SYSTEM AND METHOD FOR ANALYSING FREE STREET SPACES AND PROVIDING RECOMMENDATIONS USING ARTIFICIAL INTELLIGENCE

Abstract

The present disclosure provides a system (106) and a method (900) for analyzing free road space and providing recommendations using artificial intelligence. The system (106) simultaneously detects one or more oncoming vehicles in order to determine a trajectory associated with the oncoming vehicle(s). Based on the determined trajectory, the system (106) predicts a meeting point associated with the vehicle (102) and the one or more oncoming vehicles. In response to a determination that the vehicle (102) and the one or more oncoming vehicles are expected to collide, the system (106) determines one or more spaces for maneuvering the vehicle (102) based on a classification of the one or more spaces. The system (106) recommends the classified one or more spaces for maneuvering the vehicle (102).The system (106) transmits one or more warnings associated with the recommendation to prevent the collision.

Description

This disclosure relates generally to the field of advanced driver assistance systems (ADAS). In particular, this disclosure relates to a system and a method for analyzing free road space and providing recommendations using artificial intelligence. Driving on narrow or congested roads can make it difficult for vehicles to pass each other. In such cases, a vehicle must reverse or move forward, or temporarily park to allow another vehicle to pass. Conventional systems use automatic reversing assistance or automatic parking assistance. Furthermore, conventional narrow-road detection systems may use devices that provide information about the availability of a passing space. Additionally, automatic reversing assistance systems are unable to provide suitable solutions when a road dimension (width) remains constant over a long distance. Conventional systems using automatic parking assistance can only help locate a parking space if one is actually available. Patent specification US10953878B2 discloses a method for autonomously driving a vehicle through a narrow passage. The method includes detecting the narrow passage and an oncoming vehicle approaching within the narrow section, and determining the speed of the oncoming vehicle based on speed data acquired by the sensors. The method includes predicting the oncoming vehicle's response based on the determined speed and autonomously maneuvering the respective vehicle through the narrow passage. There is therefore a great need to provide an improved system and procedure that overcomes the problems associated with conventional systems and provides an efficient system that allows for better handling when crossing in narrow road passages. A general subject of the present disclosure is to provide a system and a method for analyzing free road space and providing recommendations using artificial intelligence, which detects one or more oncoming vehicles in real time in order to determine a trajectory associated with the one or more oncoming vehicles; Another objective of the present disclosure is to provide a system that, based on the specified trajectory, predicts a meeting point associated with the vehicle and the one or more oncoming vehicles. Another objective of the present disclosure is to provide a system which, in response to a determination that the vehicle and one or more oncoming vehicles are expected to collide, determines one or more spaces for maneuvering the vehicle based on a classification of the one or more spaces. Another objective of the present disclosure is to provide a system that recommends one or more classified spaces for maneuvering the vehicle. Another objective of the present disclosure is to provide a system that transmits one or more warnings associated with the recommendation and prevents the collision. Aspects of this disclosure generally relate to the field of advanced driver assistance systems (ADAS). In particular, this disclosure relates to a system and a method for analyzing free road space and providing recommendations using artificial intelligence. In one aspect, the present disclosure relates to a system for analyzing available road space and providing recommendations. The system includes a processor communicating with a vehicle's electronic control unit (ECU). A memory is functionally coupled to the processor, storing instructions which, when executed by the processor, cause it to simultaneously detect one or more oncoming vehicles in order to determine a trajectory associated with the one or more oncoming vehicles. Based on the determined trajectory, the processor predicts a meeting point between the vehicle and the one or more oncoming vehicles.In response to a determination that the vehicle and one or more oncoming vehicles are expected to collide, the processor identifies one or more spaces in which to maneuver the vehicle based on a classification of those spaces. The processor recommends the classified one or more spaces for maneuvering the vehicle. The processor transmits one or more warnings associated with the recommendation to prevent the collision. In one embodiment, the processor can be configured to determine the one or more spaces in order to receive information about the vehicle's surroundings. The processor can be configured to extract this information to determine the one or more spaces associated with the vehicle's surroundings. The processor can be configured to record the one or more parking spaces in an array and to classify the recorded parking spaces as a full parking space, half parking space, or partial parking space. In one embodiment, the processor can be configured