Shipborne recording system

Abstract

The invention discloses a shipborne recording system, and the system is characterized in that a face recognition module carries out the face recognition of a driver through a camera, determines the identity information of the driver according to the face recognition result, and carries out the driving qualification judgment according to the identity information; the alcohol testing module obtains exhaled gas of the driver through an alcohol tester and analyzes the alcohol content in the exhaled gas; the fatigue detection module carries out face recognition on the driver through a camera, and judges the fatigue degree of the driver according to facial expressions in a face recognition image; the monitoring module carries out omnibearing monitoring on the whole ship, and reports an illegal event to a seapolice at the first time after monitoring that the illegal event occurs on the ship. It can be seen that the system improves the sailing safety of the ship.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of shipborne terminal, in particular to a shipborne recording system. BACKGROUND

[0002] In today's society, with the increasing frequency of traffic accidents and the increasing strictness of road traffic regulations, vehicle driving detection and safety management become particularly important. The traditional vehicle-mounted driving recorder can usually only record the vehicle driving trajectory and basic information, but cannot provide monitoring and analysis of the driver's behavior and state. This brings difficulties to the supervision of the driver's safe behavior and the analysis of the accident causes.

[0003] In addition, the existing driving recorders generally have the following problems: first, there is a lack of driver identity and certificate recognition function, which cannot accurately determine whether the driver has the legal driving qualification. Second, there is no effective detection means for high-risk behaviors such as drunk driving, drunk driving and fatigue driving, which cannot timely remind the driver. SUMMARY

[0004] Based on this, the embodiments of the present application provide a shipborne recording system, through which the driver's identity information can be accurately identified, alcohol content detection can be implemented, fatigue degree can be analyzed by facial expression, and whether the vehicle speed exceeds the speed limit can be detected, so as to improve the driving safety and the awareness of obeying traffic rules.

[0005] The present application provides a shipborne recording system, which comprises:

[0006] A face recognition module is configured to recognize the driver's face through a camera, determine the driver's identity information according to the face recognition result, and determine the driving qualification according to the identity information.

[0007] An alcohol testing module is configured to obtain the exhaled gas of the driver through an alcohol tester, and analyze the alcohol content in the exhaled gas.

[0008] A fatigue detection module is configured to recognize the driver's face through a camera, and determine the driver's fatigue degree according to the facial expression in the face recognition image.

[0009] A monitoring module is configured to monitor the whole ship in all directions, and report the illegal event on the ship to the maritime police as soon as possible.

[0010] Optionally, the system further comprises an analysis module, which is configured to

[0011] Obtain the ship position information, send a request to the interface of the weather service provider through the ship position information, and obtain the weather information of the area.

[0012] After receiving the data returned by the weather service interface, the data is parsed to extract the required weather information;

[0013] The weather information is analyzed to obtain the weather change trend of the region, and the analysis result is visualized.

[0014] Optionally, the weather information is analyzed to obtain the weather change trend of the region, specifically including:

[0015] The raw data of the weather information is preprocessed; specifically including data cleaning, conversion and standardization;

[0016] The autoregressive moving average model is used to analyze the time series data, and the deep learning model of neural network is established to make prediction.

[0017] Optionally, the weather information at least includes temperature, humidity, wind speed and precipitation; and the weather change trend at least includes wind power, sea state change and whether there is a storm.

[0018] Optionally, the face recognition module is also used for fingerprint recognition and verification code recognition to determine the identity information of the driver.

[0019] Optionally, when the determined identity information of the driver does not meet the driving requirements, an alarm is prompted.

[0020] Optionally, the alcohol test module is also used to prompt the prohibition of driving when the analysis result is drunk driving.

