CN107742418A - A method for automatic identification of traffic congestion status and location of congestion points on urban expressways - Google Patents

Abstract

The invention discloses a method for automatically identifying the traffic congestion state and the location of the congestion point on an urban expressway, which comprises the following steps: 1) setting the threshold value of the traffic parameter of each monitoring road section and lane; 2) collecting the vehicle image/image in the field of view, converting Generate lane-divided traffic data information, and transmit the lane-divided traffic data information to the traffic information processing server; 3) The traffic information processing server uses the real-time traffic data information and the traffic parameter threshold database to analyze the congestion status and the location of the congestion point; 4) According to the user settings, the analysis results and corresponding suggestions are forwarded to the user terminal. The present invention can quickly judge the road section location and the lane where traffic incidents such as cargo dropping, malicious jamming, breakdown/illegal parking behavior, or traffic accident occur, which helps the traffic management department to respond reasonably in time and avoid Subsequent more serious traffic congestion, reducing the secondary accident rate.

Description

A method for automatic identification of traffic congestion status and location of congestion points on urban expressway

technical field

The invention relates to a method for automatically identifying the traffic congestion state and the location of a congestion point on an urban expressway, which combines road monitoring, image analysis and traffic state evaluation, and belongs to the technical field of traffic congestion monitoring.

Background technique

With the rapid increase of car ownership in my country's cities, traffic congestion is becoming more and more serious. Among them, although there are basic reasons for the large traffic demand and the relatively insufficient supply of road infrastructure, there are also "traffic incidents" such as "snail-walking" of vehicles, breakdowns/illegal parking, malicious congestion, dropped goods, and traffic accidents. "occasional traffic jams".

Since the regularity and periodicity of "occasional traffic jams" are not as significant as those of "frequent traffic jams", it is difficult to predict or prevent them in advance; at the same time, a considerable proportion of "occasional traffic jams" has a small impact range and short duration , the necessity of management seems to be insufficient, and it is difficult to arouse the general attention of traffic management departments. However, relevant research shows that some seemingly small traffic incidents, due to improper handling or insufficient response, eventually caused serious traffic congestion in a large area. It can be seen that for the traffic management department, it is very necessary to know the road traffic situation (especially the traffic jam status and the location of the jam point) in a timely and accurate manner.

Traditional urban road traffic congestion monitoring is mainly realized through manual monitoring, emergency calls or induction coil detectors. Manual monitoring is inefficient and prone to omissions, and it is difficult to deal with the complex road network of big cities; the timeliness of emergency calls is not good, and the accuracy of judging the degree of congestion is insufficient; the induction loop detector can only monitor part of the traffic data, and the system The road surface needs to be damaged during installation, and subsequent maintenance and guarantee are troublesome, so there are great limitations in use. In recent years, with the rapid development of high-definition video information collection and transmission technology and big data processing technology, the automatic monitoring technology of urban road traffic congestion status based on high-definition video is in the ascendant.

The automatic monitoring of urban road traffic congestion is based on real-time traffic characteristic parameters, quickly making judgments on the characteristic parameters, detecting the existence of traffic congestion, and giving early warning or alarm to the monitored traffic congestion. This helps the traffic management department to take timely countermeasures to minimize the severity and scope of traffic congestion.

The existing (high-definition) video-based automatic monitoring method for urban road traffic jam status usually first sets the threshold of traffic parameters (such as occupancy rate, average vehicle speed or cross-section traffic volume). After exceeding the above threshold to a certain extent, a judgment and suggestion on the level of traffic congestion will be formed, and an alarm mechanism will be triggered.

