WO2024052884A1

WO2024052884A1 - Method and system for congestion monitoring and management

Info

Publication number: WO2024052884A1
Application number: PCT/IB2023/058951
Authority: WO
Inventors: Vaibhav KAUSHIK; Aalaap SUDHIR NAIR; Aryan SISODIA
Original assignee: Nawgati Tech Private Limited
Priority date: 2022-09-09
Filing date: 2023-09-09
Publication date: 2024-03-14

Abstract

The present disclosure is related to a congestion monitoring and management method and system. The image captured from a premises is processed to determine hash of queuing objects in a premises, and further hash is used to determine movement of the objects in the queue. The patterns of queue movement are identified, which is further used to a lot lane to each of the new queuing objects. The solution also provides for detecting serving objects which are serving on different lanes, and to check if the serving objects are missing at a particular point of time. The solution also determines issues with respect to any other regulating objects, for example missing stop signs at fueling terminals. These identifications help in auditing the reasons for congestion.

Description

METHOD AND SYSTEM FOR CONGESTION MONITORING AND MANAGEMENT

FIELD OF THE INVENTION

The present disclosure is related to a computer implemented system and method for congestion monitoring and management. More specifically, the present disclosure is related to congestion with respect to vehicles. Still particularly, the present disclosure has implementation in fuel stations, however can be extended into any other places, like Toll Plazas etc., particularly where queuing mechanism is involved. The present disclosure can be further extended to congestion where human queue is involved. .

BACKGROUND OF THE INVENTION

Various businesses or places have high inflows of people or vehicles, and due to such inflows, the businesses or places follows queuing mechanism to control the congestion. However, such controls do not overcome congestion completely. For decongestion, another mechanism used is to follow different lane s or counters to serve people or vehicles. However, opening number of lane s also do not help to completely decongest the places, as people may use their judgement, and pour in large numbers at one lane itself, thus making a particular lane congested and over loaded, while other lane s underutilized. Sometimes, the management of these places keeps queue managers which directs the people/vehicle to move to different lane s to keep all the lane s utilized and uncongested. However, such human based management can still be error prone, and may not have complete view of the reasons of congestion of one particular lane , and without knowing any such reasons, the queue manager may keep on sending people/vehicles to a lane which may be understaffed for a moment and congest a particular lane , and may lead to chaos.

One solution had been tried by Indraprastha Gas Limited for its fuelling stations, where they have attempted to solve the queuing problem using a manual entry system in IGL Connect App, wherein a station attendant manually counts and enters the number of vehicles into a smartphone. This method is not scalable and is prone to human error.

European Patent Publication No. EP0631683B1 discloses an object monitoring system which includes a camera node for monitoring movement of an object to determine an acquisition time when an image of the object is to be acquired and acquiring the image at the predetermined time. The system includes a camera which is able to monitor moving objects, and image processing circuitry, responsive to the camera, which is able to detect a predetermined moving object from other moving and static objects. From the image acquired, information identifying the object can be automatically extracted. The system is particularly suited to monitoring and discriminating large vehicles from other vehicles over a multi -lane roadway, and acquiring high resolution images of the large vehicles at a predetermined acquisition point. Image data acquired by a plurality of camera nodes can be sent over a digital telecommunications network to a central image processing system which can extract vehicle identifying data, such as licence plate details, and obtain information on vehicle travel between nodes.

US Patent Publication No. US20040091134A1 discloses a queuing management system for managing a queue of waiting vessels or persons having a pass-through point may include a camera system configured to generate one or more images of the queue and sequential images of the pass-through point. It may include an image processing system configured to calculate information indicative of the anticipated delay in the queue, the rate of passage through the pass-through point, the number of vessels or persons in the queue, the number of vessels or persons that have passed through the pass-through point, the type of vessel, and/or unusual movement of a vessel or person in the queue, all based on the images from the camera system.