[0021] Optionally, the fatigue detection module judges the fatigue degree of the driver according to the facial expression in the face recognition image, specifically including:

[0022] The key points of the face recognition image are identified through key point detection; wherein the key points at least include eyes and mouth;

[0023] The facial expression is classified based on the position and motion of the facial key points; wherein the classification result at least includes open eyes, close eyes, yawn and frequent blinking;

[0024] According to the pre-defined fatigue degree model, the facial expression is matched with the fatigue degree, and the fatigue degree of the driver is judged according to the matching result.

[0025] Optionally, the system further includes an alarm module for automatically performing remote alarm when an accident occurs on the current ship; and when there is no response within the preset time after remote reply, the current ship is positioned and monitored and sent to the remote center.

[0026] The technical scheme provided by the embodiment of the application comprises the following steps: the face recognition module performs face recognition on the driver through the camera, and determines the identity information of the driver according to the face recognition result, and judges the driving qualification according to the identity information; the alcohol test module obtains the exhaled gas of the driver through the alcohol tester, and analyzes the alcohol content in the exhaled gas; the fatigue detection module performs face recognition on the driver through the camera, and judges the fatigue degree of the driver according to the facial expression in the face recognition image; the monitoring module performs all-around monitoring on the whole ship, and reports the illegal event on the ship to the maritime police at the first time. It can be seen that the safety of the ship is improved. BRIEF DESCRIPTION OF DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the application or the technical schemes in the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only exemplary, and for those skilled in the art, other drawings can be obtained without creative labor on the basis of the provided drawings.

[0028] Figure 1 A schematic block diagram of a shipborne recording system provided by the embodiment of the application. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical scheme and advantages of the application more clear, the following will further describe the application in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the application, and are not used to limit the application.

[0030] In the description of the application, the terms "comprise", "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device comprising a series of steps or units does not have to be limited to only those steps or units explicitly listed, but can also include other steps or units inherent to the process, method, product or device, or steps or units added based on the concept of the application.

[0031] The application provides a shipborne recording system. The main goal of the application is to provide a shipborne recording system with face recognition, alcohol testing, fatigue detection and whole-ship monitoring functions. Specifically, please refer to Figure 1 which shows a block diagram of a shipborne recording system provided by the embodiment of the application, which can comprise:

[0032] The face recognition module is configured to perform face recognition on the driver through the camera, and determine the identity information of the driver according to the face recognition result, and judge the driving qualification according to the identity information.

[0033] The system connects the cameras throughout the ship, and the specific process of face recognition includes:

[0034] Camera image acquisition: Use the camera to collect the driver's facial image. These images can be single pictures or video streams.

[0035] Face detection and positioning: Perform face detection and positioning on the collected images, i.e., find the face area in the image. This can be achieved using deep learning-based face detection algorithms.

[0036] Face feature extraction: Extract face features from each detected face area. Face features are vector representations that encode key information in facial images, usually extracted based on deep learning methods such as convolutional neural networks (CNN).

[0037] Face matching and recognition: Compare and match the extracted face features with pre-registered or stored face features in the database. If the match is successful, it is considered that the driver's identity information has been identified; otherwise, it is considered that the driver's identity information has not been identified.

[0038] Driving qualification judgment: According to the recognized driver's identity information, the driving qualification is judged. This includes verifying whether the recognized driver has a valid driving license or relevant driving qualification, and performing other additional identity verification steps according to actual needs.

[0039] The face recognition module also performs fingerprint recognition and verification code recognition to determine the driver's identity information, and when the determined driver's identity information does not meet the driving requirements, an alarm prompt is given.

[0040] Alcohol testing module, used to obtain the driver's exhaled gas through the alcohol tester and analyze the alcohol content in the exhaled gas.

[0041] In this application, the alcohol testing module connects the alcohol tester, and the specific process of alcohol testing includes:

[0042] Breath sampling: The driver blows air through the alcohol tester's air outlet. These exhaled gases will pass through a specific path and sensor.

[0043] Sensor detection: The sensor (such as an electrochemical sensor) inside the alcohol tester detects the alcohol content in the exhaled gas.