Because the relationship between the main parameters of road traffic is complex, and the traffic characteristics (vehicle speed, lane change) of vehicles on the road are also very different, the existing congestion judgment algorithm based on monitoring the overall traffic parameters of the road section has great deficiencies. For example, a vehicle breakdown accident occurred on the inner side of a certain (one-way) three-lane urban expressway, causing multiple vehicles in the lane where the breakdown vehicle was located to line up. Since the speed of the other two lanes has not been greatly affected, and the occupancy rate of the road section has not changed significantly, the automatic identification method based on the average vehicle speed or the occupancy rate of the road section cannot make an early warning of traffic congestion. However, traffic jams will gradually appear on this section of the road afterwards and there is a great risk of causing secondary accidents. By then, it will be too late for the system to detect a traffic jam.

As another example, when a long section of an urban expressway is stuck in traffic jams, multiple video surveillance systems along the line will display that the real-time traffic parameters exceed the threshold and issue an alarm. At this time, which road sections should be dispatched with limited police force has become a big problem. Once the judgment is wrong, the continued mobilization of police forces will be a good opportunity to control traffic congestion at the wrong time. It can be seen that the traffic congestion judging mechanism that is calling the police along the line does not have much practical significance.

Contents of the invention

In order to overcome the technical defects in the existing traffic congestion monitoring methods, the present invention proposes an automatic identification method for the traffic congestion state and the location of the congestion point on the urban expressway, which can automatically give an early warning, give an alarm and send an alarm when the urban expressway is congested (or is about to occur). Prompt the location of the congestion point to assist the traffic management department to solve the problems in judging the traffic congestion status and coping options, etc., and reduce the social and economic impact of traffic congestion.

In order to solve the above-mentioned technical problems, the present invention provides a kind of urban expressway traffic congestion situation and the method for automatically identifying the location of the congestion point, comprising the following steps:

1) Thresholds are set for the traffic parameters of each sub-lane in each monitored road section. The traffic parameters include the normal driving speed, space occupancy rate, lane change frequency and direction, and traffic volume of vehicles in peak and off-peak periods;

2) The vehicle image information in the field of view is collected by the camera installed beside the monitoring road, and converted into real-time traffic data information of the lanes, and the real-time traffic data information of the lanes is transmitted to the traffic information processing server. The real-time traffic data information includes The moving speed of the vehicle in the field of view, the space occupancy rate of each lane in the field of view, and the lane change frequency between lanes in the field of view, the lane change refers to the center line of the vehicle crossing the lane line;

3) The traffic information processing server analyzes the congestion situation and the position of the blocking point according to the real-time traffic data information and the traffic parameter threshold value of the monitoring road section and the real-time traffic data information obtained by the cameras of the upstream and downstream road sections of the associated monitoring road section and the traffic parameter threshold value of the relevant road section;

4) According to user settings, the analysis results, real-time images and corresponding suggestions are transmitted to the user terminal.

Further, in step 3), judge the congestion situation according to the real-time traffic data information and the traffic parameter threshold, including "snail walking" behavior judgment, parking behavior judgment and lane change frequency judgment;

If the driving speed of the vehicle in the peak period is lower than the average speed of the vehicle in the field of view of the camera or the driving speed of the vehicle in the peak period is lower than the normal driving speed threshold, that is:

When Mean-v _t >0.4×v _D :

v _tk ≤α×Mean-v _t peak hours(1)

v _tk ≤β×v _D flat peak period (2)

Be regarded as "snail walking" behavior;

Among them, v _tk is the driving speed of vehicle k at time t, Mean-v _t is the average speed of vehicles in the field of view of the camera at time t, v _D is the design speed of the expressway section, and α and β are used for control and management The coefficient of strictness can be set in combination with the traffic engineering model or the historical data of step 1);

If the average speed of the vehicle in the field of view of the camera is:

Mean-v _t ≤0.4×v _D (3)

It is regarded as slowing down as a whole of the traffic flow;

If the "space occupancy" of the road directly in front of the vehicle is zero and its driving speed remains zero for a certain period of time, that is:

v _tk = v _(t+Δtk) = 0 (4)

deemed to be parking;

The lane change frequency judgment includes:

When on a lane:

ΣC _mn ≥ γ×T _m (5)

That is to say, the lane change frequency is high;

Among them, C _mn is the number of times the vehicle changes lanes from lane m to adjacent lane n in the time interval Δt, ΣC _mn is the number of times that the vehicle changes lanes from lane m to all adjacent lanes, and T _m is the arrival upstream of lane m in the time interval The traffic volume of the boundary line, γ is a coefficient, and the traffic volume is the number of vehicles passing the upstream boundary line of the camera's field of view on the m lane within the time interval Δt.