US Patent Publication No. US9779331B2 discloses a method and system of tracking partially occluded objects using an elastic deformation model. According to an exemplary method and system, partially occluded vehicles are detected and tracked in a scene including side-by-side drive-thru lanes. A method for updating an event sequence includes acquiring video data of a queue area from at least one image source; searching the frames for subjects located at least near a region of interest (RO I) of defined start points in the video data; tracking a movement of each detected subject through the queue area over a subsequent series of frames; using the tracking, determining if a location of the a tracked subject reaches a predefined merge point where multiple queues in the queue area converge into a single queue lane; in response to the tracked subject reaching the predefined merge point, computing an observed sequence of where the tracked subject places among other subjects approaching an end-event point; and, updating a sequence of end-events to match the observed sequence of subjects in the single queue lane.

US Patent Publication No. US5953055A discloses a system and method for detecting, collecting information about, and analyzing a queue. A video camera is positioned to view the queue, and a sequence of video images from the camera may be processed in order to perform the functionality of the present invention. The technique may be implemented at checkout lanes in a retail establishment, in a bank, at customer service desks, at self-service kiosks, at banks, or any other location where a queue (line) of people or other objects may form. After detecting the queue, the present invention may collect multi-dimensional information regarding the queue, including the number of people, etc., in the queue, the average service time for each person in the queue, as well as various other types of information regarding the queue. The technique may thereafter analyze the collected information in various ways, based upon various criteria. For example, a retailer may use the analyzed information to minimize service time for people in a checkout line, in a way which makes economic sense.

All the above-said techniques focus on video analytics. They measure the width, height, and position of objects and contrast them with the prior frame to determine movement, requiring them to capture between 20 to 30 frames every second.

These techniques encounter at least two pronounced limitations:

1. High Computing Needs: Processing 20-30 frames each second demands significant computational power. In contrast, our model, processing only one frame a minute, is more resource-friendly.

2. Dedicated Camera for Each Location: To maintain a rate of 20-30 frames per second, cameras must remain fixed on a specific location.

Hence, a solution is desired which overcomes above limitations, and also monitors the congestion, further identify reasons for congestion, and take measures to handle congestion effectively.

OBJECT OF THE INVENTION The object of the present present disclosure is to provide a solution for efficient congestion monitoring and control for businesses and places having heavy inflow of humans or vehicles.

SUMMARY OF THE INVENTION

The present disclosure discloses a system designed for congestion monitoring and management in a lane-following environment. It consists of an image capturing unit that takes images of lanes at regular intervals. A queuing processing unit receives and analyzes these images to detect vehicles in a queue within the lane. It also compares images at different time intervals to determine if the vehicle's location has changed significantly, which helps identify lane congestion if the location change is below a certain threshold. The system can further process these images using an image hashing technique to generate location change values. Additionally, it includes a lane allotment processor that manages vehicle movement, detects regulating and serving objects, and determines lane allotment based on vehicle movement patterns, object presence, and other factors. This system can even fetch owner details from a database using license plate numbers to inform vehicles of their allotted lanes. Overall, it's a comprehensive system for efficient congestion monitoring and lane management.

In one of the embodiment as disclosed in the present disclosure discloses a system for congestion monitoring and management of vehicle in a lane following environment comprising an image capturing unit adapted to capture image of one or more lane at predefined intervals; a queuing

In another embodiment of the present disclosure the queuing processing unit is adapted to process the images at different time interval using an image hashing technique to generate a hash value of the image, to compare the hash values at different time intervals to generate the location change value.

In another embodiment of the present disclosure a lane allotment processor adapted to crop images of the detected vehicles in a particular lane, to determine a count of the detected vehicles which has moved in a current time interval in the particular lane, to process the count of the detected vehicles in previous time intervals and current time interval, and to determine a frequency of vehicle movement in a particular time interval in the particular lane. In another embodiment the lane allotment processor adapted to process the frequency of vehicle movement at the particular time interval and across more than one lane, and to determine a lane to be allotted to a vehicle approaching the lane following environment. In another implementation the lane allotment processor adapted to detect and crop images of at least regulating objects, or serving objects, or combination thereof, and to process the cropped images of the regulating objects and/or the cropped images of the serving objects along with the frequency of vehicle movement at the particular time interval and across more than one lane, and to determine a lane to be allotted to the vehicle approaching the lane following environment, wherein the regulating objects are defined as the objects installed to regulate movement of the vehicles in the lane, and the serving objects are defined as objects which supports in serving the vehicles.