[0044] Electric signal conversion: The alcohol content detected by the sensor is converted into a corresponding electric signal. Different sensor technologies may have different electric signal output methods.

[0045] Alcohol content calculation: The electrical signal converted by the sensor is compared and analyzed with a pre-calibrated standard curve or mathematical model to calculate the alcohol content in exhaled breath. Alcohol content is usually expressed as blood alcohol concentration, in grams per liter (g / L) or milligrams per liter (mg / L).

[0046] Results Display and Judgment: The breathalyzer displays the calculated blood alcohol content on the screen. Based on the set blood alcohol content threshold, it determines whether the driver meets the legal limit for drunk driving.

[0047] The fatigue detection module is used to perform facial recognition on the driver via a camera and judge the driver's level of fatigue based on the facial expressions in the facial recognition image.

[0048] In this embodiment of the application, key points of the face recognition image are specifically identified through key point detection; wherein, the key points include at least the eyes and the mouth;

[0049] Facial expressions are classified based on the location and movement of key facial points; the classification results include at least the following: open eyes, closed eyes, yawning, and frequent blinking.

[0050] Based on a predefined fatigue level model, facial expressions are matched with fatigue levels, and the driver's fatigue level is determined based on the matching results.

[0051] The monitoring module is used to monitor the entire ship in all directions and to report any illegal events detected on board to the coast guard immediately.

[0052] In this application, the monitoring module and settings are connected to cameras or sound sensors throughout the ship to perform comprehensive monitoring. The specific process includes:

[0053] Monitoring equipment records: Real-time monitoring and video recording of the ship's interior and exterior through various sensors and cameras.

[0054] Illegal Incident Detection: The monitoring module analyzes and processes the monitored data in real time to detect whether any illegal incidents have occurred on board. For example, image recognition technology can be used to detect unsafe behaviors, dangerous items, or unusual situations.

[0055] Triggering an alarm: When the monitoring module detects an illegal event on board, it will trigger the alarm system. The alarm can use sound, light, or other means to alert the crew or other security personnel.

[0056] Event Information Transmission: Simultaneously, the monitoring module transmits detected illegal event information to the relevant monitoring center or designated coast guard agency. This is typically achieved through network connectivity and communication equipment.

[0057] Coast Guard receives and processes: After receiving the illegal event information sent by the monitoring module, the coast guard agency will process it accordingly.

[0058] In an optional embodiment of the present application, the system further comprises an analysis module:

[0059] The analysis module is used to obtain ship position information, and sends a request to the interface of the weather service provider through the ship position information to obtain the weather information of the area;

[0060] After receiving the data returned by the weather service interface, the data is parsed to extract the required weather information;

[0061] The weather information is analyzed to obtain the weather change trend of the area, and the analysis result is visualized.

[0062] Among them, the weather data uses statistical methods or machine learning algorithms to predict the weather change trend in the next few hours or days, which can be realized by the following steps:

[0063] Data collection: First, historical weather data needs to be collected as training data. These data can include past weather conditions, temperature, humidity, wind speed, and other weather parameters, as well as time and location information related to them.

[0064] Feature engineering: Before weather prediction, raw data usually needs to be processed through feature engineering. This includes selecting appropriate features and performing data cleaning, conversion and standardization, etc. For example, daily average temperature, maximum temperature, minimum temperature, etc. can be extracted as features.

[0065] Model selection and training: According to the task requirements and data conditions, select appropriate statistical methods or machine learning algorithms for modeling. For example, you can use simple statistical methods such as ARIMA (Autoregressive Moving Average Model) to analyze time series data, or use neural network-based deep learning models such as Recurrent Neural Network (RNN) or Long Short-Term Memory Network (LSTM) for prediction.

[0066] Model training and optimization: Divide the data set into training set and validation set, use the training set to train the model, and use the validation set to optimize and evaluate the model. Different loss functions, optimization algorithms and hyperparameter settings can be used to improve the performance of the model.