Further, the threshold setting in step 1) includes: collecting the historical data of traffic parameters of each monitoring road section in lanes, and processing the collected historical data according to the time period of the road section, whether it is a working day, season, weather factors, According to the processed data, thresholds are set for traffic parameters of each monitored road section and a historical database is established.

Further, the space occupancy rate of each lane in steps 1) and 2) is a percentage of the total floor area of vehicles traveling on the road section to the total area of the road section at a certain moment.

Further, the congestion cause analysis in step 3) includes: vehicle "snail-walking", malicious jamming, cargo dropping, breakdown/illegal parking behavior, and traffic accidents.

Further, the monitoring road section is an urban expressway including viaducts, tunnels, ground floors and various weaving areas, and the weaving areas include plane weaving areas, viaducts or tunnels.

Further, in step 3), according to the "snail walking" behavior and parking behavior analysis of the lanes, the congestion situation and the position of the blocking point include:

When there are snail-moving or parking vehicles on any lane or multiple lanes in the field of view for a long time, if the frontmost vehicle does not reach the downstream boundary of the field of view, it is judged that there is a fault/illegal parking behavior or traffic accident in this lane ; If the frontmost vehicle has reached the downstream boundary of the field of view, it is judged that there is a fault/illegal parking behavior or traffic accident in the downstream direction of the lane;

The vehicle being in the field of view for a long time is defined as the time that the vehicle is in the field of view is greater than a set duration threshold, and the duration threshold is set according to the strictness of management.

Further, in step 3), analyze the congestion situation and the position of the blocking point according to the vehicle lane change frequency and direction in the field of view, including:

When the lane change frequency of the vehicle in the field of view exceeds the set lane change frequency threshold, the vehicle avoidance lane is judged according to the vehicle lane change direction and the lane change frequency of each lane, and it is judged that goods appear in the downstream section of the vehicle avoidance lane Falling, failure/violation of parking behavior or traffic accident, the traffic information processing server correlates with the real-time traffic data information obtained by the camera on the downstream road section for determination.

Further, in step 3), the congestion situation and the position of the blocking point are analyzed according to the space occupancy rate in the field of view, including:

When the moving speed of the vehicle in the field of view is not less than the normal driving speed, but the real-time space occupancy of the road section is lower than the set space occupancy threshold, it is judged that the upstream road section of the field of view has "snail-walking" and goods Falling, failure/illegal parking behavior or traffic accidents, the traffic information processing server associates the real-time traffic data information obtained by the upstream road section camera for further determination;

If the average vehicle speed in the field of view of the upstream camera is lower than the normal driving speed and the real-time space occupancy rate is higher than the space occupancy threshold, it can be judged that the traffic incident occurred in the "blind zone" road section between the two sets of cameras; If the real-time space occupancy rate in the field is also lower than the space occupancy rate threshold, it is judged that the traffic incident occurrence point is still located in the upstream section of the upstream camera, and the above steps are repeated to determine the specific occurrence location of the traffic incident occurrence point.

Further, in step 4):

User settings include setting thresholds for the duration of the vehicle state in each lane in the field of view;

The analysis results include: the space occupancy rate of the road section in the monitoring field of view and the corresponding traffic congestion level, the severity of the traffic incident, the lane where the traffic incident occurred, and the road section where the lane is located.

Suggestions include: manual analysis of real-time or historical images, notification, warning, penalties for violating vehicles, notification or warning of driving vehicles on the upstream section.