In another embodiment the lane allotment processor is adapted to process the cropped images of the serving objects to determine a number of serving objects placed in particular lane at a given instance, and to compare the number of serving objects at the given instance and a number of serving objects prescribed to be present at the given instance, and to determine a shortfall of number of serving objects.

In another implementation the lane allotment processor is adapted to process the cropped images of the regulating objects across more than one instances, to compare the cropped images of the regulating objects across the instances and to determine an absence of one or more of the regulating objects, or malfunction in one or more of the regulating objects, or combination thereof.

Furthermore, the lane allotment processor is adapted to detect license plate number of the vehicle approaching the lane following environment, and optionally adapted to fetch an owner detail from a public database matching to the detected license plate number, to intimate a lane number allotted the vehicle approaching the lane following environment along with the license plate number or the owner detail. The lane allotment processor is adapted to process images of one or more lanes for various time intervals across similar time periods for plurality of days, and to determine a queuing pattern for the given time instance, and to process the queuing pattern along with the frequency of vehicle movement at the particular time interval and across more than one lane, and the cropped images of the regulating objects and/or the cropped images of the serving objects along with the frequency of vehicle movement at the particular time interval and across more than one lane, and to determine a lane to be allotted to the vehicle approaching the lane following environment

BRIEF DISCRIPTION OF DRAWINGS

The novel features and characteristics of the disclosure are set forth in the description. The disclosure itself, however, as well as a preferred mode of use, further objectives, and advantages thereof, will best be understood by reference to the following description of an illustrative embodiment when read in conjunction with the accompanying drawings. One or more embodiments are now described, by way of example only, with reference to the accompanying drawings wherein like reference numerals represent like elements and in which:

Fig 1 pertains to the base embodiment, and where the hashing technique is not disclosed as an embodiment of the present disclosure.

Fig 2 pertains to the specific embodiment of the base embodiment, which uses the hashing technique as an embodiment of the present disclosure.

Fig 3 pertains to using Lane allotment processor as an embodiment of the present disclosure.

Fig 4 pertains to the method of the base embodiment of the present disclosure.

DESCRIPTION

For the purpose of promoting an understanding of the principles of the invention, reference will now be made to the embodiment illustrated in the figures and specific language will be used to describe them. It will nevertheless be understood that no limitation of the scope of the present disclosure is thereby intended. Such alterations and further modifications in the illustrated system, and such further applications of the principles of the present disclosure as would normally occur to those skilled in the art are to be construed as being within the scope of the present invention.

It will be understood by those skilled in the art that the foregoing general description and the following detailed description are exemplary and explanatory of the present disclosure and are not intended to be restrictive thereof.

The terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such a process or method. Similarly, one or more sub-systems or elements or structures or components preceded by "comprises... a" does not, without more constraints, preclude the existence of other, sub-systems, elements, structures, components, additional sub-systems, additional elements, additional structures or additional components. Appearances of the phrase "in an embodiment", "in another embodiment" and similar language throughout this specification may, but not necessarily do, all refer to the same embodiment.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this present disclosure belongs. The system, methods, and examples provided herein are only illustrative and not intended to be limiting.

Embodiments of the present disclosure will be described below in detail with reference to the accompanying figures.

The present disclosure is being explained for a specific use case where the fuelling stations are monitored for congestion, and further a mechanism is placed to not just audit the reasons of congestion, but also to manage the congestion in the fuelling station. It is noted that same present disclosure is implementable in different use case scenario, such as Toll Plaza, Railway reservation, Airport check-in and security, etc.

Congestion on roadways is a growing concern in urban environments, leading to increased travel times, fuel consumption, and stress for commuters. According to the present disclosure the disclosed system leverages advanced image capturing and processing technology to detect and assess congestion levels in real-time.

Fig 1 pertains to a first embodiment of a system (1) which helps in determining the congestion in a queue of vehicles.