to classify one or more rooms by recording one or more geographic coordinates associated with one or more rooms. The processor can be configured to record one or more images associated with the recorded rooms. The processor can be configured to determine one or more parameters associated with the recorded rooms. The processor can be configured to analyze the one or more geographic coordinates, the one or more images, and the one or more parameters using a technique to determine the one or more classified rooms. In one embodiment, the processor can be configured to determine, prior to predicting the meeting point, the trajectory associated with the one or more oncoming vehicles based on a relative speed associated with the vehicle and the one or more oncoming vehicles. The processor can be configured to determine a road width associated with the trajectory. The processor can be configured to compare the road width with one or more dimensions associated with the one or more oncoming vehicles and the vehicle. In response to this determination, the processor can be configured to determine, from the classified one or more spaces, a minimum space required for maneuvering the vehicle.The processor can be configured to recommend a first room from the classified one or more rooms for maneuvering the vehicle and preventing collision. In one embodiment, the processor, in order to recommend the classified space(s), can be configured to determine a location associated with the classified space(s). The processor can be configured to determine the distance of the classified space(s) from the vehicle. The processor can be configured to determine one or more images associated with the classified space(s). The processor can be configured to determine one or more types of spaces available within the classified space(s). In one aspect, the present disclosure relates to a method for analyzing available road space and providing recommendations. The method involves the simultaneous detection, by a processor associated with a system, of one or more oncoming vehicles in order to determine a trajectory associated with the one or more oncoming vehicles. The method includes the prediction, by the processor, of an encounter point between the vehicle and the one or more oncoming vehicles.The procedure involves, in response to a determination that the vehicle and one or more oncoming vehicles are expected to collide, the processor determining one or more spaces for maneuvering the vehicle based on a classification of those spaces; the procedure recommending one or more classified spaces for maneuvering the vehicle; and the procedure transmitting one or more warnings associated with the recommendation, which prevent the collision. In one embodiment, the method for determining, by the processor, one or more spaces may involve receiving information associated with the vehicle's environment. The method may involve extracting information from the processor to determine the one or more spaces associated with the vehicle's environment. The method may also involve recording, by the processor, the one or more spaces in an array and classifying the recorded spaces into a full parking space, a half parking space, or a partial parking space. In one embodiment, the method for classifying one or more spaces by the processor may involve recording one or more geographic coordinates associated with one or more spaces. The method may involve recording one or more images associated with the recorded spaces. The method may involve determining one or more parameters associated with the recorded spaces. The method may involve analyzing the geographic coordinates, the images, and the parameters by the processor to determine the one or more classified spaces. In one embodiment, the method for performing predictions of the meeting point by the processor may include determining the trajectory associated with the one or more oncoming vehicles based on a relative velocity associated with the vehicle and the one or more oncoming vehicles. The method may include determining a road width associated with the trajectory. The method may include comparing a road width with one or more dimensions associated with the one or more oncoming vehicles and the vehicle. As a response to this determination, the method may include determining a minimum space from the classified one or more spaces required for maneuvering the vehicle.The method can involve the processor recommending a first room from the classified one or more rooms for maneuvering the vehicle and avoiding a collision. In one embodiment, the method for recommending the classified room(s) can include the processor determining a location associated with the classified room(s). The method can also include the processor determining the distance of the classified room(s) from the vehicle. Furthermore, the method can include the processor determining one or more images associated with the classified one or more rooms. Finally, the method can include the processor determining one or more types of rooms available among the classified one or more rooms. The accompanying drawings are included to provide a more comprehensive understanding of the present disclosure and form part of this description. The drawings illustrate exemplary embodiments of the present disclosure and, together with the description, serve to explain the principles of the present disclosure. Fig. 1 illustrates an exemplary architecture 100 of a proposed system 106 according to an embodiment of the present disclosure. Fig. 2 illustrates an exemplary block diagram 200 of the proposed system 106 according to an embodiment of the present disclosure. Fig. 