Beneficial effects: Compared with the prior art, the present invention can automatically monitor and identify traffic jams, especially sporadic traffic jams; automatically acquire traffic information status based on high-definition video signals, and quickly determine the goods The road section location and lane where traffic incidents such as falling, malicious jamming, breakdown/illegal parking behavior, or traffic accident occurred; traffic congestion status and congestion point location information use push mode and forwarding mode for early warning and alarm release. Compared with the existing technology, it is possible to more accurately and timely discover the specific spatial location of the traffic incident that caused the congestion, which will help the traffic management department to respond in a timely and reasonable manner, such as notifying, warning and punishing illegal vehicles, dispatching police forces or Other supporting forces, informing or warning vehicles traveling on the upstream section, etc.

Description of drawings

Fig. 1 is the realization flow diagram of the urban expressway traffic congestion state and the automatic identification method of the blocking point position provided by the present invention;

Fig. 2 is a schematic view of the field of view of the camera provided by the present invention;

Fig. 3 is a logical judgment diagram of the traffic congestion status and the automatic identification of the location of the congestion point on the urban expressway provided by the present invention.

detailed description

The present invention will be further described below in conjunction with the accompanying drawings.

Fig. 1 shows the flow chart of the implementation of the urban expressway traffic congestion state and the automatic recognition method for the blocked point position of the present embodiment, specifically comprising the following steps:

In step S11, collect historical data or use the method of traffic engineering to set the threshold value of the traffic parameters of each monitored road section divided into lanes:

Collect and monitor the traffic parameters of the lanes of the road section, including: average vehicle speed, space occupancy, lane change frequency and direction, and traffic volume within a certain time interval; classify the data according to the time period, whether it is a working day, season, weather, etc. Statistical processing such as denoising, to obtain the threshold of traffic parameters of each road section under each sub-category and establish a historical database. Before collecting enough historical data, the existing traffic engineering methods can be used to set the thresholds of the above traffic parameters according to empirical data and theoretical derivation results.

In step S12, the vehicle images/images in the field of view are collected by the high-definition camera arranged beside the monitored road, converted into traffic data information of the lanes, and the traffic data information of the lanes is transmitted to the traffic information processing server;

In step S12, the traffic data information includes the moving speed of the driving vehicle in the field of view, in order to find that the driving speed is significantly lower than that of most other vehicles' "snail crawling" behavior, accidents/faults/illegal parking behaviors and malicious blocking that lead to blocked vehicles Behaviors such as sudden braking, looking for targets whose driving speed is significantly lower than other vehicles during peak hours or whose driving speed is significantly lower than the normal driving speed threshold during off-peak periods, the vehicle "snail speed" speed is judged as follows:

If the driving speed of the vehicle during the peak period is significantly lower than other vehicles in the camera field of view or the driving speed during the peak period is lower than the normal driving speed threshold, that is:

When Mean-v _t >0.4×v _D :

v _tk ≤α×Mean-v _t peak hours(1)

v _tk ≤β×v _D flat peak period (2)

Considered "snail walking" behavior.

Among them, v _tk is the driving speed of vehicle k at time t, Mean-v _t is the average speed of vehicles in the field of view of the camera at time t, v _D is the design speed of the expressway section, and α and β are used for control and management The coefficient of strictness can be set in combination with the traffic engineering model or the historical data in step S11. In this embodiment, the default values of α and β are 0.8 and 0.7, respectively.

If the average speed of the vehicle in the field of view of the camera is:

Mean-v _t ≤0.4×v _D (3)

It is regarded as slow moving of the traffic flow as a whole.

If the road in front of the vehicle is clear, that is, the "space occupancy" of the road within 5 meters in front of the vehicle is zero, and its driving speed continues to be zero for a certain period of time, that is:

v _tk = v _(t+Δtk) = 0 (4)

considered parking.

