1. A Black Ice detection system to enhance road safety with Artificial Intelligence comprises a plurality of IceGuard (1.1, 1.2, 1.N), Information Collector (4K Camera 3840x2160) (2), Cloud Server (3), Information Extraction (4), Web Interface for Display Result (LCD Screen) (5), Wifi Module (Data Transmission (6), Cloud Storage (7), Remote Monitoring (8), Infrared Camera (Night Vision) (9), Neural Stick (Fast Computing) (10), Microprocessor (Raspberry Pi) (11), Microcontroller (12), Mouse (Input) (13), Keyboard (Input) (14), Heat Sink (Thermal Maintenance) (15), Solar Pannel (16), 12v 3amp Lithium Polymer (Battery) (17), Charger (18), AC Outlet (19) and Charging Current (20) wherein the number of sensors 4K Camera 3840x2160 (2), Web Interface for Display Result (LCD Screen) (5), Wifi Module (Data Transmission) (6), Cloud Storage (7), Remote Monitoring (8), Infrared Camera (Night Vision) (9), Neural Stick (Fast Computing) (10), Raspberry Pi (11), Microcontroller (12), Mouse (Input) (13), Keyboard (Input) (14), is connected with microprocessor (11) that collect vital information; Characterized in that the camera (2) takes high-resolution pictures of the road surface while an infrared camera facilitates night vision as well as working under dim light conditions hence ensuring effective operation during these adverse lighting circumstances.

2. The system as claimed in claim 1, wherein the microprocessor (11) processes the data in a manner that uses its own neural stick for quick computation purposes, connected to a keyboard (14) and a mouse (13), where users can manually input commands and make adjustments in any way they see fit; through a WiFi module (6), data collected by this device is transmitted wirelessly to allow remote control and monitoring.

3. The system as claimed in claim 1, wherein Processed information is then displayed on an LCD screen (5) linked to the microcontroller for immediate visual feedback.

4. The system as claimed in claim 1, wherein, provides a machine learning algorithm to classify road surfaces into twelve categories (dry, moist, wet to saline environments having low; no such problems; very high levels of possible dangers); and integrate with raspberry pi for cost-effective detection systems.

5. The system as claimed in claim 1, wherein provides real-time alerts by alert system (112) thereby fostering road safety, reducing both accidents and economic costs.

6. The system as claimed in claim 1, wherein the whole set-up is powered by 12V 3A lithium polymer battery (17) to provide uninterrupted power supply to it.

7. The system as claimed in claim 1, wherein the system securely stores information on clouds storage (7) that enables prolonged analysis of data and identification of trends made possible.

8. The system as claimed in claim 1, wherein the images are continually transferred to microprocessor which then processes them in a manner that uses its own neural stick (10) for quick computation purposes.

Description:FIELD OF THE INVENTION
This invention relates to black ice detection system to enhance road safety with artificial intelligence.
BACKGROUND OF THE INVENTION
A significant risk that drivers often face is black ice, especially for areas with winter conditions. Detecting black ice in the conventional way relies most times on visual inspection and surface temperature measurements which may not be accurate or prompt enough to prevent accidents. Black ice is often silent, unpredictable and invisible thereby causing severe traffic accidents and disruptions. The need for an advanced detection system capable of accurately identifying various weather-induced conditions of black ice and providing real time alerts to mitigate risks cannot be over emphasized.
To this end, we propose a machine learning-based method that can distinguish between twelve different categories of black ice on the basis of weather patterns and level of danger associated with it. These categories range from dry, moist, wet to saline environments having low; no such problems; very high levels of possible dangers respectively. Our aim is to develop an inexpensive yet efficient detection device that combines this model with a Raspberry Pi so that it can be easily deployed across multiple locations ranging from city streets to remote highways. The proposed system would monitor road conditions by using sensor data continuously and classify them making it possible for drivers as well as highway maintenance crews to receive timely warnings. The employment of this model has numerous advantages ranging from enhanced road safety to optimized maintenance activities. It is a system that may greatly decrease black ice related accidents and, in the process, save lives and reduce economic losses. Besides, it can improve effectiveness of road maintenance operations through targeted interventions that are based on real-time data. The main goal of this project is to bring new levels of safety and efficiency into winter road management.