The system (1) includes an Image capturing unit (2) and a Queuing Processing Unit (3). The image capturing unit (2) is responsible for capturing images (4) of the lane at predefined intervals, typically at short time intervals to ensure real-time monitoring. In one of the implementations the image capturing unit incorporates an image capturing unit (2) equipped with high-resolution cameras strategically placed along one or more lanes. In a preferred embodiment, the image capturing unit captures one frame per minute, enabling the system (1) to monitor various locations with just one PTZ (Pan-Tilt-Zoom) camera. This PTZ camera, can pivot and zoom to cover multiple areas effectively.

The queuing processing unit (3), receives and processes the captured images (4) in real-time. The primary functions of the queuing processing unit (3) include: Vehicle Detection, Location Change Analysis and Congestion determination.

The queue processing unit (3) employs advanced computer vision algorithms to detect vehicles in the lane being followed. For location change analysis, the system (1) compares the images (4) at different time intervals to calculate a location change value (5). This value (5) reflects the extent of the change in the vehicle's position within the lane over time. By analyzing the location change value (5), the system (1) assesses whether the lane is congested or not. If the location change value (5) is less than a predefined threshold value (12), it indicates congestion. According to the present disclosure the queuing processing unit (3) uses object detection and tracking algorithms to identify and track vehicles within the lane. This allows the system (1) to keep a continuous record of vehicle movements within the monitored lane. The system (1) continuously compares the positions of detected vehicles in the lane over time by location change analysis. It calculates the location change value (5) for each vehicle, indicating the extent of movement within the lane. To assess congestion, the system (1) monitors the location change values (5) for all vehicles within the lane. If the majority of vehicles exhibit minimal location change (location change value < threshold value), the queue processing unit (3) identifies the lane as congested. Upon congestion detection, the system (1) can trigger various actions, such as notifying traffic management authorities, adjusting traffic signals, or providing congestion alerts to drivers via smart traffic signs or mobile apps.

In another embodiment, the capabilities of the queuing processing unit (3) are enhanced to detect categories (17) of each vehicle within the lane. The categories can be two-wheeler, three-wheeler, four-wheeler, etc. Within each category, sub categories can also be detected. For example, in 4 wheelers, different models of vehicles can also be categorized. The categorization can be carried out using advanced image recognition and machine learning techniques. The queuing processing unit (3) continues to process the images (4) captured by the image capturing unit (2) at predefined intervals which ensures that the system maintains a continuous and up-to-date record of the lane's traffic conditions.

Fig 2 pertains to a second embodiment of the system (2) where hashing technique is used for detecting the congestion. Most of the techniques and implementation of the system (1) of Fig. 2 remains same with respect to the system (1) of Fig 1. Difference lies in using a specialized technique for image processing. In Fig 2, the queuing processing unit (3) uses image hashing technique to process images captured at various time intervals and subsequently generate hash values (6) for each image. These hash values (6) are then employed to calculate location change values, providing a more accurate and robust assessment of congestion. This technique involves converting each captured image (4) into a unique hash value (6) through a mathematical process. The system calculates hash values (6) for images captured at different time intervals. These hash values (6) are then compared to identify similarities and differences between consecutive images. The degree of change between hash values is used to generate the location change value (5), reflecting the extent of vehicle movement within the lane over time.

Fig 3 pertains to another aspect of the system (1) which relates to allotment of a lane to a vehicle approaching the lane-following environment. According to Fig 3, the system (1) also employs a lane allotment processor (7) to capture and process images (4) of vehicles detected within a specific lane by cropping the detected vehicles to generate a cropped images (25) of the vehicle. These cropped images (25) of vehicles serve as the basis for determining a count (16) of vehicles that have moved within that lane during a specified time interval. This count (16), which encompasses both the current time interval and data from previous time intervals, plays a pivotal role in calculating a frequency (8) of vehicle movement within that particular lane.

In another embodiment, the lane allotment processor (7) can process not only the frequency (8) of vehicle movement within a single lane but also across multiple lanes. As vehicles approach the lane-following environment, the processor (7) determines the most suitable lane number (18) to allot to each vehicle, ensuring optimal traffic flow and organization. While allotting a lane number (18), the lane allotment processor (7) also considers information about the serving objects and regulating objects in a lane. The lane allotment processor (7) is enabled to detect and crop images (11) of regulating objects, crop images (10) of serving objects, or a combination of both. Regulating objects, designed to govern vehicle movement within the lane, and serving objects, which assist vehicles, are vital components. The lane allotment processor (7) uses these images (10, 11), combined with data on vehicle movement frequency (8) at a particular time interval and across more than one lane, to make precise determinations about the appropriate lane number (18) to allocate for vehicles approaching the lane-following environment.