The "space occupancy rate" in the prior art is defined as: at a certain moment t, the percentage of the total length of vehicles traveling on the road section to the length of the road section, that is, the space occupancy rate (%) O _t = (ΣLength-car)/Length- road; in step S12, the "space occupancy rate" in the present embodiment is redefined as: at a certain moment t, the percentage of the total floor area of vehicles running on the road section to the total area of the road section, that is, the space occupancy rate (%) O _t '=(ΣArea-car)/Area-road. This is considering that in very congested road sections, the number of vehicles queuing up may exceed the number of lanes. For example, on a one-way three-lane expressway, there may be four vehicles queuing up. The space occupancy mentioned in this embodiment below Both are the redefined space occupancy rate (%) O _t '=(ΣArea-car)/Area-road.

In step S12, the traffic data information also includes the "lane changing frequency" between adjacent lanes in the field of view or the frequency of large lateral movement of the driving vehicle. When on a lane:

ΣC _mn ≥ γ×T _m ; (5)

It is regarded as frequent lane-changing behavior.

Among them: C _mn is the number of times that vehicles change lanes from lane m to adjacent lane n within the time interval Δt, m and n are the natural numbers of lane numbers, m, n∈[1, 2,...N]; ΣC _mn is The number of lane changes from lane m to all adjacent lanes; γ is a coefficient used to control the strictness of monitoring, and it is recommended that γ take a value of 0.8; T _m is the traffic volume of lane m reaching the upstream boundary line in the time interval, the time The interval is in minutes, where the vehicle centerline is considered to have changed lanes when it crosses the lane line, and the traffic volume is defined as the number of vehicles passing the upstream boundary line of the camera's field of view on the m lane within the time interval Δt.

In step S13, the traffic information processing server analyzes the congestion state according to the traffic data information, and the specific method is described in the content of FIG. 3 below.

In step S14, according to user settings, the analysis results and corresponding suggestions are forwarded to the user terminal. The analysis results include: monitoring the space occupancy rate of the road section and its corresponding traffic congestion level, the possible types of traffic incidents that have occurred, the lane where the traffic incident occurred and the road section where the traffic incident occurred, and the corresponding suggestions include: notification, warning and punishment of illegal vehicles, timely dispatch The police force or other supporting force informs or warns the traveling vehicles on the upstream road section. The specific calculation of the traffic congestion level in this embodiment is based on the existing formula of traffic engineering.

FIG. 2 shows a schematic view of the field of view of the camera in this embodiment.

Among them, l represents the road section covered by the field of view of the current camera, the _top of l represents the upstream road section of the road section monitored by the current camera, and the _{bottom of} l represents the downstream road section of the road section monitored by the current camera; X represents the upstream boundary line of the road section monitored by the current camera, and Y represents The current camera monitors the downstream boundary line of the road segment.

Fig. 3 shows the logic judgment diagram of the urban expressway traffic congestion state and the automatic identification of the location of the congestion point in this embodiment. For the convenience of explanation, only the parts related to this embodiment are shown in the figure.

According to the information collected by the camera located on the road section, first judge whether there is a low-speed or parked vehicle in the field of view for a long time. The time for low-speed, "snail-walking" or stopped vehicles in the field of view is greater than the set duration threshold. The duration threshold is set according to the strictness of management, and the value range is usually 5 to 30 seconds:

If there are such vehicles in some lanes and the frontmost vehicle in the forward direction does not reach the downstream boundary line Y of the field of view, it is judged that there is a fault/illegal parking behavior or a traffic accident, and the traffic event occurs in the lane (judgment A), Live images/videos can be sent back for manual analysis.

If there are such vehicles in some lanes and the frontmost vehicle in the forward direction has reached the downstream boundary line Y of the field of view, it is judged that there is a fault/illegal parking behavior or a traffic accident, and the traffic event occurs in the downstream direction of the lane ( Judgment B), it can guide the nearby spherical camera to turn to this direction to confirm violations or accidents.