KR102034027B1 The present invention relates to an automatic liquid snow removing agent spraying system for a road having a black ice removing function and a method thereof and, more specifically, to an automatic liquid snow removing agent spraying system for a road having a black ice removing function and a method thereof, wherein the system calculates an expected amount of a snow removing agent to be consumed by calculating the amount of snowfall per minute when the snow falls on a road; determines whether there is a possible freezing environment section based on the amount of snowfall per minute and a road surface temperature for each road section, checks a spray record within a set period when there is a possible freezing environment section, sprays the snow removing agent when there is no spray record, additionally obtains an image for each road section, analyzes the image using a deep learning technique to determine whether there is a black ice section, and removes black ice by intensively spraying the snow removing agent to the corresponding section when there is a black ice section, thereby promoting traffic safety in winter.
RESEARCH GAP:
1. Comprehensive Coverage: Covering a large number of weather conditions and risk levels, the model will ensure that it detects correctly over different environments.
2. Cost-effective Solution: Making use of Raspberry Pi in this model makes it affordable to many people including small municipalities and rural areas.
KR102136131B1 The present invention discloses a road traffic safety management technology. That is, according to an embodiment of the present invention, provided are an automatic road ice prediction system and an operating method. As an IoT-based integrated disaster prevention solution which predicts and monitors freezing conditions by installing in areas where black ice regularly occurs, such as on an overpass, on a bridge, near a tunnel, or the like. Before drivers and pedestrians enter the freezing section, the freezing condition is predicted to display a road freezing situation with a warning light and an electric sign at the same time. A snow removal agent is automatically sprayed, and a site situation is grasped in a situation control room and follow-up measures such as road control or the like are taken, so that traffic accidents due to road freezing can be prevented in advance.
RESEARCH GAP:
1. Real-time Alerts: This system sends real time driver alerts which let them take immediate actions to avoid dangerous conditions.
2. Improved Road Safety: This black ice detector can significantly reduce accidents attributed to undetected black ice thus enhancing road safety as a whole.
None of the prior art indicate above either alone or in combination with one another disclose what the present invention has disclosed. This invention relates to Black Ice detection to enhance road safety with Artificial Intelligence.
SUMMARY OF THE INVENTION
This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the invention.
This summary is neither intended to identify key or essential inventive concepts of the invention and nor is it intended for determining the scope of the invention.
To further clarify advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which is illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail with the accompanying drawings.
A machine learning-based method that can distinguish between twelve different categories of black ice on the basis of weather patterns and level of danger associated with it. These categories range from dry, moist, wet to saline environments having low; no such problems; very high levels of possible dangers respectively. Our aim is to develop an inexpensive yet efficient detection device that combines this model with a Raspberry Pi so that it can be easily deployed across multiple locations ranging from city streets to remote highways. The proposed system would monitor road conditions by using sensor data continuously and classify them making it possible for drivers as well as highway maintenance crews to receive timely warnings. The employment of this model has numerous advantages ranging from enhanced road safety to optimized maintenance activities. It is a system that may greatly decrease black ice related accidents and, in the process, save lives and reduce economic losses. Besides, it can improve effectiveness of road maintenance operations through targeted interventions that are based on real-time data. The main goal of this project is to bring new levels of safety and efficiency into winter road management.
At the core of the black ice detection device is a Raspberry Pi functioning as the main processing unit. It is connected with various input devices and sensors that collect vital information. A 4K camera takes high-resolution pictures of the road surface while an infrared camera facilitates night vision as well as working under dim light conditions hence ensuring effective operation during these adverse lighting circumstances. These images are continually transferred to Raspberry Pi which then processes them in a manner that uses its own neural stick for quick computation purposes. Such neural stick quickens machine learning algorithms, thereby enabling real time analysis and classification of road conditions. Processed information is then displayed on an LCD screen linked to the microcontroller for immediate visual feedback. The microcontroller is responsible for the intermediate service as data links between the Raspberry Pi and the display module. It also maintains system stability by using heat sink which disperse excessive heat produced by processing components.