In it is pertinent to note that, in an alternate embodiment, the lane allotment processor (7) may use just the frequency (8) at a particular time interval across more than one lane alone to determine the lane number (18).

The lane allotment processor (7) is able to process the cropped images (10) of the serving objects to assess a number (22) of serving objects placed within a specific lane at a given instance. By comparing this count (22) to a prescribed number (23) of serving objects, the system (1) can identify any shortfalls (24) of the serving objects, providing valuable insights for maintenance and management. In one specific embodiment, such determination about shortfalls (24) of the serving objects may not be desired.

The lane allotment processor (7) processes cropped images (11) of regulating objects across multiple instances, allowing it to detect an absence (20) of one or more of the regulating objects, malfunctions (19) in one or more of the regulating objects, or a combination of both. This proactive approach ensures that the lane-following environment operates smoothly and safely. In one specific embodiment, such determination about absence (20) or malfunction (19) of the regulating objects may not be desired.

The lane allotment processor (7) is further enabled to detect license plate numbers (13) of approaching vehicles by using images (4) on application of image processing techniques. Additionally, the lane allotment processor (7) can fetch owner details (14) from a public database (21), enabling the system (1) to communicate the allotted lane number (18) along with the license plate number (13) or owner details (14) on a display, or even in some scenario to a mobile device of the user of the vehicle using the owners’ details (14). This feature enhances the overall experience for vehicle owners and aids in traffic management.

According to another embodiment, the lane allotment processor (7) processes images (4) of multiple lanes over various time intervals and establishes a queuing pattern (15) across the time intervals. By combining this data (15) with vehicle movement frequency (8) and information (11, 10) on regulating and serving objects the lane allotment processor (7) determines the most appropriate lane number (18) for vehicles approaching the lanefollowing environment.

Fig 4 illustrates a method for determining congestion, and further allotting appropriate lane to a vehicle approaching the lane following environment.

Firstly, an image is captured using an image capturing device. Such image capturing device can be a video camera, like CCTV camera, or any other image capturing means which can capture images of the scene of a queue in a premise where congestion is to be monitored.

The captured image is processed through a object detection module. Object detection is a phenomenon in computer vision that involves the detection of various objects in digital images or videos. Some of the objects detected include people, cars, chairs, stones, buildings, and animals. For the current use case the primary object detected are vehicles. In a fuelling station, the queuing objects are the vehicles. In other use cases, the queuing objects can be humans or robots, etc. The object detection module detects the vehicle as queuing object. In addition to the queuing object, the object detection module is further configured to capture serving objects which serves queuing objects. In the current use case, the fuel station attendants are the serving objects. The shortage of serving staff or serving objects may lead to improper serving of the queuing objects, which can further lead to congestion. The congestion can further be carried out due to certain other regulating objects which are relied upon or followed by the queuing objects or the serving objects. In a fuelling station, one such regulating objects are stoppers which are metal objects positioned to stop fuelling vehicles from moving while fuel hose is attached to the vehicle. The object detection module is further configured to identify these congestion creating objects too. It is to be noted that the queuing objects may be of different category, and the object detection module is also configured to identify category of the queuing objects. For example, in the current use case, a vehicle can be a four-wheeler or a two-wheeler, or a heavy vehicle or a light vehicle, or a petrol fuelled vehicle or a diesel fuelled vehicle. Each of these vehicles could belong to a different queue, and wrong entry of such vehicle in a queue may lead to congestion.