If there are low-speed or stopped vehicles in all lanes and the frontmost vehicle in the forward direction does not reach the downstream boundary line Y of the field of view, then it is judged that there is a fault/illegal parking behavior or a traffic accident, and the traffic event has seriously affected all lanes ( Judgment A), immediately send back the real-time image/video for manual analysis.

If there are low-speed or stopped vehicles in all lanes and the frontmost vehicle in the forward direction has lined up to the downstream boundary line Y of the field of view, it is judged that there is a serious traffic jam on the downstream section. At this time, if frequent one-way lateral movement or lane change continues within a certain period of time, it is judged that there is a cargo drop, breakdown/illegal parking behavior or traffic accident, and the traffic incident occurs in the downstream direction of the vehicle avoidance lane (judgment B); if there is no continuous one-way lateral movement or lane change within a certain time frame, it is judged that the traffic incident occurred far downstream, or the traffic jam occurred was not caused by the traffic incident, but " frequent traffic jams”, that is, judgment C. When judging B or C, continue to analyze the information collected by the downstream camera, for example, guide the nearby spherical camera to turn to this direction to confirm violations or accidents, so as to further determine the specific location of the traffic incident.

If the speed of the vehicle in the field of view is within a reasonable range, but frequent one-way lateral movement or lane change continues within a certain period of time, it is judged that a cargo drop, breakdown/illegal parking behavior or a traffic accident occurred and the event occurred in The lane to avoid by the vehicle or the downstream direction of this lane, judge B, and the real-time image/video can be sent back for manual analysis.

Since there is no artificial blockage such as traffic lights on urban expressways, the traffic flow on it is a continuous traffic flow, and the traffic parameters between the upstream and downstream have a more direct relationship with traffic behavior. , help to obtain more accurate and timely traffic event information.

If the speed of vehicles in the field of view is within a reasonable range, but the "space occupancy" during the peak hours of working days is significantly lower than the normal level, for example, for the road section where the "space occupancy" fluctuates between 0.4 and 0.5 during peak hours , it is found that its "space occupancy rate" is lower than 0.3 for 1 minute in a row, then it is judged that this parameter is significantly lower than the normal level. Vehicle "snail-walking", cargo falling, failure/illegal parking behavior or traffic accidents; if the "space occupancy rate" within a certain period of time is still significantly lower than the normal level, cargo drop, failure/ Parking violations or traffic accidents. At this time, the traffic information obtained by the cameras on the upstream road section can be combined. If the average vehicle speed in the field of view of the upstream cameras is low and the "space occupancy rate" is higher than the threshold, it can be judged that the traffic incident occurred in the "blind zone" between the two sets of cameras. " road section (judgment D); if the "space occupancy rate" in the field of view of the upstream camera is also lower than the threshold, then it is judged that the blocking point is still located in the upstream road section before the camera (judgment E), and the above steps can be repeated to determine the occurrence of a traffic incident The specific occurrence location of the point and guide the nearby dome camera to turn to this direction to confirm the violation or accident.

For the information collected by cameras whose field of view is located in the weaving area, in addition to the aforementioned judgment criteria, special attention should also be paid to the "space occupancy" of each lane in the weaving area, which includes plane weaving areas, viaducts, or on-and-off ramps of tunnels connection to the mainline.

If the "space occupancy rate" of the inner lane of the main line is low or the vehicle speed is high, while the "space occupancy rate" or vehicle speed of the main line outer lane is relatively high, the above-mentioned "space occupancy rate" or high vehicle speed are related to Compared with the value of the historical database in step S11, it is judged that malicious jamming, failure/violation of parking behavior or traffic accident (judgment A) has occurred in the outer lane or ramp of the main line; if this state lasts for a certain period of time (such as more than 30 seconds) , it can be further determined that there is malicious congestion, failure/illegal parking behavior or traffic accident in the outer lane or ramp of the main line (judgment A).

