CN114530035A - Single-hand and double-hand separation steering wheel early warning system based on active safety terminal - Google Patents
Single-hand and double-hand separation steering wheel early warning system based on active safety terminal Download PDFInfo
- Publication number
- CN114530035A CN114530035A CN202111215280.4A CN202111215280A CN114530035A CN 114530035 A CN114530035 A CN 114530035A CN 202111215280 A CN202111215280 A CN 202111215280A CN 114530035 A CN114530035 A CN 114530035A
- Authority
- CN
- China
- Prior art keywords
- hand
- active safety
- double
- steering wheel
- safety terminal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000926 separation method Methods 0.000 title claims abstract description 28
- 238000004422 calculation algorithm Methods 0.000 claims description 20
- 230000006399 behavior Effects 0.000 claims description 12
- 230000008520 organization Effects 0.000 claims description 9
- 230000001360 synchronised effect Effects 0.000 claims description 6
- 230000003442 weekly effect Effects 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 2
- 238000007405 data analysis Methods 0.000 description 8
- 238000012549 training Methods 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 6
- 238000000034 method Methods 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 210000002569 neuron Anatomy 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000001788 irregular Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000011176 pooling Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000001681 protective effect Effects 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 2
- 230000002929 anti-fatigue Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000008689 nuclear function Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000017105 transposition Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/76—Television signal recording
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/12—Messaging; Mailboxes; Announcements
- H04W4/14—Short messaging services, e.g. short message services [SMS] or unstructured supplementary service data [USSD]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Signal Processing (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Networks & Wireless Communication (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Alarm Systems (AREA)
Abstract
The invention solves the problems that single-hand and double-hand separation of a steering wheel cannot be detected and early-warned data cannot be transmitted to a mobile phone end in the prior art, and provides a single-hand and double-hand separation steering wheel early warning system based on an active safety terminal.
Description
Technical Field
The invention relates to the technical field of buses, in particular to a one-hand and two-hand separation steering wheel early warning system based on an active safety terminal.
Background
The number of accidents caused by public transportation accounts for about 1 percent of the number of national traffic accidents, and the number of accidents is not greatly reduced in the last 10 years. This phenomenon has caused a high level of attention and vigilance to competent departments, industries, and enterprises. And a part of accidents happen just because of the irregular driving behaviors of the bus drivers. In China, the algorithm scene of the active safety system is mostly transplanted from 'two passengers are in danger', and the general precision is not high when the method is applied to the public transportation scene. Coordination of the software platform and aid decision making for enterprise management are de-emphasized. And the most common irregular driving behavior of the bus with the largest hidden danger of 'one or two hands are separated from the steering wheel' cannot be overcome. Referring to a vehicle-mounted monitoring system and method based on active safety early warning, with chinese patent application No. CN202110400306.6, the system includes a monitoring background and a plurality of vehicle-mounted embedded devices located on different vehicles; the vehicle-mounted embedded equipment is used for acquiring vehicle positioning information, vehicle speed information and vehicle inside and outside image information, performing anti-fatigue early warning of active safety early warning according to the vehicle positioning information, the vehicle speed information, the vehicle inside and outside image information and the vehicle number information and transmitting the vehicle positioning information, the vehicle speed information, the vehicle inside and outside image information and the vehicle number information to the monitoring background when the active safety early warning is needed or the anti-fatigue early warning is needed; and the monitoring background is used for comprehensively monitoring the problems occurring in the running process of the vehicle according to the information uploaded by the vehicle-mounted embedded equipment, counting the problems occurring in each vehicle and the problems occurring in each driver and generating a corresponding report. This application helps guaranteeing driving safety, can gather analysis and comprehensive monitoring to the problem that the driving in-process appeared simultaneously. However, a single-hand and double-hand separation algorithm model is not established in the scheme, the behavior that a single hand and double hands are separated from a steering wheel cannot be detected and warned, and one of the most common irregular driving behaviors of a bus driver is omitted. According to the scheme, a plurality of data related to alarm are transmitted to the background, the front-end display report is carried out on the webpage end, the report cannot be transmitted to the mobile phone end, and the current front-end application layer of the current mobile internet which is developed at a high speed is limited and has less coverage.
Disclosure of Invention
The invention solves the problems that in the prior art, single-hand and double-hand separation of a steering wheel cannot be detected and early-warning data cannot be transmitted to a mobile phone end, and provides an active safety terminal-based single-hand and double-hand separation steering wheel early-warning system.