3 illustrates an exemplary schematic diagram 300, which represents a mapping of free street spaces by the proposed system 106 according to an embodiment of the present disclosure.Figure 4 illustrates a high-level flowchart of an exemplary method 400 implemented by the proposed system 106 according to an embodiment of the present disclosure. Figure 5 illustrates a flowchart of an exemplary method 500 for recommending free roadside spaces by the proposed system 106 using a convolutional neural network (CNN) technique according to an embodiment of the present disclosure. Figure 6 illustrates an exemplary schematic diagram 600 providing network details of the CNN technique according to an embodiment of the present disclosure. Figure 7 illustrates an exemplary schematic diagram 700 representing the storage of free roadside spaces in an arrangement by the proposed system 106 according to an embodiment of the present disclosure.Figure 8 illustrates an exemplary schematic diagram 800 for object detection and parking space recommendation, which are implemented by the proposed system 106 according to an embodiment of the present disclosure. A detailed description of embodiments of the disclosure, illustrated in the accompanying drawings, follows. The embodiments are described in sufficient detail to clearly convey the disclosure. However, the intention is not to limit foreseeable variations of embodiments with the necessary level of detail; on the contrary, the intention is to cover all modifications, correspondences, and alternatives that fall within the spirit and scope of the present disclosure as defined by the attached claims. Embodiments of the present disclosure generally relate to the field of advanced driver assistance systems (ADAS). In particular, the present disclosure relates to a system and a method for analyzing free road space and providing recommendations using artificial intelligence. Various embodiments of the present disclosure are explained in detail with reference to Figures 1-8. Fig. 1 illustrates an exemplary architecture 100 of a proposed system 106 according to an embodiment of the present disclosure. As illustrated in Fig. 1, in one embodiment the system 106 can be connected to one or more vehicles (102-1, 102-2...102-N) via a network 104. A person skilled in the art will understand that the one or more vehicles (102-1, 102-2...102-N) can also be referred to as the vehicles 102 or the vehicle 102 throughout this disclosure. In one embodiment, the network 104 may, by way of example but not limitation, include at least one section of one or more networks having one or more nodes that transmit, receive, forward, generate, buffer, store, route, switch, process, etc., one or more messages, packets, signals, waves, voltage or current levels, a combination thereof. The network 104 may, by way of example but not limitation, also include one or more wireless networks, wired networks, an internet, an intranet, a public network, a private network, a packet-switched network, a circuit-switched network, an ad-hoc network, an infrastructure network, a public switched telephone network (PSTN), a cable network, a mobile network, a satellite network, a fiber optic network, or a combination thereof. In one embodiment, the system 106 focuses on vehicles on narrow roads and records clearances surrounding both sides of the vehicle 102. These recorded clearances are used to maneuver the vehicle 102, allowing oncoming vehicles to easily pass. The recorded clearances are classified based on the available space and the dimensions of the vehicle 102. Furthermore, the system 106 recommends the most suitable clearance when two vehicles cannot pass each other. The system 106 provides multiple recorded clearances, allowing the driver to switch between a first recommended clearance and a second. From the classified parking spaces, the system 106 recommends the nearest and most suitable parking space. Fig. 2 illustrates an exemplary block diagram 200 of the proposed system 106 according to an embodiment of the present disclosure. Referring to Fig. 2, the system 106 can comprise one or more processors 202, which may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, logic circuits, and / or any devices that process data based on operating instructions. Among other capabilities, the one or more processors 202 can be configured to retrieve and execute computer-readable instructions stored in a memory 204 of the system 106. The memory 204 can be configured to store one or more computer-readable instructions or routines in a non-transitory, computer-readable storage medium, which can be retrieved and executed to create or share data packets via a network service. The memory 204 can comprise any non-transitory storage device, such as...a volatile memory such as random access memory (RAM) or a non-volatile memory such as a erasable programmable read-only memory (EPROM), flash memory or the like. In one embodiment, the system 106 may include one or more interfaces 206. The interface(s) 206 may comprise a variety of interfaces, such as interfaces for data input / output (I / O) devices, storage devices, and the like. The interface(s) 206 may also provide a communication path for one or more components of the system 106. Examples of such components include, but are not limited to, processing machine(s) 208 and a database 210, wherein the processing machine(s) 208 may include, but are not limited to, a data input machine 212 and one or more other machines 214. In one embodiment, the other machine(s) 214 may include, but are not limited to, a data management machine, an input / output machine, and a notification