In this embodiment, the user can set and adjust the strictness of monitoring and alarming. For example, you can set a threshold for the duration of the vehicle running at a low speed or in a stopped state, and the system will only respond and analyze the situation in the camera field of view when the vehicle is running at a low speed or in a stopped state for a duration exceeding the threshold, in order to avoid too frequent alarms and manual monitoring. intervene.

Claims (10)

1. a kind of urban expressway traffic congestion situation and the automatic recognition method of blocking point position, it is characterized in that: comprise the following steps: 1) Thresholds are set for the traffic parameters of each sub-lane in each monitored road section. The traffic parameters include the normal driving speed, space occupancy rate, lane change frequency and direction, and traffic volume of vehicles in peak and off-peak periods; 2) The vehicle image information in the field of view is collected by the camera installed beside the monitoring road, and converted into real-time traffic data information of the lanes, and the real-time traffic data information of the lanes is transmitted to the traffic information processing server. The real-time traffic data information includes The moving speed of the vehicle in the field of view, the space occupancy rate of each lane in the field of view, and the lane change frequency between lanes in the field of view, the lane change refers to the center line of the vehicle crossing the lane line; 3) The traffic information processing server analyzes the congestion situation and the position of the blocking point according to the real-time traffic data information and the traffic parameter threshold value of the monitoring road section and the real-time traffic data information obtained by the cameras of the upstream and downstream road sections of the associated monitoring road section and the traffic parameter threshold value of the relevant road section; 4) According to user settings, the analysis results, real-time images and corresponding suggestions are transmitted to the user terminal. 2. a kind of urban expressway traffic congestion situation and the automatic identification method of blocking point position according to claim 1, it is characterized in that: in described step 3) carry out congestion situation judgment according to real-time traffic data information and traffic parameter threshold value, comprise "Snail walking" behavior judgment, parking behavior judgment and lane change frequency judgment; If the driving speed of the vehicle in the peak period is lower than the average speed of the vehicle in the field of view of the camera or the driving speed of the vehicle in the peak period is lower than the normal driving speed threshold, that is: When Mean-v _t >0.4×v _D : v _tk ≤α×Mean-v _t peak hours(1) v _tk ≤β×v _D flat peak period (2) Be regarded as "snail walking" behavior; Among them, v _tk is the driving speed of vehicle k at time t, Mean-v _t is the average speed of vehicles in the field of view of the camera at time t, v _D is the design speed of the expressway section, and α and β are used for control and management The coefficient of strictness can be set in combination with the traffic engineering model or the historical data of step 1); If the average speed of the vehicle in the field of view of the camera is: Mean-v _t ≤0.4×v _D (3) It is regarded as slowing down as a whole of the traffic flow; If the "space occupancy" of the road directly in front of the vehicle is zero and its driving speed remains zero for a certain period of time, that is: v _tk = v _(t+Δtk) = 0 (4) deemed to be parking; The lane change frequency judgment includes: When on a lane: ΣC _mn ≥ γ×T _m (5) That is to say, the lane change frequency is high; Among them, C _mn is the number of times the vehicle changes lanes from lane m to adjacent lane n in the time interval Δt, ΣC _mn is the number of times that the vehicle changes lanes from lane m to all adjacent lanes, and T _m is the arrival upstream of lane m in the time interval The traffic volume of the boundary line, γ is a coefficient, and the traffic volume is the number of vehicles passing the upstream boundary line of the camera's field of view on the m lane within the time interval Δt. 3. a kind of urban expressway traffic congestion situation and the automatic identification method of blocking point position according to claim 1, it is characterized in that: the threshold value setting in the described step 1) comprises: collecting the history of each monitoring road section lane-dividing traffic parameter Data, and process the collected historical data according to the time period of the road section, whether it is a working day, season, and weather factors. According to the processed data, thresholds are set for the traffic parameters of each monitored road section and a historical database is established. 4. a kind of urban expressway traffic congestion situation and the automatic identification method of blocking point position according to claim 1, it is characterized in that: the space occupancy rate of each lane in described step 1) and 2) is a certain instant , the percentage of the total area occupied by vehicles traveling on the road section to the total area of the road section. 