The Raspberry Pi is connected to a keyboard and a mouse, where users can manually input commands and make adjustments in any way they see fit. Through a WiFi module, data collected by this device is transmitted wirelessly to allow remote control and monitoring. In addition, this system securely stores information on clouds that enables prolonged analysis of data and identification of trends made possible. This whole set-up is powered by 12V 3A lithium polymer battery to provide uninterrupted power supply to it. The solar panel charges the battery thereby making it eco-friendly and reducing reliance on external sources of energy. It captures sun energy converting it into electrical power stored in its memory cells thus being recharged during daytime. Thereafter, there is a management system for power supply which ensures that battery does not go out of charge or even fail.The system consists of the charger and an AC outlet for flexibility in how to power it. The charger changes alternating current (AC) from the outlet into direct current (DC) suitable for battery charging. There is one component that is labeled “Changing Current” which ensures that all parts get enough power without overloading the system. The device’s detailed structure of detecting black ice has been designed to be comprehensive and efficient by incorporating sophisticated technologies for accurate detection and timely warnings. This tool, through combining high-resolution cameras, fast computing neural sticks, as well as robust power management, can be a great instrument in order to boost road safety. By using cloud storage together with remote monitoring capabilities, this system will deliver real-time information to its users as well as authorities hence enabling early intervention against black ice risk. Furthermore, integration of renewable energy sources such as solar panels underscores sustainability of this device making it fit for widespread use. In sum, this detailed structure emphasizes meticulous planning and integration of various components to create a complex but functional black ice detection system.
Data collection is the first step taken in building the flowchart that relates to the black ice detection system. In this phase, diverse sensors located on the road acquire complete data concerning road conditions. These indicators include such as wetness, temperature and saltiness which are essential factors for any potential black ice formation. The raw data collected encompasses all environmental factors that might be concerned with road safety; it has not been processed. This stage gives a good starting point in terms of available data so that analysis and prediction of black ice conditions can be pretty accurate. The system is updated on real time basis from this stage onwards consequently enabling timely identification and intervention by system. After collecting data, the next stage involves pre-processing the data. This entails cleaning up the raw information to eliminate noises or irrelevant details that may lead to biasing results. Preprocessing includes normalization, dealing with missing values or even changing them into a more usable form if necessary. Therefore, this phase is very crucial as it prepares for feature extraction hence allowing other subsequent steps to proceed accordingly.
The system is capable of focusing on the most critical aspects that contribute to black ice formations by refining its data. This procedure improves the accuracy in feature extraction and model classification steps, which build a foundation on which dependable risk assessment and alert generation can be established. Following data preprocessing, the system proceeds to feature extraction, where it identifies key features that influence the formation of black ice. These features include temperature thresholds, moisture levels, and salinity concentrations, among others. The extracted features are then fed into the model classification stage, where a machine learning algorithm classifies the road conditions into one of the twelve predefined categories, such as dry low or moist, very high. This classification is crucial for assessing the risk level associated with the detected condition. The risk assessment phase evaluates the classified condition and determines the corresponding risk level, whether it is none, low, or very high. Based on this assessment, the system generates appropriate alerts. High-risk alerts prompt immediate action from road maintenance teams and drivers, while low-risk alerts are monitored for potential changes. Every now and then, the system keeps watching and reviews the status. This is to ensure alerts are always based on the latest information by continuously updating its classifications and risk assessments as it collects new data.
BRIEF DESCRIPTION OF THE DRAWINGS
The illustrated embodiments of the subject matter will be understood by reference to the drawings, wherein like parts are designated by like numerals throughout. The following description is intended only by way of example, and simply illustrates certain selected embodiments of devices, systems, and methods that are consistent with the subject matter as claimed herein, wherein:
Figure 1: General architecture of the device
Figure 2: Detailed Structure of the device with Power management
Figure 3: Algorithmic view of all the processes
Figure 4: Output
The figures depict embodiments of the present subject matter for the purposes of illustration only. A person skilled in the art will easily recognize from the following description that alternative embodiments of the structures and methods illustrated herein may be employed without departing from the principles of the disclosure described herein.