Further, the images bearing queuing objects once determined, shall be sent to a queuing processor, which is configured to crop the image to crop out the queuing object, which in current use case is a vehicle. Thereafter, the queuing processor is configured to calculate a hash of the queuing object. Each of such hash calculated shall be stored in a memory unit along with there timelines. The queuing processor is further configured to compare hashes for a two successive pre-defined period to identify movement of the vehicles. The comparison results in a change output. The change output can refer to a positive change, if the comparison results in a mismatch, which means the vehicles are moving and the lane at which the image capturing device is kept is congestion free. The change output can refer to a negative change, if the hash is matched.

The system also includes a lane allotment processor which receives images of the cropped queuing objects, the change output, information on serving objects, and information on regulating objects. The lane allotment processor processes the cropped images of the queuing objects to determine a count of queuing objects which has moved in a predefined period of time. Also, information on change output for a predefined period of time shall be used by the lane allotment processor to determine how frequent the changes are occurring in the queue. Using this information, the lane allotment processor shall alot lane number to a newly entered vehicle which has entered the premises. While making the lane allotment, the lane allotment processor also uses the information on serving objects in the lane s, and information on the regulating objects placed in the lane. Also, the lane allotment processor generates an output related to sufficiency of the serving objects in the lane, and presence of regulating objects in the lane.

The lane allotment processor is also configured to detect license plate for referring them while allotting the numbers, or to dig in details of vehicle owners from public database for referring to the owner while allotting the lane. The detected license number can be used for any other compliance purposes too. The lane allotment processor captures a queuing pattern from the data captured about the vehicle movement, and may further use this along with above mentioned data, for allotting lane to the vehicle approaching the premises for service.

The system further includes an audit processor which receives information on the serving objects and regulating objects. The audit processor processes the serving objects information to identify if there are missing serving objects, and lane s on which the serving objects are missing or present in lesser numbers with respect to the allotted serving objects. The audit processor also processes information on regulating objects and determines if there are missing regulating objects or if there are wrongly placed congestion created objects. The output from the audit processor is helpful to take corrective measures to make decision making for reducing congestion creating instances.

With help of the above solution, the fuel stations are able to achieve complete operational oversight from their existing CCTV systems. Some of the key features are complete congestion, utilization, and operational oversight of the fuelling outlets, available through a dedicated analytics dashboard, API endpoint for customer touch points, Shift-wise attendant count using uniform, Lane -wise utilization, Cumulative vehicle count, Commercial v/s private vehicle count, Stopper placement detection, Ad-hoc reports for employees, Listing CCTV downtimes, Email notifications and triggers.

In the current invention, custom models of computer vision (deep learning) algorithms have been trained, and are being used specifically for congestion and queue management at fuel stations. The input data for training the algorithm was annotated images on CCTV footage from the fuel stations. For more categories, the images corresponding to that particular category can be annotated (example, an oil tanker for a specific client).

The current system if further equipped to provide fuel companies with retail insights, custom metrics, and complete operational oversight. A dashboard can be provided which shows output related to crucial congestion, operational and general compliance metrics.

It is to be noted that the entire system is event-driven. As things change and move on the ground, relevant personnel are kept in the loop, so they can further trigger actions or respond to events. Some key features live on the system of the present disclosure includes shift-wise attendant count, lane -wise utilization, cumulative vehicle count, commercial v/s private vehicle count, stopper placement detection, ad-hoc reports for fuel station employees, listing CCTV downtimes, and email notifications. The current solution can be further extended to any other businesses or processes which involves queue management and where the congestion is required to be resolved.

Reference Numerals:

1. System

2. Image capturing unit

3. Queuing processing unit

4. Image

5. Location change value

6. Hash value

7. Lane allotment processor

8. Frequency of vehicle movement

9. Congestion in the lane

10. Cropped images of serving objects

11. Cropped images of regulating objects

12. Threshold value

13. License plate number

14. Owner detail

15. Queuing pattern

16. Count of the detected vehicles

17. Category of the vehicle

18. Lane number

19. Malfunction in one or more of the regulating objects

20. Absence of one or more of the regulating objects

21. Public database

22. Number of serving objects

23. Number of serving objects prescribed to be present at the given instance

24. Shortfall of number of serving objects

25. Cropped images of detected vehicles

26. Memory unit

Claims

We Claim:

1. A system (1) for congestion monitoring and management of vehicle in a lane following environment comprising: an image capturing unit (2) adapted to capture image (4) of one or more lane at predefined intervals; a queuing processing unit (3) is adapted to: receive and process the image(4), to detect vehicles in a queue being followed in the lane, to compare the images (4) at different time intervals for determining a location change value (5) for differentiating change of a location of the vehicle in the lane at different time intervals, and to determine a congestion (9) in the lane if the location change value (5) is less than a threshold value (12).