machine. In one embodiment, the processing machine(s) 208 can be implemented as a combination of hardware and programming (e.g., programmable instructions) to implement one or more functions of the processing machine(s) 208. In the examples described here, such combinations of hardware and programming can be implemented in various ways. For example, the programming for the processing machine(s) 208 consists of processor-executable instructions stored on a non-transient, machine-readable storage medium, and the hardware for the processing machine(s) 208 can include a processing resource (e.g., one or more processors) to execute such instructions. In the present examples, the machine-readable storage medium can store instructions which, when executed by the processing resource, implement the processing machine(s) 208.In such examples, System 106 may comprise the machine-readable storage medium on which the instructions are stored and the processing resource for executing the instructions, or the machine-readable storage medium may be separate but accessible to System 106 and the processing resource. In other examples, the processing module(s) 208 may be implemented by electronic circuits. In one embodiment, the processor 202 can receive data associated with one or more oncoming vehicles via the data input machine 212. The processor 202 can store the data in the database 210. Simultaneously, the processor 202 can detect the one or more oncoming vehicles in order to determine a trajectory associated with them. Based on this determined trajectory, the processor 202 can predict an encounter point associated with the vehicle 102 and the one or more oncoming vehicles. Prior to predicting the encounter point, the processor 202 can determine the trajectory associated with the one or more oncoming vehicles based on a relative speed associated with the vehicle 102 and the one or more oncoming vehicles.Processor 202 can determine a road width associated with the trajectory. Processor 202 can compare the road width with one or more dimensions associated with one or more oncoming vehicles and vehicle 102. In response to this determination, Processor 202 can determine a minimum space from the classified one or more spaces required to maneuver vehicle 102. Processor 202 can recommend a first space from the classified one or more spaces for maneuvering the vehicle and preventing a collision. Processor 202 can recommend the nearest and most suitable parking space from the classified parking spaces. In one embodiment, the processor 202 can, in response to the determination that the vehicle 102 and the one or more oncoming vehicles are expected to collide, determine one or more spaces in order to maneuver the vehicle 102 based on the classification of the one or more spaces; In one embodiment, the processor 202 can receive information associated with the environment of the vehicle 102 to determine one or more spaces. The processor 202 can extract this information to determine the one or more spaces associated with the environment of the vehicle 102. The processor 202 can record the one or more spaces in an array and classify the recorded spaces. In one embodiment, the one or more parking spaces are classified into a full parking space, half parking space, or partial parking space using a CNN network. The one or more parking spaces can be subdivided into a small, a medium, and a full parking space. The Processor 202 can record one or more geographic coordinates associated with one or more spaces. The Processor 202 can record one or more images associated with the recorded spaces. The Processor 202 can determine one or more parameters associated with the recorded spaces. The Processor 202 can analyze the one or more geographic coordinates, the one or more images, and the one or more parameters using a specific technique to determine the one or more classified spaces. In one embodiment, the processor 202 can recommend one or more classified spaces for maneuvering the vehicle 102. The processor 202 can determine a location associated with the classified space(s) in order to recommend the classified space(s). The processor 202 can determine a distance of the classified space(s) from the vehicle 102. The processor 202 can determine one or more images associated with the classified space(s). The processor 202 can determine one or more types of spaces available under the classified space(s). Furthermore, the processor 202 can transmit one or more warnings associated with the recommendation to prevent a collision. Fig. 3 illustrates an exemplary schematic diagram 300, which represents a recording of free street spaces by the proposed system 106 according to an embodiment of the present disclosure. As illustrated in Fig. 3, in one embodiment, the system 106 can simultaneously detect one or more oncoming vehicles in order to determine a trajectory associated with the oncoming vehicle(s). The system 106 can use a sensor field of view to determine the vehicle's surroundings. The sensor field of view can be associated with the vehicle moving forward. In one embodiment, the system 106 can predict, based on the determined trajectory, an encounter point associated with the vehicle and the one or more oncoming vehicles. In response to a determination that the vehicle and the one or more oncoming vehicles are expected to collide, it determines one or more spaces (302-1, 302-2...302-N) for maneuvering the vehicle based on the classification of the one or more spaces (302-1, 302-2...302-N). The system 106 can further classify the one or more parking spaces (302-1, 302-2...302-N) as a full parking space, half parking space, or