DETAILED DESCRIPTION OF THE INVENTION
The detailed description of various exemplary embodiments of the disclosure is described herein with reference to the accompanying drawings. It should be noted that the embodiments are described herein in such details as to clearly communicate the disclosure. However, the amount of details provided herein is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the scope of the present disclosure as defined by the appended claims.
It is also to be understood that various arrangements may be devised that, although not explicitly described or shown herein, embody the principles of the present disclosure. Moreover, all statements herein reciting principles, aspects, and embodiments of the present disclosure, as well as specific examples, are intended to encompass equivalents thereof.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a",” “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and/or “including,” when used herein, specify the presence of stated features, integers, steps, operations, elements and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and/or groups thereof.
It should also be noted that in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed concurrently or may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
In addition, the descriptions of "first", "second", “third”, and the like in the present invention are used for the purpose of description only, and are not to be construed as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Thus, features defining "first" and "second" may include at least one of the features, either explicitly or implicitly.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which example embodiments belong. It will be further understood that terms, e.g., those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
A machine learning-based method that can distinguish between twelve different categories of black ice on the basis of weather patterns and level of danger associated with it. These categories range from dry, moist, wet to saline environments having low; no such problems; very high levels of possible dangers respectively. Our aim is to develop an inexpensive yet efficient detection device that combines this model with a Raspberry Pi so that it can be easily deployed across multiple locations ranging from city streets to remote highways. The proposed system would monitor road conditions by using sensor data continuously and classify them making it possible for drivers as well as highway maintenance crews to receive timely warnings. The employment of this model has numerous advantages ranging from enhanced road safety to optimized maintenance activities. It is a system that may greatly decrease black ice related accidents and, in the process, save lives and reduce economic losses. Besides, it can improve effectiveness of road maintenance operations through targeted interventions that are based on real-time data. The main goal of this project is to bring new levels of safety and efficiency into winter road management.
At the core of the black ice detection device is a Raspberry Pi functioning as themain processing unit. It is connected with various input devices and sensors that collect vital information. A 4K camera takes high-resolution pictures of the road surface while an infrared camera facilitates night vision as well as working under dim light conditions hence ensuring effective operation during these adverse lighting circumstances. These images are continually transferred to Raspberry Pi which then processes them in a manner that uses its own neural stick for quick computation purposes. Such neural stick quickens machine learning algorithms, thereby enabling real time analysis and classification of road conditions. Processed information is then displayed on an LCD screen linked to the microcontroller for immediate visual feedback. The microcontroller is responsible for the intermediate service as data links between the Raspberry Pi and the display module. It also maintains system stability by using heat sink which disperse excessive heat produced by processing components.
The Raspberry Pi is connected to a keyboard and a mouse, where users can manually input commands and make adjustments in any way they see fit. Through a WiFi module, data collected by this device is transmitted wirelessly to allow remote control and monitoring. In addition, this system securely stores information on clouds that enables prolonged analysis of data and identification of trends made possible. This whole set-up is powered by 12V 3A lithium polymer battery to provide uninterrupted power supply to it. The solar panel charges the battery thereby making it eco-friendly and reducing reliance on external sources of energy. It captures sun energy converting it into electrical power stored in its memory cells thus being recharged during daytime. Thereafter, there is a management system for power supply which ensures that battery does not go out of charge or even fail. The system consists of the charger and an AC outlet for flexibility in how to power it. The charger changes alternating current (AC) from the outlet into direct current (DC) suitable for battery charging. There is one component that is labeled “Changing Current” which ensures that all parts get enough power without over loading the system. The device’s detailed structure of detecting black ice has been designed to be comprehensive and efficient by incorporating sophisticated technologies for accurate detection and timely warnings. This tool, through combining high-resolution cameras, fast computing neural sticks, as well as robust power management, can be a great instrument in order to boost road safety. By using cloud storage together with remote monitoring capabilities, this system will deliver real-time information to its users as well as authorities hence enabling early intervention against black ice risk. Furthermore, integration of renewable energy sources such as solar panels underscores sustainability of this device making it fit for widespread use. In sum, this detailed structure emphasizes meticulous planning and integration of various components to create a complex but functional black ice detection system.