[0067] Prediction and evaluation: The trained and optimized model can be used for future weather prediction. According to actual needs, you can choose to predict the weather change trend in the next few hours or days. Apply the model to new data to get weather prediction results, and compare and evaluate them with actual observation data.

[0068] Continuous updating and improvement: Weather prediction is a dynamic process that requires continuous collection of new data for the ongoing updating and improvement of the model. The model can be retrained periodically to adapt to new weather patterns and changes.

[0069] In an alternative embodiment of the present application, the system further comprises an alarm module for automatically sending a remote alarm when an accident occurs on the current ship, and sending the current ship positioning and monitoring to the remote center when there is no response within the preset time after the remote reply.

[0070] The technical features of the above embodiments can be combined in any way. To make the description concise, not all possible combinations of the technical features in the above embodiments are described, but as long as the combinations of the technical features do not exist, they should be considered as within the scope of the present application.

[0071] The above embodiments only express several implementation manners of the present application, and the description is specific and detailed, but it should not be understood as a limitation on the patent scope of the application. It should be pointed out that for ordinary skilled persons in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the protection scope of the present application. Therefore, the patent protection scope of the present application should be subject to the appended claims.

Claims

1. A shipborne recording system, characterized in that, The system includes: The facial recognition module is used to perform facial recognition on the driver through a camera, determine the driver's identity information based on the facial recognition results, and make a driving qualification judgment based on the identity information. The alcohol testing module is used to obtain the driver's exhaled breath through an alcohol tester and analyze the alcohol content in the exhaled breath; The fatigue detection module is used to perform facial recognition on the driver via a camera and to determine the driver's level of fatigue based on the facial expressions in the facial recognition image. The monitoring module is used to monitor the entire ship in all directions and to report any illegal events detected on board to the coast guard immediately.

2. The shipborne recording system according to claim 1, characterized in that, The system also includes an analysis module, which is used for... Obtain the ship's location information and send a request to the weather service provider's interface through the ship's location information to obtain the weather information for the area. After receiving the data returned by the weather service interface, the data is parsed to extract the required weather information; The weather information is analyzed to obtain the weather change trend of the local area, and the analysis results are visualized.

3. The shipborne recording system according to claim 2, characterized in that, The analysis of weather information to obtain the weather change trend of the region specifically includes: The raw weather data is preprocessed, which specifically includes data cleaning, transformation, and standardization. We use an autoregressive moving average model to analyze time series data and build a deep learning model of a neural network for prediction.

4. The shipborne recording system according to claim 2, characterized in that, The weather information includes at least temperature, humidity, wind speed, and precipitation; the weather change trend includes at least wind speed, sea state changes, and the presence of storms.

5. The shipborne recording system according to claim 1, characterized in that, The facial recognition module is also used to identify the driver's identity information by performing fingerprint recognition and verification code recognition.

6. The shipborne recording system according to claim 5, characterized in that, An alarm will be issued if the identified driver's identity information does not meet the driving requirements.

7. The shipborne recording system according to claim 1, characterized in that, The alcohol testing module is also used to prompt a prohibition on driving when the analysis result indicates that the driver is under the influence of alcohol or is driving under the influence.

8. The shipborne recording system according to claim 1, characterized in that, The fatigue detection module determines the driver's fatigue level based on facial expressions in a facial recognition image, specifically including: Key points are identified in facial recognition images through key point detection; these key points include at least the eyes and mouth. Facial expressions are classified based on the location and movement of key facial points; the classification results include at least the following: open eyes, closed eyes, yawning, and frequent blinking. Based on a predefined fatigue level model, facial expressions are matched with fatigue levels, and the driver's fatigue level is determined based on the matching results.

9. The shipborne recording system according to claim 1, characterized in that, The system also includes an alarm module, which is used to automatically issue a remote alarm when an accident occurs on the current vessel; and if there is no response within a preset time after a remote reply, the current vessel location and monitoring data are sent to the remote center.

Images