD) or similar components, and used to record code, software modules (for example, license plate recognition module 571, behavior analysis module 573, etc.), trust The database 575, the training database 577, images, pairing combinations, and other data or files will be described in detail in subsequent embodiments.

The processor 59 is coupled to the communication transceiver 51 and the memory 57. The processor 59 may be a CPU, a microcontroller, a programmable controller, an ASIC, or other similar components or a combination of the foregoing components.

In order to facilitate the understanding of the operation process of the embodiments of the present invention, a number of embodiments will be given below to describe in detail the collection, training and analysis processes for vehicle identification in the embodiments of the present invention. Hereinafter, the methods described in the embodiments of the present invention will be described with various devices, components, and modules in the behavior analysis system 1. The various processes of the method can be adjusted according to the implementation situation, and it is not limited to this.

FIG. 3 is a flowchart of a behavior analysis method-training phase according to an embodiment of the invention. Referring to FIG. 3, the eTag reader 14 of the front-end identification system 1 detects eTag information of one or several lane passing vehicles through the eTag antenna 13 corresponding to each lane, and each image capturing unit 151 captures including passing vehicles To obtain the identification information of the vehicles detected in those lanes within several time intervals (for example, 0.5, 1, 2 seconds, etc.), so as to collect the identification information of the vehicles (step S310). These time intervals can be set to be the same or adjusted according to demand. That is to say, the front-end identification system 1 can obtain the eTag information and license plate image detected by a certain road segment at each set time interval.

Next, the license plate recognition module 153 in the front-end recognition system 1 recognizes the license plate image (step S330). The license plate recognition module 153 uses, for example, a hardware recognition mechanism to recognize the license plate (ie, license plate number) in the image, that is, the license plate recognition module 153 is a special chip or processing circuit designed for license plate recognition.

It is worth noting that the license plate recognition module 153 is the first built-in hardware license plate recognition, which features a faster recognition speed. However, due to weather, lights, license plate defects and other factors, it will inevitably cause misunderstandings. Therefore, when the first license plate recognition module 153 detects the vehicle, it will first perform the first heavy license plate recognition to obtain the front-end license plate recognition result. The processor 19 transmits the front-end license plate recognition result, the image including the license plate (ie, the image captured by the image capture unit 151), and the detected eTag information to the back-end recognition system 50 through the communication transceiver 11.

The processor 59 of the back-end identification system 50 can obtain the identification information of the vehicle detected by the front-end identification system 10 on the lane within several time intervals through the communication transceiver 51, and the license plate recognition module 571 performs the second pass on the license plate image License plate recognition (step S350). The license plate recognition module 571 uses, for example, software detection (eg, AdaBoost algorithm, Principal Component Analysis (PCA), Independent Component Analysis (ICA), artificial intelligence (AI) classifier, etc.). Filter unreasonable data (for example, the license plate is cut, the photo is obviously unable to judge, etc.), and then the result of the rear-end license plate recognition is obtained. The license plate recognition module 571 can also increase the accuracy of judgment through software self-learning (for example, machine learning).

The license plate recognition module 571 compares the rear-end license plate recognition result with the previous license plate recognition result corresponding to the same license plate image to determine whether the two results are consistent (step S370). When the two license plate recognitions in steps S330 and S350 are the same license plate (that is, the license plate numbers are the same), the license plate recognition module 571 determines that the front-end and back-end license plate recognition results are correct and reasonable.

For these license plate recognition results that are judged to be correct and reasonable (consistent), the processor 59 will perform cross-comparison with the eTag information (step S390) to form paired combinations, so as to store these paired combinations in the training database 577. In this embodiment, for each time interval, the processor 59 pairs the eTag information detected on the same lane with the license plate detected on the same lane to generate multiple sets of pairing combinations. For example, for the case of multiple lanes, the processor 59 needs to first calibrate the time of the license plate recognition modules 153, 571 and the eTag reader 14 and confirm that the time is consistent (ie, the eTag reader 14 reads eTag information The time interval is the same as the corresponding time interval of the images recognized by the license plate recognition modules 153 and 571), and pairing starts. The front-end and back-end identification systems 10, 50 first collect identification data for a period of time as a basis for pairing. This stage is called the "training stage". The processor 59 pairs the license plate recognition result of the same lane in the same time interval (for example, the same second) with the eTag information detected in the same lane in the same time interval (for example, the same second). In other words, each pairing combination records all detected eTag information and license plates on the same lane in a certain time interval. Since the reading range of the eTag antenna 13 may involve more than two lanes, a single license plate may correspond to multiple eTag information. The processor 59 writes all possible pairing combinations into a "training table" and records the time interval of the pairing at the same time, and records them in the training database 577.

)(即，統計時間間距，用於挑選部分時間區間的配對組合)，並初始化時序編號n 為0(步驟S410)。處理器59接著對訓練資料庫577中的配對組合以特定統計時間(例如，一個月、三個月或半年等)進行統計。當收集資料量足夠時(例如，一個月、或半年以上之車輛配對組合)，舉例來說，若將每30分鐘設定為一個時段(即，一個統計時間區間)，則處理器59可將每日分為48個時段(即，48個統計時間區間)。處理器59將透過計算公式(1)來判斷是否寫入信賴資料庫575： |Di × Wi| ＜ T …(1) Di為第一與第二時間區間的時間差，此第一時間區間(t=t_n )對應最近(新)一次的配對組合，而第二時間區間對應第一時間區間之前上一次相同配對組合；Wi為權重(weight)；T為門檻值(Threshold)。換句而言，處理器59是將此時間差Di進行加權運算(步驟S450)，並判斷時間差的加權運算結果是否小於門檻值T(步驟S470)。若此加權運算結果小於門檻值T，則處理器59將此時間區間對應的配對組合輸入(記錄)到信賴資料庫575(步驟S480)。反之，若此加權運算結果未小於門檻值T，則處理器59會調整統計時間區間(觀察時間寬度

)(返回步驟S410)。需注意的是，門檻值T可因應實務設定之參數而調整。Next, please refer to FIG. 3 is a flowchart of the behavior analysis method-comparison phase according to an embodiment of the present invention. The processor 59 initializes the relevant parameters of the vehicle behavior (for example, starting time, starting position, multi-lane road segment, time to date, time to point location, etc.), and sets the time width for observation of the active state (

) (That is, the statistical time interval is used to select a paired combination of partial time intervals), and the timing number n is initialized to 0 (step S410). The processor 59 then counts the pairing combinations in the training database 577 at a specific statistical time (for example, one month, three months, or half a year, etc.). When the amount of collected data is sufficient (for example, a vehicle pairing combination of one month or more than half a year), for example, if every 30 minutes is set as a period (ie, a statistical time interval), the processor 59 may The day is divided into 48 time periods (ie, 48 statistical time intervals). The processor 59 will determine whether to write to the trust database 575 through the calculation formula (1): |Di × Wi| <T… (1) Di is the time difference between the first and second time intervals, this first time interval (t =t _n ) corresponds to the most recent (new) pairing combination, and the second time interval corresponds to the same pairing combination last time before the first time interval; Wi is the weight; T is the threshold (Threshold). In other words, the processor 59 performs a weighted operation on the time difference Di (step S450), and determines whether the weighted operation result of the time difference is smaller than the threshold value T (step S470). If the weighted operation result is less than the threshold value T, the processor 59 inputs (records) the matching combination corresponding to the time interval to the trust database 575 (step S480). Conversely, if the weighted operation result is not less than the threshold T, the processor 59 will adjust the statistical time interval (observation time width

) (Return to step S410). It should be noted that the threshold T can be adjusted according to the parameters set in practice.

Next, the behavior analysis module 573 automates the matching process of the pairing combinations recorded in the trust database 575 (step S). In this embodiment, the behavior analysis module 573 can compare the paired combinations of different time intervals within the width of a specific observation interval (for example, through SQL program syntax) to determine whether the identification information of each vehicle conforms to the recognition change behavior ( Step S490).

The identification change behavior is that the pairing combinations in different time intervals do not match. For example, assume that the time interval t2 is after the time interval t1 (that is, the time interval t2 is later than the time interval t1), and the license plate is P _i (i is a positive integer), and the eTag information is E _j (j is a positive integer). If one of the pairing combinations in the statistical time interval has one eTag information corresponding to two (or more) license plates, the time corresponding to the eTag information and the license plate can be observed through time sorting. If the eTag information E ₁ in the pairing combination counted before the time interval t1 corresponds to the license plate P ₁ , but after this time interval t1 corresponds to a different license plate P ₂ , the behavior analysis module 573 determines that the identification change behavior is a license plate replacement behavior. However, if the eTag information E ₁ in the pairing combination before the time interval t1 corresponds to the license plate P ₁ , and after the time interval t1 corresponds to the license plate P ₂ , but after the time interval t2 corresponds to the license plate P ₁ , the behavior analysis module 573 determines this Identifying the change behavior is the behavior of changing license plates back and forth.

If two (more than one) eTag information are corresponding to the same license plate in several pairing combinations, all pairing combinations can still be observed by time sorting. If the pairing combination in the time interval t1 is the license plate P ₃ corresponding to the eTag group (including at least two different eTag information), and the pairing combination in the time interval t2 is still the license plate P ₃ corresponding to the same eTag group, the behavior analysis module 573 Determine that this identification change behavior is to install multiple eTag behaviors. However, if the license plate P _{3 in the} paired combination counted before the time interval t1 corresponds to the eTag information E ₂ , but the license plate P ₃ in the paired combination counted after the time interval t1 corresponds to the eTag information E ₃ , the behavior analysis module 573 determines this identification change The behavior is to replace the eTag behavior.

It is worth noting that the aforementioned comparison process will enter the loop operation, and the behavior analysis module 573 will receive the pairing combination of eTag information and license plate from the same time interval and distinguish by lane, and according to the previous training stage (training stage). Record the corresponding historical pairing combination in the trust database 577, and after updating the latest data, determine whether there is a special identification change behavior between the license plate and eTag information of the latest passing vehicle.

In summary, the embodiment of the present invention is to install a front-end recognition system on one or several lanes on the main road or any road section to be detected, and without having to know the eTag information corresponding to the license plate in the official data, you can use real-time and Automate the matching of eTag information and license plates. Next, the embodiment of the present invention collects historical records of driving behaviors in the past, and then uses algorithms and thresholds to determine all possible combinations of eTag information and license plate pairs. These matching combinations can be further used as a basis for behavior analysis and feedback from relevant personnel, and even as a reference for criminal cases.

The embodiments of the present invention include the following features and effects:

In the embodiment of the present invention, the eTag information is matched with the license plate, and it is not necessary to obtain the true correspondence between the eTag information recorded in the official database and the license plate. The historical record is used to automatically determine a reasonable matching combination.

The embodiment of the present invention uses an automatic filtering method: considering that there may be several vehicles passing through the lane at the same time, the corresponding relationship between the eTag information detected by the front end and the vehicle is not necessarily correct, and a larger number of pairing combinations need to be used to confirm a reasonable pairing Combination, so as to avoid the use of a single threshold to cause incorrect pairing judgment.

In the embodiments of the present invention, individual statistics are sorted through different pairing combinations to select statistical data suitable for subsequent behavior analysis.

Although the present invention has been disclosed as above with examples, it is not intended to limit the present invention. Any person with ordinary knowledge in the technical field can make some changes and modifications without departing from the spirit and scope of the present invention. The scope of protection of the present invention shall be subject to the scope defined in the appended patent application.

1‧‧‧ Behavior analysis system 10‧‧‧ Front-end identification system 11, 51‧‧‧ Communication transceiver 13, 13a, 13b ‧‧‧eTag antenna 14‧‧‧eTag reader 15‧‧‧Image recognition device 151, 151a, 151b‧ Image capture unit 153‧‧‧ License plate recognition module 19, 59‧‧‧ Processor L1, L2‧‧‧ Lane 50‧‧‧ Rear-end recognition system 57‧‧‧ Storage 571‧‧ ‧Vehicle license plate recognition module 573‧‧‧Behavior analysis module 575‧‧‧Trust database 577‧‧‧Training database S310~S390, S410~S490‧‧‧Steps

FIG. 1 is a block diagram of components of a behavior analysis system according to an embodiment of the invention. 2 is a schematic diagram of a front-end recognition system according to an embodiment of the invention. FIG. 3 is a flowchart of a behavior analysis method-training phase according to an embodiment of the invention. 4 is a flowchart of the R&S-comparison phase of the behavior analysis method according to an embodiment of the present invention.

S410~S490‧‧‧Step

575‧‧‧Trust database

577‧‧‧Training database

Claims (10)