5. A kind of urban expressway traffic congestion situation and the method for automatically identifying the position of the blocking point according to claim 1, characterized in that: the analysis of the reasons for the congestion in the step 3) includes: vehicle "snail travel", malicious blocking, goods Falls, breakdowns/parking violations, traffic accidents. 6. A kind of urban expressway traffic congestion situation and the automatic identification method of blocking point position according to claim 1, it is characterized in that: described monitoring road section is that urban expressway comprises viaduct, tunnel, ground floor and various weaving areas, The weaving area includes the plane weaving area, the connection between the upper and lower/in and out ramps of viaducts or tunnels and the main line. 7. A kind of urban expressway traffic congestion situation and the automatic identification method of blocking point position according to claim 2, it is characterized in that: in step 3) according to the " crawling " behavior of sub-lane and parking behavior analysis congestion situation and blocking up Point locations include: When there are snail-moving or parking vehicles on any lane or multiple lanes in the field of view for a long time, if the frontmost vehicle does not reach the downstream boundary of the field of view, it is judged that there is a fault/illegal parking behavior or traffic accident in this lane ; If the frontmost vehicle has reached the downstream boundary of the field of view, it is judged that there is a fault/illegal parking behavior or traffic accident in the downstream direction of the lane; The vehicle being in the field of view for a long time is defined as the time that the vehicle is in the field of view is greater than a set duration threshold, and the duration threshold is set according to the strictness of management. 8. According to claim 2 or 7, a kind of urban expressway traffic congestion situation and the method for automatically identifying the position of the blocking point, it is characterized in that: in step 3), analyze the congestion situation and the blocking point according to the vehicle lane change frequency and direction in the field of view. point locations, including: When the lane change frequency of the vehicle in the field of view exceeds the set lane change frequency threshold, the vehicle avoidance lane is judged according to the vehicle lane change direction and the lane change frequency of each lane, and it is judged that goods appear in the downstream section of the vehicle avoidance lane Falling, failure/violation of parking behavior or traffic accident, the traffic information processing server correlates with the real-time traffic data information obtained by the camera on the downstream road section for determination. 9. A kind of urban expressway traffic congestion situation and the automatic identification method of blocking point position according to claim 7, it is characterized in that: in the step 3) according to the space occupancy rate analysis congestion situation and blocking point position in the field of view, comprising: When the moving speed of the vehicle in the field of view is not less than the normal driving speed, but the real-time space occupancy of the road section is lower than the set space occupancy threshold, it is judged that the upstream road section of the field of view has "snail-walking" and goods Falling, failure/illegal parking behavior or traffic accident, the real-time traffic data information obtained by the traffic information processing server associated with the upstream road section camera is further confirmed; If the average vehicle speed in the field of view of the upstream camera is lower than the normal driving speed and the real-time space occupancy rate is higher than the space occupancy threshold, it can be judged that the traffic incident occurred in the "blind zone" road section between the two sets of cameras; If the real-time space occupancy rate in the field is also lower than the space occupancy rate threshold, it is judged that the traffic incident occurrence point is still located in the upstream section of the upstream camera, and the above steps are repeated to determine the specific occurrence location of the traffic incident occurrence point. 10. a kind of urban expressway traffic congestion situation and the automatic identification method of blocking point position according to claim 1, it is characterized in that: in described step 4): User settings include setting thresholds for the duration of the vehicle state in each lane in the field of view; The analysis results include: the space occupancy rate of the road section in the monitoring field of view and the corresponding traffic congestion level, the severity of the traffic incident, the lane where the traffic incident occurred, and the road section where the lane is located. Suggestions include: manual analysis of real-time or historical images, notification, warning, penalties for violating vehicles, notification or warning of driving vehicles on the upstream section.