partial parking space using a CNN network. Fig. 4 illustrates a higher-level flowchart of an exemplary method 400 implemented by the proposed system 106 according to an embodiment of the present disclosure. As illustrated in Fig. 4, the overall flowchart may include the following steps. In step 402: System 106 can initiate the process. In step 404: System 106 can receive information from a data acquisition module and perform a precondition check. In step 406: System 106 can determine whether an object has been detected. In response to a negative determination, System 106 can proceed with object detection and performing the precondition check. In step 408: In response to a positive determination in step 406, System 106 can activate the vehicle perception unit. In step 410: System 106 can predict the encounter point and calculate road and object dimensions. In step 412: System 106 can determine whether the object has a clear path. Based on a positive determination, System 106 can proceed to step 406. In step 414: In response to a negative determination in step 412, System 106 can determine whether the oncoming vehicle has stopped or is reversing to allow the ego vehicle / vehicle to pass. Based on a positive determination, System 106 can proceed to step 410. In step 416: In response to a negative determination in step 414, System 106 can determine whether there is clear space in a forward direction before the meeting point. In step 418: In response to a negative determination in step 416, System 106 can analyze the required minimum space and compare the minimum speed with the recorded clear space.In step 420: The system 106 can perform object detection and storage of free space data based on the information received from the data collector module and the precondition check from step 404. In step 422: System 106 can classify the detected free spaces. In step 424: System 106 can issue a notification via the user interface (UI) recommending the best free spaces. In step 426: System 106 can determine whether the driver has acknowledged the notification. In response to a negative determination, System 106 can proceed to step 424. In step 428: In response to a positive determination in step 426, the driver can begin maneuvering. In step 430: System 106 can determine whether a gap is still free. In response to a negative determination, System 106 can proceed to step 424. In step 432: In response to a positive determination in step 430, the driver can maneuver the vehicle. Fig. 5 illustrates a flowchart of an exemplary method 500 for recommending free roadside spaces by the proposed system 106 using a convolutional neural network (CNN) technique according to an embodiment of the present disclosure. As illustrated in Fig. 5, the flowchart may include the following steps. In step 502: The system 106 can use an HD map to determine whether a narrow road is detected while the vehicle is moving forward. If the determination is negative, the system 106 can continue detecting narrow roads. In step 504: In response to a positive determination in step 502, the system 106 can use a camera to take pictures of empty spaces on both sides of the narrow road. In step 506: System 106 can use a CNN-based architecture to extract features from the captured images. In step 508: System 106 can record the information associated with the captured images in an array structure. In step 510: System 106 can generate an array that includes one or more spaces / gaps. In step 512: System 106 can iterate through the recorded free spaces and recommend the most suitable space for temporary parking or maneuvering. In step 514: System 106 can determine a minimum distance required to park the vehicle and allow one or more oncoming vehicles to pass. In step 516: System 106 can predict the meeting point of the vehicle and the one or more oncoming vehicles and further determine whether the vehicle is able to safely pass the one or more oncoming vehicles on the narrow road. Based on a positive determination, the system can proceed to step 514. In step 518: In response to a negative determination in step 514, System 106 can continue environmental perception using sensors. Fig. 6 illustrates an exemplary schematic diagram 600, which provides network details of the CNN technique according to an embodiment of the present disclosure. As illustrated in Fig. 6, the CNN method in one embodiment can include the following steps: In step 602: The System 106 can receive N camera frames per time. In step 604: The System 106 can generate an adaptive average pool based on the received N camera frames per time / dataset. In step 606: The System 106 can use an image data generator to divide the dataset into a training set, a validation set, and a test set. In step 608: The System 106 can generate a convolutional 2D set from the dataset. In step 610: The System 106 can use an activation ReLU (rectified linear unit) to process the dataset. In step 612: The System 106 can perform a maxpooling 2D operation to further process the dataset.In step 614: System 106 can generate the convolutional 2D set from the data set produced by the Maxpooling 2D operation. In step 616: System 106 can use the activation ReLU to further process the data set from step 614. In step 618: System 106 can perform the Maxpooling 2D operation on the data set obtained in step 616. In step 620: System 106 can use a flattening plane to convert all resulting 2D arrays from aggregated feature maps into a single long continuous linear vector. In step 622: System 106 can perform a densification layer operation on the single long continuous linear vector. In step 624: System 106 can perform another densification layer operation on the single long continuous linear vector from step 622.In step 626: System 106 can use a softmax layer to convert the logits of the last layer of the CNN network into probability distributions. System 106 can categorize the one or more spaces based on the processed information into a non-parking space 626, a small parking space 628, a medium parking space 630, and a full parking space 632. Fig. 7 illustrates an exemplary schematic diagram 700, which represents a storage of the free roadside spaces in an arrangement by the proposed system 106 according to an embodiment of the present disclosure. As illustrated in Fig. 7, in an embodiment 702, the system 106 can record the one or more parking spaces in an array of structures (the array size can be determined based on the boundary for storing parking spaces). When a new parking space (from the one or more spaces) is identified, the new parking space can be stored in an earliest index of an array (704), and the existing parking space information can be moved to the next index (704). The parking space information can include the location of the parking space (longitudinal and lateral coordinates), a real-time image associated with the parking space, a classification of the parking space, four X- and Y-corner coordinates associated with the parking space, a confidence score associated with the parking space, and a parking space type. Fig. 8 illustrates an exemplary schematic diagram 800 for object detection and parking space recommendation implemented by the proposed system 106 according to an embodiment of the present disclosure. In one embodiment, when the system 106 identifies a vehicle traveling forward and unable to pass an oncoming vehicle, it can record images associated with the oncoming vehicle and the road dimensions as environmental perception. If passing is not possible, the system 106 can suggest the nearest and best parking space (from one or more available spaces). The system 106 can provide the current location of the parking space, its distance from the vehicle's current position, and a real-time image of the parking space. Furthermore, the system 106 can classify the parking space as a full parking space, a half parking space, or a partial parking space. If the driver selects a first parking space and, while reversing, finds that the first space is occupied, the driver can always select a second space.Choose from the other stored available spaces (one or more parking spaces) to maneuver or park the vehicle. As illustrated in Fig. 8, in an embodiment 802, the system 108 can identify a minimum distance required to temporarily park the vehicle to allow one or more oncoming vehicles to pass. Furthermore, the system 106 can iterate through the recorded free spaces 804 to recommend the nearest and most suitable space for temporary parking. While the foregoing describes various embodiments of the disclosure, other and further embodiments of the invention may be conceivable without deviating from the fundamental scope of the invention. The scope of the disclosure is defined by the patent claims below. The disclosure is not limited to the described embodiments, variants, or examples that enable a person with normal technical knowledge to produce and use the disclosure when combined with the information and knowledge available to that person. The present disclosure provides a system that detects one or more oncoming vehicles in real time in order to determine a trajectory associated with the one or more oncoming vehicles. The present disclosure provides a system that, based on the specified trajectory, predicts a meeting point associated with the vehicle and the one or more oncoming vehicles. In response to a determination that the vehicle and one or more oncoming vehicles are expected to collide, the present disclosure provides a system that, based on a classification of the one or more spaces, determines one or more spaces for maneuvering the vehicle. The present disclosure provides a system that recommends one or more classified spaces for maneuvering the vehicle. The present disclosure provides a system that transmits one or more warnings associated with the recommendation and prevents the collision. QUOTES INCLUDED IN THE DESCRIPTION This list of documents cited by the applicant was automatically generated and is included solely for the reader's convenience. The list is not part of the German patent or utility model application. The DPMA accepts no liability for any errors or omissions. Cited patent literature US 10953878B2

[0003]

Claims

System (106) for analyzing free road space and providing recommendations, the system (106) comprising: a processor (202) communicating with an electronic control unit (ECU) of a vehicle (102); a memory (204) functionally coupled to the processor (202), the memory (204) storing instructions which, when executed by the processor (202), cause the processor (202) to: simultaneously detect one or more oncoming vehicles in order to determine a trajectory associated with the one or more oncoming vehicles; predict, based on the determined trajectory, an encounter point associated with the vehicle (102) and the one or more oncoming vehicles;in response to a determination that the vehicle (102) and the one or more oncoming vehicles are expected to collide; determining one or more spaces in which to maneuver the vehicle (102) based on the classification of the one or more spaces; recommending the one or more classified spaces for maneuvering the vehicle (102); and transmitting one or more warnings associated with the recommendation that prevent the collision. System (106) according