In order to realize the purpose, the following technical scheme is provided:
a single-hand and double-hand separation steering wheel early warning system based on an active safety terminal comprises the active safety terminal, an auxiliary camera arranged near a B column of a bus and used for shooting a driver seat from top to bottom, a dispatching system background and an application end, wherein the auxiliary camera is electrically connected with the active safety terminal and used for recording a video of the steering wheel in real time and transmitting the video to the active safety terminal; the active safety terminal transmits the alarm records and the video to the background of the dispatching system through the network, and the background of the dispatching system transmits the alarm records and the video to the application end through the network.
The invention collects million-level video materials of a bus driver, performs machine learning training, and specially establishes a one-hand and two-hand separation algorithm model, thereby effectively recognizing the behavior of the driver that one hand and two hands are separated from a steering wheel and performing early warning. Effective protective measures are provided for different operation habits of drivers. And carrying out local early warning and background transmission on the behavior that the single hand and the double hands are separated from the steering wheel.
Preferably, the application end comprises a short message end, an applet end and a webpage end.
The auxiliary camera is additionally arranged near the B column and shoots the driving seat from top to bottom to serve as a collecting end. And when the algorithm detects that the duration time of the single-hand and double-hand separation action exceeds the configuration time, the algorithm carries out voice local voice broadcast and uploads the alarm record to the background of the scheduling system through a network module. The background of the dispatching system can classify the alarms according to the vehicle speed triggering threshold and the quantity triggering threshold, and different strategies are carried out. The high-level alarm can be pushed to a mobile phone end of a manager in real time through a short message interface, the low-level alarm and the medium-level alarm are stored in a background of a scheduling system, and data analysis reports are embodied in a daily report/weekly report mode at a small program end and a short message end. All alarms can be checked and processed at the webpage end.
Preferably, a graded warning algorithm is arranged on the background of the dispatching system, and the graded warning algorithm divides the alarm records into a high-grade alarm, a middle-grade alarm and a low-grade alarm according to the triggering threshold value of the vehicle speed and the triggering threshold value of the quantity from large to small.
Preferably, the high-level alarm is pushed to the short message end in real time through the short message interface, the low-level alarm and the medium-level alarm are stored in the background of the scheduling system and are displayed in a daily report or weekly report mode at the small program end and the short message end, and all alarm records can be checked on the webpage end to obtain details and processing results.
Preferably, the network connection comprises a 4g network or a 5g network.
Preferably, the background of the scheduling system stores management personnel information of all levels of a plurality of fleets and a plurality of organization nodes, and the management personnel information of all levels is associated with the active safety terminal.
The invention increases data transmission, data analysis and data display of the mobile phone terminal. After the terminal gives an alarm, the data is transmitted to the background through the application and network module for data analysis, if pre-configuration early warning is met, short messages are pushed to managers at all levels of a public transport company, and different fleets and different organization nodes can be distinguished for hierarchical management according to equipment association organization. The short message side and the multi-end cloud side of the webpage side are synchronous, the short message side can inquire the details of alarming and a data statistical analysis report through H5, and the data updating frequency is consistent with that of the webpage side.
Preferably, the background of the scheduling system accesses the alarm records and the videos into the Alice cloud platform through a wireless network, the data of the short message end, the data of the applet end and the data of the webpage end are synchronous with the data of the Alice cloud platform, and the data updating frequency of the Alice cloud platform is consistent with that of the webpage end.
The background of the scheduling system is accessed into a safe driving early warning management platform service in the Ali cloud platform through a wireless network, wherein the video system and the expanded streaming media cluster group thereof can be deployed in different Ali cloud nodes and machine rooms. An internal server of the same node of the Aliyun performs intranet communication, and servers of different nodes perform wired extranet communication.
The invention has the beneficial effects that:
(1) the invention collects million-level video materials of a bus driver, performs machine learning training, and specially establishes a one-hand and two-hand separation algorithm model, thereby effectively recognizing the behavior of the driver that one hand and two hands are separated from a steering wheel and performing early warning. Effective protective measures are provided for different operation habits of drivers. And carrying out local early warning and background transmission on the behavior that the single hand and the double hands are separated from the steering wheel.
(2) The invention increases data transmission, data analysis and data display of the mobile phone terminal. After the terminal gives an alarm, the data is transmitted to the background through the application and network module for data analysis, if pre-configuration early warning is met, short messages are pushed to managers at all levels of a public transport company, and different fleets and different organization nodes can be distinguished for hierarchical management according to equipment association organization. The short message side and the multi-end cloud side of the webpage side are synchronous, the short message side can inquire the details of alarming and a data statistical analysis report through H5, and the data updating frequency is consistent with that of the webpage side.
