A bus arrival time prediction system and method based on fusion sensing

Abstract

This invention relates to the field of data processing technology, specifically to a bus arrival time prediction system and method based on fusion perception. The system includes a route search subsystem, a location acquisition subsystem, a perception acquisition subsystem, a prediction subsystem, and an arrival display subsystem. The route search subsystem searches for the target bus's route; the location acquisition subsystem obtains the target bus's current location and the location of each bus stop based on the route by collecting the bus's license plate; the perception acquisition subsystem obtains the traffic flow from the current location to each bus stop; the prediction subsystem predicts the remaining time for the target bus to reach each bus stop based on the current location and traffic flow; and the arrival display subsystem installed at each bus stop displays the remaining time for the target bus to arrive at that bus stop, thus solving the problem of passenger anxiety caused by not knowing the exact arrival time of the bus.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a bus arrival time prediction system and method based on fusion sensing. Background Technology

[0002] When passengers are taking a bus, not knowing the exact arrival time can cause anxiety while waiting, thus affecting their ride satisfaction. Summary of the Invention

[0003] The purpose of this invention is to provide a bus arrival time prediction system and method based on fusion perception, which aims to solve the problem of waiting anxiety caused by passengers not knowing the specific arrival time of the bus.

[0004] To achieve the above objectives, in a first aspect, the present invention provides a bus arrival time prediction system based on fusion perception, comprising a route search subsystem, a location acquisition subsystem, a perception acquisition subsystem, a prediction subsystem, and an arrival display subsystem, wherein the route search subsystem, the location acquisition subsystem, the perception acquisition subsystem, the prediction subsystem, and the arrival display subsystem are connected sequentially.

[0005] The route search subsystem is used to search for the driving route of the target bus;

[0006] The location acquisition subsystem obtains the current location of the target bus and the location of each bus stop by collecting the license plate of the target bus based on the driving route.

[0007] The perception acquisition subsystem is used to acquire the traffic flow currently located at each of the bus station locations;

[0008] The prediction subsystem predicts the remaining time for the target bus to reach each of the bus stops based on the current location and the traffic flow.

[0009] The arrival display subsystem is used to display the remaining time for the target bus to arrive at the corresponding bus stop location.

[0010] The route search subsystem includes a map acquisition module, a number acquisition module, and a route search module, wherein the map acquisition module and the number acquisition module are respectively connected to the route search module;

[0011] The map acquisition module is used to acquire regional maps;

[0012] The number acquisition module is used to acquire the number of the target bus;

[0013] The route search module searches for driving routes in the area map based on the number.

[0014] The perception acquisition subsystem includes a road condition acquisition module and a feature extraction module, which are connected to each other.

[0015] The traffic condition acquisition module is used to acquire traffic condition images of each bus stop currently located.

[0016] The feature extraction module is used to extract features from the road condition image to obtain traffic flow.

[0017] The feature extraction module includes a construction submodule, a training submodule, and an extraction submodule, which are connected sequentially.

[0018] The construction submodule is used to construct the neural network model;

[0019] The training submodule is used to train the neural network model using the training dataset to obtain the feature extraction module;

[0020] The extraction submodule is used to input the road condition image into the feature extraction model for training to obtain vehicle features, and calculate traffic flow based on the vehicle features.

[0021] The arrival display subsystem includes a display module and a voice prompt module, which are connected in sequence.

[0022] The display module is used to display the remaining time for the target bus to arrive at the corresponding bus stop location;

[0023] The voice prompt module is used to broadcast a travel reminder when the remaining time is within a preset range.

[0024] The arrival display subsystem further includes a brightness adjustment module, which is connected to the display module.

[0025] The brightness adjustment module adjusts the current display brightness of the display module based on the current light intensity.

[0026] Secondly, the present invention provides a method for predicting bus arrival times based on fused sensing, comprising the following steps:

[0027] The route search subsystem searches for the route of the target bus;

[0028] The location acquisition subsystem obtains the current location of the target bus and the location of each bus stop by collecting the license plate of the target bus based on the driving route.

[0029] The perception and acquisition subsystem acquires the traffic flow currently located at each of the bus stops;

[0030] The prediction subsystem predicts the remaining time for the target bus to reach each of the bus stops based on the current location and the traffic flow.

[0031] The arrival display subsystem installed at each of the bus stop locations displays the remaining time for the target bus to arrive at the corresponding bus stop location.

[0032] This invention discloses a bus arrival time prediction system based on fusion perception. First, the route search subsystem searches for the target bus's route. Next, the location acquisition subsystem, based on the route, acquires the target bus's current location and the location of each bus stop by collecting the bus's license plate. Then, the perception acquisition subsystem acquires the traffic flow from the current location to each bus stop. Subsequently, the prediction subsystem predicts the remaining time for the target bus to reach each bus stop based on the current location and the traffic flow. Finally, an arrival display subsystem installed at each bus stop displays the remaining time for the target bus to arrive at that bus stop, thus solving the problem of passenger anxiety caused by not knowing the bus's exact arrival time. Attached Figure Description

[0033] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0034] Figure 1 This is a schematic diagram of the structure of a bus arrival time prediction system based on fusion perception provided by the present invention.

[0035] Figure 2 This is a schematic diagram of the route search subsystem.

[0036] Figure 3 This is a schematic diagram of the sensing and acquisition subsystem.

[0037] Figure 4 This is a schematic diagram of the feature extraction module.

[0038] Figure 5 This is a schematic diagram of the arrival display subsystem.

[0039] Figure 6 This is a flowchart of a bus arrival time prediction method based on fusion sensing provided by the present invention.

[0040] 1-Route search subsystem, 2-Location acquisition subsystem, 3-Perception acquisition subsystem, 4-Prediction subsystem, 5-Arrival display subsystem, 6-Map acquisition module, 7-Number acquisition module, 8-Route search module, 9-Road condition collection module, 10-Feature extraction module, 11-Construction submodule, 12-Training submodule, 13-Extraction submodule, 14-Display module, 15-Voice prompt module, 16-Brightness adjustment module. Detailed Implementation

[0041] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0042] Please see Figures 1 to 5 The present invention provides a bus arrival time prediction system based on fusion perception, including a route search subsystem 1, a location acquisition subsystem 2, a perception acquisition subsystem 3, a prediction subsystem 4, and an arrival display subsystem 5, wherein the route search subsystem 1, the location acquisition subsystem 2, the perception acquisition subsystem 3, the prediction subsystem 4, and the arrival display subsystem 5 are connected in sequence.

[0043] The route search subsystem 1 is used to search for the driving route of the target bus;

[0044] The location acquisition subsystem 2 obtains the current location of the target bus and the location of each bus stop by collecting the license plate of the target bus based on the driving route.

[0045] The perception acquisition subsystem 3 is used to acquire the traffic flow currently located at each of the bus station locations;

[0046] The prediction subsystem 4 predicts the remaining time for the target bus to reach each of the bus stops based on the current location and the traffic flow.

[0047] The arrival display subsystem 5 is used to display the remaining time for the target bus to arrive at the corresponding bus stop location.

[0048] Specifically, firstly, the route search subsystem 1 searches for the target bus's route; then, the location acquisition subsystem 2, based on the route, acquires the target bus's current location and the location of each bus stop by collecting the bus's license plate; next, the perception acquisition subsystem 3 acquires the traffic flow from the current location to each bus stop; subsequently, the prediction subsystem 4, based on the current location and the traffic flow, predicts the remaining time for the target bus to reach each bus stop; finally, the arrival display subsystem 5 installed at each bus stop displays the remaining time for the target bus to arrive at that bus stop, thus solving the problem of passengers not knowing the bus's exact arrival time and causing waiting anxiety.

[0049] Furthermore, the route search subsystem 1 includes a map acquisition module 6, a number acquisition module 7, and a route search module 8, wherein the map acquisition module 6 and the number acquisition module 7 are respectively connected to the route search module 8;

[0050] The map acquisition module 6 is used to acquire regional maps;

[0051] The number acquisition module 7 is used to acquire the number of the target bus;

[0052] The route search module 8 searches for driving routes in the area map based on the number.

[0053] Specifically, the map acquisition module 6 acquires a regional map; the number acquisition module 7 acquires the number of the target bus; and the route search module 8 searches for a route in the regional map based on the number.

[0054] Furthermore, the perception acquisition subsystem 3 includes a road condition acquisition module 9 and a feature extraction module 10, which are connected to each other.

[0055] The road condition acquisition module 9 is used to acquire road condition images of each bus stop currently located.

[0056] The feature extraction module 10 is used to extract features from the road condition image to obtain traffic flow.

[0057] The feature extraction module 10 includes a construction submodule 11, a training submodule 12, and an extraction submodule 13, which are connected in sequence.

[0058] The construction submodule 11 is used to construct a neural network model;

[0059] The training submodule 12 is used to train the neural network model using the training dataset to obtain the feature extraction module 10;

[0060] The extraction submodule 13 is used to input the road condition image into the feature extraction model for training to obtain vehicle features, and calculate traffic flow based on the vehicle features.

[0061] Specifically, the road condition acquisition module 9 is a vehicle-mounted forward-facing camera, which is an important perception sensor for intelligent driving. The road condition acquisition module 9 acquires road condition images located at each of the bus stop locations. The construction submodule 11 constructs a neural network model; the training submodule 12 trains the neural network model using a training dataset to obtain the feature extraction module 10; the extraction submodule 13 inputs the road condition images into the feature extraction model for training to obtain vehicle features, and calculates traffic flow based on the vehicle features.

[0062] Furthermore, the arrival display subsystem 5 includes a display module 14 and a voice prompt module 15, which are connected in sequence.

[0063] The display module 14 is used to display the remaining time for the target bus to arrive at the corresponding bus stop location;

[0064] The voice prompt module 15 is used to broadcast a travel reminder when the remaining time is within a preset range.

[0065] The arrival display subsystem 5 also includes a brightness adjustment module 16, which is connected to the display module 14.

[0066] The brightness adjustment module 16 adjusts the current display brightness of the display module 14 based on the current light intensity.

[0067] Specifically, the display module 14 displays the remaining time for the target bus to arrive at the corresponding bus stop location; when the remaining time is within a preset range, the voice prompt module 15 broadcasts a boarding reminder, allowing passengers who have unloaded their luggage and are resting at the bus stop to pack their belongings in advance for faster boarding. Additionally, the brightness adjustment module 16 adjusts the current display brightness of the display module 14 based on the current light intensity, increasing the display brightness in bright light environments and thus improving display clarity.

[0068] Please see Figure 6 Secondly, the present invention provides a method for predicting bus arrival time based on fusion sensing, comprising the following steps:

[0069] S1 route search subsystem 1 searches for the route of the target bus;

[0070] Specifically, the map acquisition module 6 acquires a regional map; the number acquisition module 7 acquires the number of the target bus; and the route search module 8 searches for a route in the regional map based on the number.

[0071] S2 Location Acquisition Subsystem 2 obtains the current location of the target bus and the location of each bus stop by collecting the license plate of the target bus based on the driving route;

[0072] Specifically, the license plate of the target bus is captured by cameras installed along the route, and the current location of the target bus is determined based on the location of the camera that captured the license plate.

[0073] S3 Perception Acquisition Subsystem 3 acquires the traffic flow currently located at each of the bus station locations;

[0074] Specifically, the road condition acquisition module 9 is a vehicle-mounted forward-facing camera, which is an important perception sensor for intelligent driving. The road condition acquisition module 9 acquires road condition images located at each of the bus stop locations. The construction submodule 11 constructs a neural network model; the training submodule 12 trains the neural network model using a training dataset to obtain the feature extraction module 10; the extraction submodule 13 inputs the road condition images into the feature extraction model for training to obtain vehicle features, and calculates traffic flow based on the vehicle features.

[0075] S4 prediction subsystem 4 predicts the remaining time of the target bus from each bus stop location based on the current location and the traffic flow;

[0076] S5 The arrival display subsystem 5 installed at each of the bus stop locations displays the remaining time for the target bus to arrive at the corresponding bus stop location.

[0077] Specifically, the display module 14 displays the remaining time for the target bus to arrive at the corresponding bus stop location; when the remaining time is within a preset range, the voice prompt module 15 broadcasts a boarding reminder, allowing passengers who have unloaded their luggage and are resting at the bus stop to pack their belongings in advance for faster boarding. Additionally, the brightness adjustment module 16 adjusts the current display brightness of the display module 14 based on the current light intensity, increasing the display brightness in bright light environments and thus improving display clarity.

[0078] The above description is merely a preferred embodiment of the bus arrival time prediction system and method based on fusion perception of the present invention. Of course, it should not be construed as limiting the scope of the present invention. Those skilled in the art can understand that implementing all or part of the above embodiments and making equivalent changes in accordance with the claims of the present invention still fall within the scope of the invention.

Claims

1. A bus arrival time prediction system based on fusion sensing, characterized in that, It includes a route search subsystem, a location acquisition subsystem, a perception acquisition subsystem, a prediction subsystem, and an arrival display subsystem, which are connected in sequence. The route search subsystem is used to search for the driving route of the target bus; The location acquisition subsystem obtains the current location of the target bus and the location of each bus stop by collecting the license plate of the target bus based on the driving route. The perception acquisition subsystem is used to acquire the traffic flow currently located at each of the bus station locations; The prediction subsystem predicts the remaining time for the target bus to reach each of the bus stops based on the current location and the traffic flow. The arrival display subsystem is used to display the remaining time for the target bus to arrive at the corresponding bus stop location.

2. The bus arrival time prediction system based on fusion sensing as described in claim 1, characterized in that, The route search subsystem includes a map acquisition module, a number acquisition module, and a route search module, wherein the map acquisition module and the number acquisition module are respectively connected to the route search module; The map acquisition module is used to acquire regional maps; The number acquisition module is used to acquire the number of the target bus; The route search module searches for driving routes in the area map based on the number.

3. The bus arrival time prediction system based on fusion sensing as described in claim 1, characterized in that, The perception acquisition subsystem includes a road condition acquisition module and a feature extraction module, and the road condition acquisition module and the feature extraction module are connected. The traffic condition acquisition module is used to acquire traffic condition images of each bus stop currently located. The feature extraction module is used to extract features from the road condition image to obtain traffic flow.

4. The bus arrival time prediction system based on fusion sensing as described in claim 3, characterized in that, The feature extraction module includes a construction submodule, a training submodule, and an extraction submodule, which are connected sequentially. The construction submodule is used to construct the neural network model; The training submodule is used to train the neural network model using the training dataset to obtain the feature extraction module; The extraction submodule is used to input the road condition image into the feature extraction model for training to obtain vehicle features, and calculate traffic flow based on the vehicle features.

5. The bus arrival time prediction system based on fusion sensing as described in claim 1, characterized in that, The arrival display subsystem includes a display module and a voice prompt module, which are connected in sequence. The display module is used to display the remaining time for the target bus to arrive at the corresponding bus stop location; The voice prompt module is used to broadcast a travel reminder when the remaining time is within a preset range.

6. The bus arrival time prediction system based on fusion sensing as described in claim 5, characterized in that, The arrival display subsystem also includes a brightness adjustment module, which is connected to the display module. The brightness adjustment module adjusts the current display brightness of the display module based on the current light intensity.

7. A bus arrival time prediction method based on fusion sensing, applied to the bus arrival time prediction system based on fusion sensing as described in claim 1, characterized in that, Includes the following steps: The route search subsystem searches for the route of the target bus; The location acquisition subsystem obtains the current location of the target bus and the location of each bus stop by collecting the license plate of the target bus based on the driving route. The perception and acquisition subsystem acquires the traffic flow currently located at each of the bus stops; The prediction subsystem predicts the remaining time for the target bus to reach each of the bus stops based on the current location and the traffic flow. The arrival display subsystem installed at each of the bus stop locations displays the remaining time for the target bus to arrive at the corresponding bus stop location.

Images