to claim 1, wherein the processor (202) is configured to determine the one or more spaces by: receiving information associated with the environment of the vehicle (102); extracting the information to determine the one or more spaces associated with the environment of the vehicle (102); and recording the one or more spaces in an arrangement and classifying the one or more recorded spaces as a full parking space, half parking space, or partial parking space. System (106) according to claim 2, wherein the processor (202) is configured to classify the one or more rooms by: recording one or more geographic coordinates associated with one or more rooms; recording one or more images associated with the one or more recorded rooms; determining one or more parameters associated with the one or more recorded rooms; and analyzing, by a technique, the one or more geographic coordinates, the one or more images, and the one or more parameters to determine the one or more classified rooms. System (106) according to claim 1, wherein the processor (202) is configured prior to predicting the meeting point to: determine the trajectory associated with the one or more oncoming vehicles based on a relative velocity associated with the vehicle (102) and the one or more oncoming vehicles; determine a road width associated with the trajectory; compare the road width with one or more dimensions associated with the one or more oncoming vehicles and the vehicle (102); in response to the determination, determine a minimum space from the classified one or more spaces required for maneuvering the vehicle (102); and recommend a first space from the classified one or more spaces for maneuvering the vehicle (102) and preventing the collision. System (106) according to claim 4, wherein the processor (202) is configured to recommend the classified one or more rooms to: determine a location associated with the classified one or more rooms; determine a distance of the classified one or more rooms from the vehicle (102); determine one or more images associated with the classified one or more rooms; and determine one or more available room types among the classified one or more rooms. A method for analyzing free road spaces and providing recommendations, the method comprising: simultaneous detection, by a processor (202) associated with a system (106), of one or more oncoming vehicles in order to determine a trajectory associated with the one or more oncoming vehicles; prediction, by the processor (202), based on the determined trajectory, of an encounter point associated with the vehicle (102) and the one or more oncoming vehicles; in response to a determination that the vehicle and the one or more oncoming vehicles are expected to collide, determination, by the processor (202), of one or more spaces in which to maneuver the vehicle based on a classification of the one or more spaces; and recommendation, by the processor (202), of the classified one or more spaces for maneuvering the vehicle (102).and transmitted, by the processor (202), one or more warnings associated with the recommendation that prevent the collision; The method of claim 6, comprising determining, by the processor (202), one or more spaces by: receiving, by the processor (202), information associated with the environment of the vehicle (102); extracting, by the processor (202), the information to determine the one or more spaces associated with the environment of the vehicle (102); and recording, by the processor (202), the one or more spaces in an arrangement and classifying the one or more recorded spaces into a full parking space, half parking space or partial parking space. The method of claim 7, comprising classifying, by the processor (202), one or more spaces by: recording, by the processor (202), one or more geographic coordinates associated with one or more spaces; recording, by the processor (202), one or more images associated with the one or more recorded spaces; determining, by the processor (202), one or more parameters associated with the one or more recorded spaces; and analyzing, by the processor (202), using a technique, the one or more geographic coordinates, the one or more images, and the one or more parameters to determine the one or more classified spaces. The method of claim 6, comprising performing, by the processor (202), prior to predicting the meeting point: determining, by the processor (202), the trajectory associated with the one or more oncoming vehicles, based on a relative speed associated with the vehicle (102) and the one or more oncoming vehicles; determining, by the processor (202), a road width associated with the trajectory; comparing, by the processor (202), the road width with one or more dimensions associated with the one or more oncoming vehicles and the vehicle (102); in response to the determination, determining, by the processor (202), a minimum space from the classified one or more spaces required for maneuvering the vehicle (102);and recommend, by the processor (202), a first room from the classified one or more rooms for maneuvering the vehicle (102) and preventing the collision.; The method of claim 9, comprising recommending, by the processor (202), the classified one or more rooms by: determining, by the processor (202), a location associated with the classified one or more rooms; determining, by the processor (202), a distance of the classified one or more rooms from the vehicle (102); determining, by the processor (202), one or more images associated with the classified one or more rooms; and determining, by the processor (202), one or more available room types among the classified one or more rooms.

Images