Drawings
FIG. 1 is a system connection diagram of an embodiment;
FIG. 2 is a two-class single-or double-handed gesture recognition model structure of an embodiment;
fig. 3 is a gesture classification network structure of an embodiment.
Detailed Description
Example (b):
the embodiment provides a single-hand and double-hand separation steering wheel early warning system based on an active safety terminal, and the system is characterized by referring to fig. 1, comprising the active safety terminal, an auxiliary camera arranged near a B column of a bus and used for shooting a driver seat from top to bottom, a dispatching system background and an application end, wherein the auxiliary camera is electrically connected with the active safety terminal, the auxiliary camera is used for recording a real-time video of the steering wheel and transmitting the video to the active safety terminal, the active safety terminal is provided with a local voice broadcast module and a single-hand and double-hand separation algorithm, the single-hand and double-hand separation algorithm is used for identifying the duration time of single-hand and double-hand separation behaviors and generating an alarm record, and the local voice broadcast module is used for voice broadcasting the alarm record; the active safety terminal transmits the alarm record and the video to the background of the dispatching system through the network, and the background of the dispatching system transmits the alarm record and the video to the application end through the network. The application end comprises a short message end, an applet end and a webpage end.
The invention collects million-level video materials of a bus driver, performs machine learning training, and specially establishes a one-hand and two-hand separation algorithm model, thereby effectively recognizing the behavior of the driver that one hand and two hands are separated from a steering wheel and performing early warning. Effective protective measures are provided for different operation habits of drivers. And carrying out local early warning and background transmission on the behavior that the single hand and the double hands are separated from the steering wheel.
The single-hand and double-hand separation algorithm model is based on a single-hand and double-hand gesture recognition model of the self-adaptive enhanced convolutional neural network, recognition of single-hand and double-hand gestures is achieved, and the recognition accuracy is improved by adopting the self-adaptive enhanced convolutional neural network on the basis of analyzing the reasons and feedback of errors generated in the training process. The overall network structure of the model is shown in FIG. 2, firstly, preprocessing operation is carried out on the image, a hand number classifier is input, image recognition is converted from overall to local, and two-hand gesture prediction is grouped into one-hand gestures; secondly, introducing a self-adaptive enhancement module on the basis of the convolutional neural network, carrying out residual error self-adaptive enhancement by analyzing iteration times and classification results, and updating hidden layer parameters; and finally, respectively training the two classifiers.
The number classifier mainly performs packet prediction by dividing both hands into one hand, and its network structure is shown in fig. 3, where C1 and C2 represent the first and second convolutional layers, respectively, S1 and S2 represent the first and second pooling layers, respectively, and FC is a full connection layer. For subsequent network identification, the input size of the network is set as 28pixel × 28pixel, the calculated amount of convolution is reduced by replacing one convolution kernel of 5 × 5 with two convolution kernels of 3 × 3, on the premise of obtaining the same visual field, the input size of the network is set as 28 × 28, 32 feature maps are generated after convolution with the convolution kernel size of 3 × 3, the sliding step size of 1 and the padding of 0, local response normalization is carried out on the down-sampled feature maps by adopting a maximum pooling mode with a window size of 2 × 2 and ReLU function activation, adjacent neurons are inhibited by the activated neurons to improve the generalization capability of the network, 64 feature maps are generated after convolution with the convolution kernel size of 3 × 3, the step size of 2 and the padding of 0, the feature maps are subjected to the activation function and then to the maximum pooling of 2 × 2 windows again, and node neurons which enter a full connection layer and a Dropout layer and have a certain probability p to be ignored, and the hidden layer output node is not output temporarily, namely, parameters connected with the part of nodes are not updated when the network is trained and the weight and the bias are updated. And then training in the rest neuron networks with the probability of 1-p, setting p to be 0.4-0.6 during first training, modifying according to the fitting condition of the training set, if overfitting is obvious, properly reducing the value of p, if overfitting is not obvious, properly increasing the value of p, and repeating the process in a circulating mode to obtain a proper p value, so that the calculation amount and the overfitting phenomenon can be reduced, and the generalization capability of the network can be improved. The sigmoid kernel used may be represented as
In the formula: x is the number ofi，xjFeature vectors at low latitudes; t is the transposition of the vector; tan h is a hyperbolic tangent function; beta and theta are nuclear parameters of the nuclear function, beta is greater than 0, and theta is less than 0.