A vehicle behavior analysis system, wherein the identification information of each vehicle includes an eTag and a license plate, and the behavior analysis system includes: a front-end identification system, located in at least one lane of a road segment, and including: an eTag reader, through A plurality of connected eTag antennas detect eTag information of passing vehicles, each of which corresponds to a lane; and a plurality of image capturing units, each of which corresponds to a lane, and captures Obtain the image of the license plate including the passing vehicle; and a back-end recognition system to obtain the identification information of the vehicle detected on the at least one lane in multiple time intervals; for each time interval, the same The detected eTag information is paired with the same license plate detected on the lane to generate multiple pairing combinations, where each pairing combination records the same one within the time interval for all detected eTags on the lane Information and license plate; and matching pairs of different time intervals are compared to determine whether the identification information of each vehicle conforms to a recognition change behavior, wherein the recognition change behavior is that the matching combinations of different time intervals do not match. The vehicle behavior analysis system as described in item 1 of the patent application scope, wherein the time intervals include a first time interval and a second time interval, and the back-end recognition system combines the first time interval and the second time interval The time difference between the time intervals is weighted, where the first time interval corresponds to the most recent paired combination, and the second time interval corresponds to the last paired combination before the first time interval; the weighted operation result of the time difference is determined Whether it is less than a threshold; and if the weighted operation result is less than the threshold, then input the matching combination corresponding to the second time interval into a trust database, where the identification change behavior is judged from the data in the trust database. The vehicle behavior analysis system as described in item 2 of the patent application scope, wherein if the weighted operation result is not less than the threshold, the back-end identification system adjusts a statistical time interval, wherein the statistical time interval is used to select some of these Paired combinations of time intervals. The vehicle behavior analysis system as described in item 1 of the patent application scope, wherein the time intervals include a third time interval and a fourth time interval, and the fourth time interval is after the third time interval, and if the The first eTag information in the pairing combination counted before the third time interval corresponds to a first license plate, but after the third time interval corresponds to a different second license plate, the back-end recognition system determines that the recognition change behavior is to replace the license plate Behavior; if the first eTag information in the pairing combination counted before the third time interval corresponds to the first license plate, and after the third time interval corresponds to the second license plate, but after the fourth time interval corresponds to the first A license plate, the back-end recognition system judges that the recognition change behavior is the behavior of changing license plates back and forth; if the pairing combination in the third time interval is a third license plate corresponding to an eTag group, and the matching combination in the fourth time interval Still the third license plate corresponds to the eTag group, the back-end identification system determines that the identification change behavior is to install plural eTag behaviors, where the eTag group includes multiple different eTag information; and if the third time interval is before The third license plate in the statistical matching combination corresponds to a second eTag information, but the third license plate in the statistical matching combination after the third time corresponds to a third eTag information, the back-end recognition system judges the recognition change behavior Is to replace eTag behavior. The vehicle behavior analysis system as described in item 1 of the patent application scope, wherein the back-end recognition system obtains the images obtained by the image capturing units and accordingly obtains a back-end license plate recognition result to determine the back-end license plate recognition The result is consistent with the result of the front-end recognition system's recognition of the license plate in the passing vehicle, and the matching license plate is matched with the corresponding eTag information. A behavior analysis method of a vehicle, wherein the identification information of each vehicle includes an eTag and a license plate, and the behavior analysis method includes: detecting eTag information of a passing vehicle in at least one lane; capturing an image of a license plate including a passing vehicle; obtaining multiple Identification information of the vehicle detected on the at least one lane within the time interval; for each time interval, pair the eTag information detected on the same lane with the same license plate detected on the lane To generate multiple pairing combinations, where each pairing combination records the same eTag information and license plate on the same lane in the time interval; and compares the pairing combinations in different time intervals to determine each Whether the identification information of the vehicle conforms to a recognition change behavior, wherein the recognition change behavior is a pairing combination that differs between the time intervals. The vehicle behavior analysis method as described in item 6 of the patent application scope, wherein the time intervals include a first time interval and a second time interval, and the step of comparing the paired combinations of different time intervals includes: The time difference between the first time interval and the second time interval is weighted, wherein the first time interval corresponds to the most recent pairing combination, and the second time interval corresponds to the same matching combination last time before the first time interval ; Determine whether the weighted operation result of the time difference is less than a threshold value; and if the weighted operation result is less than the threshold value, then enter the pairing combination corresponding to the second time interval into a trust database, where from the trust database The data judges the identification change behavior. The method for analyzing the behavior of a vehicle as described in item 7 of the patent application scope, after the step of determining whether the weighted operation result of the time difference is less than the threshold value, further includes: If the weighted operation result is not less than the threshold value, the back end The identification system adjusts a statistical time interval, wherein the statistical time interval is used to select a part of the matching combinations of these time intervals. The vehicle behavior analysis method as described in item 6 of the patent application scope, wherein the time intervals include a third time interval and a fourth time interval, and the fourth time interval is after the third time interval, and the comparison The steps of the pairing combinations that are different in these time intervals include: If the first eTag information in the pairing combination counted before the third time interval corresponds to a first license plate, but after the third time interval corresponds to a different second license plate, It is judged that the identification change behavior is the behavior of changing the license plate; if the first eTag information in the pairing combination counted before the third time interval corresponds to the first license plate, and after the third time interval corresponds to the second license plate, but the After the fourth time interval corresponds to the first license plate again, it is judged that the identification change behavior is the behavior of changing the license plate back and forth; if the pairing combination in the third time interval is a third license plate corresponding to an eTag group, and the fourth time If the pairing combination of the interval is still that the third license plate corresponds to the eTag group, the identification change behavior is determined to be a plural eTag installation behavior, where the eTag group includes multiple different eTag information; and if the third time interval is before The third license plate in the statistical pairing combination corresponds to second eTag information, but the third license plate in the statistically matched pair after the third time corresponds to third eTag information, then the identification change behavior is determined to be an eTag replacement behavior. The method for analyzing the behavior of a vehicle as described in item 6 of the patent application scope, wherein before the step of comparing the pairing combinations in different time intervals, the method further includes: obtaining the images obtained by the image capturing units and obtaining a The result of the back-end license plate recognition; determine whether the result of the back-end license plate recognition matches the result of the front-end recognition system's recognition of the license plate in the passing vehicle; and pair the matching license plate with the corresponding eTag information.

Images