2. The system (1) as claimed in claim 1, wherein the queuing processing unit (3) is adapted to process the images (4) at different time interval using an image hashing technique to generate a hash value (6) of the image, (4) to compare the hash values(6) at different time intervals to generate the location change value (5).

3. The system (1) as claimed in claim 1 comprising a lane allotment processor (7) adapted to crop images of the detected vehicles (25) in a particular lane, to determine a count (16) of the detected vehicles which has moved in a current time interval in the particular lane, to process the count of the detected vehicles (16) in previous time intervals and current time interval, and to determine a frequency of vehicle movement (8) in a particular time interval in the particular lane.

4. The system (1) as claimed in claim 3, wherein the lane allotment processor (7) adapted to process the frequency of vehicle movement (8) at the particular time interval and across more than one lane, and to determine a lane number (18) to be allotted to a vehicle approaching the lane following environment.

5. The system(l) as claimed in claim 4, wherein the lane allotment processor (7) adapted to detect and crop images (10, 11) of at least regulating objects, or serving objects, or combination thereof, and to process the cropped images (11) of the regulating objects and/or the cropped images (10) of the serving objects along with the frequency (8) of vehicle movement at the particular time interval and across more than one lane, and to determine the lane number (18) to be allotted to the vehicle approaching the lane following environment, wherein the regulating objects are defined as the objects installed to regulate movement of the vehicles in the lane, and the serving objects (10) are defined as objects which supports in serving the vehicles. The system (1) as claimed in claim 5, wherein the lane allotment processor (7) is adapted to process the cropped images of the serving objects (10) to determine a number (22) of serving objects placed in particular lane at a given instance, and to compare the number (22) of serving objects at the given instance and a number of serving objects prescribed to be present at the given instance (23), and to determine a shortfall of number (24) of serving objects. The system (1) as claimed in claim 5, wherein the lane allotment processor (7) is adapted to process the cropped images (11) of the regulating objects across more than one instances, to compare the cropped images (11) of the regulating objects across the instances and to determine an absence (20) of one or more of the regulating objects, or malfunction (19) in one or more of the regulating objects, or combination thereof. The system (1) as claimed in claims 5, wherein the lane allotment processor (7) is adapted to detect license plate number (13) of the vehicle approaching the lane following environment, and optionally adapted to fetch an owner detail (14) from a public database(21) matching to the detected license plate number (13), to intimate a lane number (18) allotted to the vehicle approaching the lane following environment along with the license plate number (13) or the owner detail (14). The system (1) as claimed in claim 5, wherein the lane allotment processor (7) is adapted to process images (4) of one or more lanes for various time intervals across similar time periods for plurality of days, and to determine a queuing pattern (15) for the given time instance, and to process the queuing pattern (15) along with the frequency of vehicle movement (8) at the particular time interval and across more than one lane, and the cropped images (11) of the regulating objects and/or the cropped images (10) of the serving objects along with the frequency of vehicle movement (8) at the particular time interval and across more than one lane, and to determine a lane number(18) to be allotted to the vehicle approaching the lane following environment.

10. The system(l) as claimed in claim 1, wherein the queuing processing unit (3) is adapted to process the image (4) of the one or more lane at predefined intervals, and to detect a category (17). of the vehicle.

11. A method for congestion monitoring and management of vehicle in a lane following environment comprising: capturing image of one or more lane at predefined intervals by an image capturing unit; receiving and processing of the image by a queuing processing unit, detecting vehicles in a queue being followed in the lane by the queuing processing unit, compare the images at different time intervals by the queuing processing unit, and determining a location change value for differentiating change of a location of the vehicle in the lane at different time intervals, determining a congestion in the lane, by the queuing processing unit, if the location change value is less than a threshold value.