The auxiliary camera is additionally arranged near the B column and shoots the driving seat from top to bottom to serve as a collecting end. And when the algorithm detects that the duration time of the single-hand and double-hand separation action exceeds the configuration time, the algorithm carries out voice local voice broadcast and uploads the alarm record to the background of the scheduling system through a network module. The background of the dispatching system can classify the alarms according to the vehicle speed triggering threshold and the quantity triggering threshold, and different strategies are carried out. The high-level alarm can be pushed to a mobile phone end of a manager in real time through a short message interface, the low-level alarm and the medium-level alarm are stored in a background of a scheduling system, and data analysis reports are embodied in a daily report/weekly report mode at a small program end and a short message end. All alarms can be checked and processed at the webpage end.
The background of the dispatching system is provided with a grading warning algorithm, and the grading warning algorithm divides the alarm records into high-grade alarm, middle-grade alarm and low-grade alarm according to the triggering threshold value of the vehicle speed and the triggering threshold value of the quantity from large to small.
The high-level alarm is pushed to the short message end in real time through the short message interface, the low-level alarm and the medium-level alarm are stored in the background of the scheduling system and are displayed in a daily report or weekly report mode at the small program end and the short message end, and all alarm records can be checked on the webpage end to obtain detailed and processed results.
The network connection includes a 4g network or a 5g network.
The dispatching system background stores management personnel information of all levels of a plurality of fleets and a plurality of organization nodes, and the management personnel information of all levels is associated with the active safety terminal.
The invention increases data transmission, data analysis and data display of the mobile phone terminal. After the terminal gives an alarm, the data is transmitted to the background through the application and network module for data analysis, if pre-configuration early warning is met, short messages are pushed to managers at all levels of a public transport company, and different fleets and different organization nodes can be distinguished for hierarchical management according to equipment association organization. The short message side and the multi-end cloud side of the webpage side are synchronous, the short message side can inquire the details of alarming and a data statistical analysis report through H5, and the data updating frequency is consistent with that of the webpage side.
The background of the dispatching system accesses the alarm records and the videos into the Alice cloud platform through a wireless network, data of the short message end, the applet end and the webpage end are synchronous with data of the Alice cloud platform, and the data updating frequency of the Alice cloud platform is consistent with that of the webpage end.
The background of the scheduling system is accessed into a safe driving early warning management platform service in the Ali cloud platform through a wireless network, wherein the video system and the expanded streaming media cluster group thereof can be deployed in different Ali cloud nodes and machine rooms. An internal server of the same node of the Aliyun performs intranet communication, and servers of different nodes perform wired extranet communication.
Claims (7)
1. A single-hand and double-hand separation steering wheel early warning system based on an active safety terminal is characterized by comprising the active safety terminal, an auxiliary camera, a dispatching system background and an application end, wherein the auxiliary camera is installed near a B column of a bus and used for shooting a driver seat from top to bottom, the auxiliary camera is electrically connected with the active safety terminal, the auxiliary camera is used for recording a video of the steering wheel in real time and transmitting the video to the active safety terminal, the active safety terminal is provided with a local voice broadcasting module and a single-hand and double-hand separation algorithm, the single-hand and double-hand separation algorithm is used for identifying the duration time of single-hand and double-hand separation behaviors and generating an alarm record, and the local voice broadcasting module is used for voice broadcasting the alarm record; the active safety terminal transmits the alarm records and the video to the background of the dispatching system through the network, and the background of the dispatching system transmits the alarm records and the video to the application end through the network.
2. The active safety terminal-based one-hand and two-hand separation steering wheel early warning system as claimed in claim 1, wherein the application terminal comprises a short message terminal, an applet terminal and a web page terminal.
3. The active safety terminal-based single-hand and double-hand separation steering wheel early warning system is characterized in that a graded warning algorithm is arranged in the background of the dispatching system, and the graded warning algorithm divides the warning records into a high-grade warning, a middle-grade warning and a low-grade warning according to the triggering threshold value of the vehicle speed and the triggering threshold value of the quantity from large to small.
4. The active safety terminal-based single-hand and double-hand separation steering wheel early warning system is characterized in that high-level alarms are pushed to a short message end in real time through a short message interface, low-level alarms and medium-level alarms are stored in a background of a scheduling system and are displayed in a daily report or weekly report mode at a small program end and the short message end, and all alarm records can be checked for details and processing results at a webpage end.
5. The active safety terminal-based one-hand and two-hand disengagement steering wheel pre-warning system as claimed in claim 1, wherein the network connection comprises a 4g network or a 5g network.
6. The active safety terminal-based single-hand and double-hand separation steering wheel early warning system as claimed in claim 1, wherein the scheduling system is provided with a plurality of fleets and a plurality of organization nodes of management personnel information at each level in a background, and the management personnel information at each level is associated with the active safety terminal.