Data collection is the first step taken in building the flowchart that relates to the black ice detection system. In this phase, diverse sensors located on the road acquire complete data concerning road conditions. These indicators include such as wetness, temperature and saltiness which are essential factors for any potential black ice formation. The raw data collected encompasses all environmental factors that might be concerned with road safety; it has not been processed. This stage gives a good starting point in terms of available data so that analysis and prediction of black ice conditions can be pretty accurate. The system is updated on real time basis from this stage onwards consequently enabling timely identification and intervention by system. After collecting data, the next stage involves pre-processing the data. This entails cleaning up the raw information to eliminate noises or irrelevant details that may lead to biasing results. Preprocessing includes normalization, dealing with missing values or even changing them into a more usable form if necessary. Therefore, this phase is very crucial as it prepares for feature extraction hence allowing other subsequent steps to proceed accordingly.
The system is capable of focusing on the most critical aspects that contribute to black ice formations by refining its data. This procedure improves the accuracy in feature extraction and model classification steps, which build a foundation on which dependable risk assessment and alert generation can be established. Following data preprocessing, the system proceeds to feature extraction, where it identifies key features that influence the formation of black ice. These features include temperature thresholds, moisture levels, and salinity concentrations, among others. The extracted features are then fed into the model classification stage, where a machine learning algorithm classifies the road conditions into one of the twelve predefined categories, such as dry low or moist, very high. This classification is crucial for assessing the risk level associated with the detected condition. The risk assessment phase evaluates the classified condition and determines the corresponding risk level, whether it is none, low, or very high. Based on this assessment, the system generates appropriate alerts. High-risk alerts prompt immediate action from road maintenance teams and drivers, while low-risk alerts are monitored for potential changes. Every now and then, the system keeps watching and reviews the status. This is to ensure alerts are always based on the latest information by continuously updating its classifications and risk assessments as it collects new data.
A Black Ice detection system to enhance road safety with Artificial Intelligence comprises a plurality of IceGuard (1.1, 1.2, 1.N), Information Collector (4K Camera 3840x2160) (2), Cloud Server (3), Information Extraction (4), Web Interface for Display Result (LCD Screen) (5), Wifi Module (Data Transmission (6), Cloud Storage (7), Remote Monitoring (8), Infrared Camera (Night Vision) (9), Neural Stick (Fast Computing) (10), Microprocessor (Raspberry Pi) (11), Microcontroller (12), Mouse (Input) (13), Keyboard (Input) (14), Heat Sink (Thermal Maintenance) (15), Solar Pannel (16), 12v 3amp Lithium Polymer (Battery) (17), Charger (18), AC Outlet (19) and Charging Current (20) wherein the number of sensors 4K Camera 3840x2160 (2), Web Interface for Display Result (LCD Screen) (5), Wifi Module (Data Transmission) (6), Cloud Storage (7), Remote Monitoring (8), Infrared Camera (Night Vision) (9), Neural Stick (Fast Computing) (10), Raspberry Pi (11), Microcontroller (12), Mouse (Input) (13), Keyboard (Input) (14), is connected with microprocessor (11) that collect vital information;
In another embodiment Processed information is then displayed on an LCD screen (5) linked to the microcontroller for immediate visual feedback.
In another embodiment provides a machine learning algorithm to classify road surfaces into twelve categories (dry, moist, wet to saline environments having low; no such problems; very high levels of possible dangers); and integrate with raspberry pi for cost-effective detection systems.
In another embodiment provides real-time alerts by alert system thereby fostering road safety, reducing both accidents and economic costs.
In another embodiment the whole set-up is powered by 12V 3A lithium polymer battery (17) to provide uninterrupted power supply to it.
In another embodiment the system securely stores information on clouds storage (7) that enables prolonged analysis of data and identification of trends made possible.
In another embodiment the images are continually transferred to microprocessor which then processes them in a manner that uses its own neural stick (10) for quick computation purposes.
ADVANTAGES OF THE INVENTION
1. Enhanced Maintenance Efficiency: The system helps maintenance teams prioritize where their resources should be deployed by providing accurate road conditions hence minimizing wastage of resource through focus targeting efforts of maintenance team.
2. Scalability: It is easy to extend the system covering bigger areas or integrating it with existing traffic management systems.
3. User-friendly Interface: The system can easily be designed with a user interface that is user friendly making it easier for drivers and maintenance crews to comprehend and respond to alerts.
4. Reduced Economic Losses: Such accidents can be avoided; the black ice incidents could lead to these economic losses being minimized by efficient use of resources in maintaining them efficiently.
5. Environmental Benefits: Making use of exact data, targeted salting and de-icing measures can reduce the environmental impact resulting from road maintenance activities.
6. Continuous Improvement: With machine learning, this system can always be improved through so that they learn from new information going forward such as evolving weather patterns over time thus making them very accurate.
, Claims:1. A Black Ice detection system to enhance road safety with Artificial Intelligence comprises a plurality of IceGuard (1.1, 1.2, 1.N), Information Collector (4K Camera 3840x2160) (2), Cloud Server (3), Information Extraction (4), Web Interface for Display Result (LCD Screen) (5), Wifi Module (Data Transmission (6), Cloud Storage (7), Remote Monitoring (8), Infrared Camera (Night Vision) (9), Neural Stick (Fast Computing) (10), Microprocessor (Raspberry Pi) (11), Microcontroller (12), Mouse (Input) (13), Keyboard (Input) (14), Heat Sink (Thermal Maintenance) (15), Solar Pannel (16), 12v 3amp Lithium Polymer (Battery) (17), Charger (18), AC Outlet (19) and Charging Current (20) wherein the number of sensors 4K Camera 3840x2160 (2), Web Interface for Display Result (LCD Screen) (5), Wifi Module (Data Transmission) (6), Cloud Storage (7), Remote Monitoring (8), Infrared Camera (Night Vision) (9), Neural Stick (Fast Computing) (10), Raspberry Pi (11), Microcontroller (12), Mouse (Input) (13), Keyboard (Input) (14), is connected with microprocessor (11) that collect vital information;
Characterized in that the camera (2) takes high-resolution pictures of the road surface while an infrared camera facilitates night vision as well as working under dim light conditions hence ensuring effective operation during these adverse lighting circumstances.
2. The system as claimed in claim 1, wherein the microprocessor (11) processes the data in a manner that uses its own neural stick for quick computation purposes, connected to a keyboard (14) and a mouse (13), where users can manually input commands and make adjustments in any way they see fit; through a WiFi module (6), data collected by this device is transmitted wirelessly to allow remote control and monitoring.
3. The system as claimed in claim 1, wherein Processed information is then displayed on an LCD screen (5) linked to the microcontroller for immediate visual feedback.
4. The system as claimed in claim 1, wherein, provides a machine learning algorithm to classify road surfaces into twelve categories (dry, moist, wet to saline environments having low; no such problems; very high levels of possible dangers); and integrate with raspberry pi for cost-effective detection systems.
5. The system as claimed in claim 1, wherein provides real-time alerts by alert system (112) thereby fostering road safety, reducing both accidents and economic costs.
6. The system as claimed in claim 1, wherein the whole set-up is powered by 12V 3A lithium polymer battery (17) to provide uninterrupted power supply to it.
7. The system as claimed in claim 1, wherein the system securely stores information on clouds storage (7) that enables prolonged analysis of data and identification of trends made possible.
8. The system as claimed in claim 1, wherein the images are continually transferred to microprocessor which then processes them in a manner that uses its own neural stick (10) for quick computation purposes.