7. The active safety terminal-based single-hand and double-hand separation steering wheel early warning system is characterized in that a scheduling system background accesses alarm records and videos into an Aliskian platform through a wireless network, data of the short message end, the applet end and the webpage end are synchronous with data of the Aliskian platform, and the data updating frequency of the Aliskian platform is consistent with that of the webpage end.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111215280.4A CN114530035A (en) | 2021-10-19 | 2021-10-19 | Single-hand and double-hand separation steering wheel early warning system based on active safety terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111215280.4A CN114530035A (en) | 2021-10-19 | 2021-10-19 | Single-hand and double-hand separation steering wheel early warning system based on active safety terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114530035A true CN114530035A (en) | 2022-05-24 |
Family
ID=81619785
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111215280.4A Pending CN114530035A (en) | 2021-10-19 | 2021-10-19 | Single-hand and double-hand separation steering wheel early warning system based on active safety terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114530035A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104276080A (en) * | 2014-10-16 | 2015-01-14 | 北京航空航天大学 | Bus driver hand-off-steering-wheel detection warning system and warning method |
| CN104751663A (en) * | 2015-02-28 | 2015-07-01 | 北京壹卡行科技有限公司 | Safe driving auxiliary system and safe driving auxiliary method for driver |
| CN109034111A (en) * | 2018-08-17 | 2018-12-18 | 北京航空航天大学 | A kind of driver's hand based on deep learning is from steering wheel detection method and system |
| CN212313525U (en) * | 2020-08-28 | 2021-01-08 | 陕西科技大学 | Monitoring platform of vehicle operation and maintenance enterprise |
-
2021
- 2021-10-19 CN CN202111215280.4A patent/CN114530035A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104276080A (en) * | 2014-10-16 | 2015-01-14 | 北京航空航天大学 | Bus driver hand-off-steering-wheel detection warning system and warning method |
| CN104751663A (en) * | 2015-02-28 | 2015-07-01 | 北京壹卡行科技有限公司 | Safe driving auxiliary system and safe driving auxiliary method for driver |
| CN109034111A (en) * | 2018-08-17 | 2018-12-18 | 北京航空航天大学 | A kind of driver's hand based on deep learning is from steering wheel detection method and system |
| CN212313525U (en) * | 2020-08-28 | 2021-01-08 | 陕西科技大学 | Monitoring platform of vehicle operation and maintenance enterprise |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11254325B2 (en) | Vehicle-data analytics | |
| CN107886073B (en) | Fine-grained vehicle multi-attribute identification method based on convolutional neural network | |
| Yi et al. | A machine learning based personalized system for driving state recognition | |
| WO2020042984A1 (en) | Vehicle behavior detection method and apparatus | |
| US8126833B2 (en) | Detecting anomalous events using a long-term memory in a video analysis system | |
| CN112686090B (en) | Intelligent monitoring system for abnormal behavior in bus | |
| Yan et al. | Driving posture recognition by joint application of motion history image and pyramid histogram of oriented gradients | |
| CN112633057B (en) | Intelligent monitoring method for abnormal behavior in bus | |
| CN106570444A (en) | On-board smart prompting method and system based on behavior identification | |
| US10860865B2 (en) | Predictive security camera system | |
| CN111488803A (en) | Airport target behavior understanding system integrating target detection and target tracking | |
| Valeriano et al. | Recognition of driver distractions using deep learning | |
| CN110796109A (en) | Driver distraction behavior identification method based on model fusion | |
| US12014588B2 (en) | Automatic event classification | |
| Yan et al. | Recognizing driver inattention by convolutional neural networks | |
| US20230351894A1 (en) | Accident reporter | |
| Hu et al. | Detecting socially abnormal highway driving behaviors via recurrent graph attention networks | |
| Reddy et al. | Cloud-Based Road Safety for Real-Time Vehicle Rash Driving Alerts with Random Forest Algorithm | |
| CN118015562A (en) | Method and system for extracting key frames of traffic accident monitoring video in severe weather | |
| CN114530035A (en) | Single-hand and double-hand separation steering wheel early warning system based on active safety terminal | |
| US11468671B2 (en) | Sentiment analysis for situational awareness | |
| US10650275B2 (en) | Method for detection of temporal pattern anomalies in video streams | |
| Sirisha et al. | Utilizing a hybrid model for human injury severity analysis in traffic accidents | |
| Raut et al. | Review on: Severity estimation unit of automotive accident | |
| Jayashree et al. | Convolutional Neural Networks (CNN)-based Vehicle Crash Detection and Alert System |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |