CN104732251A - Video-based method of detecting driving state of locomotive driver - Google Patents
Video-based method of detecting driving state of locomotive driver Download PDFInfo
- Publication number
- CN104732251A CN104732251A CN201510194411.3A CN201510194411A CN104732251A CN 104732251 A CN104732251 A CN 104732251A CN 201510194411 A CN201510194411 A CN 201510194411A CN 104732251 A CN104732251 A CN 104732251A
- Authority
- CN
- China
- Prior art keywords
- driver
- trainman
- judge
- image
- locomotive driver
- 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.)
- Granted
Links
Landscapes
- Emergency Alarm Devices (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a video-based method of detecting driving state of a locomotive driver. The method includes: using two cameras to take a video image of the locomotive driver standing up to work and a video image of the locomotive driver driving a locomotive; according to whether the locomotive driver is in the images, judging whether the locomotive driver is off the station, thus avoiding the locomotive driver from being mistakenly judged as being off the station when the locomotive driver stands and looks out; when the locomotive driver is in the image of the locomotive driver standing to work, tracking and detecting a facial area in the image, and judging whether the locomotive driver is tired according to changes of the facial area; when the locomotive driver is in the image of the locomotive driver driving the locomotive, detecting operational frequency parameter, eye state parameter and mouth state parameter of the locomotive driver so as to judge whether the locomotive driver is tired, thus avoiding missing of judging the locomotive driver being in the sleep with eyes opened. The problems that the locomotive driver standing and looking out is not detected and the fatigue driving state of the locomotive driver is inaccurately judged are solved; the driving state of the locomotive driver can be comprehensively detected.
Description
Technical field
The present invention relates to a kind of trainman's driving condition detection method based on video, belong to technical field of image processing.
Background technology
Flourish along with China Railway Transportation cause, improving constantly of locomotive driving speed, the safety problem of locomotive operation is more outstanding, and the factor affecting locomotive safety running is a lot, but the driving behavior of trainman occupies the status of can not ignore in locomotive safety running.Therefore, research and development trainman fatigue-driving detection technology, can effectively prevent and reduce the potential safety hazard that the misbehave of locomotive driver driving brings.
Real-Time Monitoring trainman fatigue driving state also provides warning message in time, and the situation that can reduce fatigue driving largely occurs.In a practical situation, trainman needs to look at the continual Zhan Li of locomotive driving process, to guarantee the safe operation of locomotive.Current home and abroad is not looked at for trainman Zhan Li and operator seat drives the technology that the driving condition in two kinds of situations monitors simultaneously, trainman Zhan Li can be looked at be mistaken for trainman and leave post.Existing detection method is detected by PERCLOS, head position, mouth state parameter etc. judges trainman's fatigue state, if application number is the patent application document of 201410848027, this document disclose a kind of fatigue driving monitoring method based on Kinect and recognition of face, the method is exactly by the eyes image in extraction face and mouth image, by detecting the rate of change of frequency of wink, closed-eye time and the yawning feature of mouth judge whether driver is in fatigue state, and when trainman keep one's eyes open eyeball sleeping time, can't detect tired driver by the way to drive, occur failing to report phenomenon etc., and head position can change according to the height of driver, more than simple basis several parameter judges there will be to fail to judge, erroneous judgement.
Summary of the invention
The object of this invention is to provide a kind of trainman's driving condition detection method based on video, to solve the problem of failing to judge and judging by accident that existing driver driving state-detection process occurs.
The present invention is for solving the problems of the technologies described above and providing a kind of trainman's driving condition detection method based on video, and this driving condition detection method comprises the following steps:
1) gather trainman to stand the video image of working position and driving task position, judge whether above-mentioned image has people, if equal nobody, then judge that trainman is in the state of leaving the post;
2) when having people in the video image of working position of standing, tracing detection is carried out to the human face region of driver, the number of times that human face region changes in setting-up time is less than setting value, illustrate that driver is in fatigue state, otherwise, illustrate that driver carries out Zheng Chang lookout, return step 1) gather next frame image;
3) when the video image of driving task position has people, detect the operational frequency parameters of driver, eye state parameter and mouth states parameter, judge that driver is in fatigue state when arbitrary parameter occurs abnormal, otherwise, return step 1) gather next frame image.
The method also comprises the detection to driver gestures, and this detection calculates the face anglec of rotation by support vector regression algorithm, if the face anglec of rotation is in setting range, illustrates that driving attitude is normal, otherwise illustrates that driving attitude rectified by needs.
Described step 1) in be utilize the facial image of all attitudes of detection of classifier driver to judge whether have people in image, be provided with training positive sample and negative sample in this classification and Detection device, store in the positive sample of described training and comprise driver face vertical rotation angle and around the image of vertical axis revolving angle within the scope of set angle.
Described step 2) in adopt Context Tracking track algorithm to follow the tracks of human face region.
Described step 3) in eye state parameter comprise PERCLOS, frequency of wink and blink duration, described PERCLOS refers to eyes closed degree within the unit interval, frequency of wink is for representing the speed that eye state changes, and blink duration refers to that eyes close again to opening this process time used from opening to.
Described mouth states parameter refers to the width in face region and the ratio of height.
Described step 3) in the detection of eye state parameter and mouth states parameter be utilize to position realization based on the multiple dimensioned eye detector of study and Mouth detection device.
Described step 3) in the deterministic process of eyes and face fatigue state as follows:
A). judge whether eye parameters PERCLOS is greater than setting value, if so, then judge that driver is in fatigue state, ends process, otherwise enter step b);
B). judge that whether frequency of wink is lower than setting value, if so, then judge that driver is in fatigue state, ends process, otherwise enter step c);
C). judge that blink duration is no and be greater than setting value, if be greater than, then judge that driver is in fatigue state, ends process, otherwise enter steps d);
D). judge whether face stretching degree is greater than setting threshold value, if be greater than, then judge that driver is in fatigue state, ends process, otherwise enter step 1) gather next frame video image.
Described operational frequency parameters obtains by the log sheet calling locomotive, comprises the adjustment of driver to the operation of handle, the adjustment of speed, the operation of display button and locomotive pipe pressure.
When number of times of leaving the post is greater than setting value, driver be in fatigue state and driver gestures abnormal time all by report to the police remind.
The invention has the beneficial effects as follows: the present invention gathers trainman respectively by two cameras and to stand the video image of working position and operator seat working position, according on above-mentioned image, whether someone judges whether trainman is in the state of leaving the post, and avoids when driver is mistaken for when Zhan Li looks at the state of leaving the post; When having people in the video image of working position of standing, tracing detection is carried out to the human face region of driver, if human face region does not change or seldom changes within a period of time, illustrate that driver is in fatigue state, if human face region, in constantly changing, illustrates that driver carries out Zheng Chang lookout; When the video image of operator seat working position has people, judging whether driver is in fatigue state by detecting the operational frequency parameters of driver, eye state parameter and mouth states parameter, avoiding when trainman keeps one's eyes open the phenomenon of failing to judge when eyeball is fallen asleep.The invention solves and can't detect trainman Zhan Li lookout and inaccurate problem is judged to tired driver driving condition, achieve the complete detection to trainman's driving condition.
Accompanying drawing explanation
Fig. 1 is the installation site schematic diagram of two cameras in the embodiment of the present invention;
Fig. 2 is the process flow diagram that trainman in the embodiment of the present invention drives detection method.
Embodiment
Below in conjunction with accompanying drawing, the specific embodiment of the present invention is further described.
As shown in Figure 1, first the present invention adopts two cameras to gather trainman respectively and to stand the video image of working position and driving task position, judges whether above-mentioned image has people, if equal nobody, then judges that trainman is in the state of leaving the post; When having people in the video image of working position of standing, tracing detection is carried out to the human face region of driver, if human face posture does not change or seldom changes within a period of time, illustrate that driver is in fatigue state, if human face region, in constantly changing, illustrates that driver carries out Zheng Chang lookout; When the video image of driving task position has people, detect the operational frequency parameters of driver, eye state parameter and mouth states parameter, then judge that driver is in fatigue state when arbitrary parameter occurs abnormal, thus realize the real-time detection to trainman's driving condition.
The idiographic flow of the method as shown in Figure 2, is described the specific implementation process of the method below.
1. gather trainman to stand the video image of working position and driving task position.
As shown in Figure 1, the present invention adopts two cameras to realize, camera 1 is arranged near trainman's driving task position, to gather upper part of the body direct picture when driver is sitting on seat, camera 2 is arranged on trainman and stands near working position, to gather upper part of the body direct picture when driver stands.
2. pair collect image and carry out Face datection location, judge whether have people in video image.
Specific practice: utilize Adaboost algorithm, extracts Haar features training and obtains human-face detector, carry out tracing detection to face, to detect in complex background situation in real time and to navigate to human face region, detects in the video image of camera 1 collection whether have people; If nobody, analyze in the video image of camera 2 collection whether have people; If also nobody in the video image that camera 2 gathers, then illustrate that driver is in the state of leaving the post, the counter that makes to leave the post adds 1, and when leaving the post, counter is greater than threshold value T1, then export and leave the post to report to the police, end process; If nobody in the video image that camera 1 gathers, there is people in the video image that camera 2 gathers, think that driver is in Zhan Li and looks at, carry out step 3; If have people in the video image that camera 1 gathers, then illustrate that driver is on seat, then enter step 4 and carry out fatigue detecting.
In this enforcement, the special feature of sorter training is:
1) sorter trains the angle of face in positive sample to contain driver face vertical rotation angle from looking up 30 °, looking squarely, overlooking 30 ° of scopes, and face is around vertical axis revolving angle from left side 90 ° to right side 90 °;
2) background picture without face is only comprised in the negative sample of sorter.
The effect of such process is, sorter can detect the facial image of all attitudes of driver, for the situation that can't detect face, thinks that driver leaves post.
3. when the video image gathered when camera 2 has a people, Context Tracking track algorithm is utilized to carry out tracing detection to the human face region of driver, if human face region does not change or seldom changes within a period of time, illustrate that driver is in fatigue state, if human face region is in constantly changing, illustrate that driver carries out Zheng Chang lookout, return step 1 and gather next frame image.
4. when the video image gathered when camera 2 has a people, by detecting the operational frequency parameters of driver, eye state parameter and mouth states parameter, judge whether driver is in fatigue state, if operating frequency is lower than certain threshold value T3, export fatigue warning, end process; If operating frequency is normal, eye state is in fatigue state, exports fatigue warning signal, ends process; If eye state is in normal condition, judge mouth states, if mouth states is in fatigue state, exports fatigue warning signal, end process; If eyes and mouth states are all normal, turn back to step 1 and gather next frame video image, repeat said process, thus continuous print carries out real-time analysis to trainman's state.The detection computations process of parameters is as follows:
The calculating of operating frequency obtains according to locomotive operation log file, locomotive operation log file is various kinds of vehicles running state information relevant with locomotive safety running in the locomotive operation process of locomotive operation monitor system real time record, comprise locomotive speed, pipe pressure, locomotive operating mode etc., can show that in the time period that N two field picture is corresponding, trainman is to the corresponding operating of locomotive and operating frequency by locomotive operation log file.
Eye state parameter comprises PERCLOS, frequency of wink and blink duration, and PERCLOS refers to that time that within unit interval eyes closed degree exceedes a certain threshold value (70%, 80%) accounts for the ratio of T.T.; Frequency of wink is for representing the speed that eye state (open eyes or close) changes; Blink duration refers to that eyes close again to opening this process time used from opening to.
Mouth states parameter refers to the stretching degree of face, can represent with the ratio of the width in face region and height, and this enforcement is by calculating stretching degree and the duration of face in N two field picture.
The deterministic process of eyes and face fatigue state: if PERCLOS is greater than threshold value T4, exports fatigue warning control signal, ends process; If PERCLOS is less than T4, judge frequency of wink, if frequency of wink is lower than threshold value T5/ time, exports fatigue warning control signal, end process; If frequency of wink is higher than T5/ time, judge blink duration, if blink duration is greater than threshold value T6, exports fatigue warning control signal, end process; If blink duration is less than T6, judge mouth states parameter, if face stretching degree is greater than setting threshold value, export fatigue warning control signal, end process, if face stretching degree is less than setting threshold value, then can gather next frame image in step 1, setting threshold value in the present embodiment is 0.5.
Meanwhile, whether the present invention can also detect driver driving attitude correct, and the testing process of driver driving attitude is as follows: calculate the face anglec of rotation, whether normally judges to drive attitude; If it is abnormal to drive attitude, attitude counter adds 1, if attitude counter is greater than threshold value T2, and output terminal skipper attitude alerting signal.This process fatigue state can be implemented before detecting after step 2 judges there is people in any video image.
In the present embodiment, the calculating of the face anglec of rotation adopts support vector regression algorithm, the trainman's facial image navigated to is divided into grid, calculate the local feature of each grid, view data is transformed into the subspace of low dimension, be converted to one-dimensional vector, as the input of this support vector regression algorithm.Collect known face vertical rotation angle looking up 30 °, level, overlooking 30 °, around vertical axis revolving from left 90 °, left 45 °, 0 °, right 45 °, right 90 °, the facial image sample of totally 15 kinds of posture angles, a left side is designated as " ﹣ ", the right side is designated as " ﹢ ", be divided into ﹣ 90 °, ﹣ 45 °, 0 °, ﹢ 45 ° and ﹢ 90 ° of 5 rotary freedoms, for each rotary freedom trains support vector regression model, for trainman's facial image, utilize one-dimensional vector characteristic sum regression model, calculate the corresponding anglec of rotation; If the face anglec of rotation is in [-30 ° ,+30 °] scope, drive attitude normally, otherwise driving attitude is abnormal.
Involved parameter T1 in said process, T2, T3, T4, T5, T6, can calculate according to the alarming determining time:
T
i＝t
i×n；
T
ifor T
ithe corresponding alarming determining time, unit is second, and n is the frame number of algorithm process p.s..
Therefore the better feasible embodiment of above-mentioned only the present invention, non-ly limit to scope, does various distortion or apply mechanically all within this technical scheme protection domain according to above-described embodiment.
Claims (10)
1. based on trainman's driving condition detection method of video, it is characterized in that, this driving condition detection method comprises the following steps:
1) gather trainman to stand the video image of working position and driving task position, judge whether above-mentioned image has people, if equal nobody, then judge that trainman is in the state of leaving the post;
2) when having people in the video image of working position of standing, tracing detection is carried out to the human face region of driver, the number of times that human face region changes in setting-up time is less than setting value, illustrate that driver is in fatigue state, otherwise, illustrate that driver carries out Zheng Chang lookout, return step 1) gather next frame image;
3) when the video image of driving task position has people, detect the operational frequency parameters of driver, eye state parameter and mouth states parameter, judge that driver is in fatigue state when arbitrary parameter occurs abnormal, otherwise, return step 1) gather next frame image.
2. the trainman's driving condition detection method based on video according to claim 1, it is characterized in that, the method also comprises the detection to driver gestures, this detection calculates the face anglec of rotation by support vector regression algorithm, if the face anglec of rotation is in setting range, illustrate that driving attitude is normal, otherwise illustrate that driving attitude rectified by needs.
3. the trainman's driving condition detection method based on video according to claim 2, it is characterized in that, described step 1) in be utilize the facial image of all attitudes of detection of classifier driver to judge whether have people in image, be provided with training positive sample and negative sample in this classification and Detection device, store in the positive sample of described training and comprise driver face vertical rotation angle and around the image of vertical axis revolving angle within the scope of set angle.
4. the trainman's driving condition detection method based on video according to claim 2, is characterized in that, described step 2) in adopt Context Tracking track algorithm to follow the tracks of human face region.
5. the trainman's driving condition detection method based on video according to claim 2, it is characterized in that, described step 3) in eye state parameter comprise PERCLOS, frequency of wink and blink duration, described PERCLOS refers to eyes closed degree within the unit interval, frequency of wink is for representing the speed that eye state changes, and blink duration refers to that eyes close again to opening this process time used from opening to.
6. the trainman's driving condition detection method based on video according to claim 3, is characterized in that, described mouth states parameter refers to the width in face region and the ratio of height.
7. the trainman's driving condition detection method based on video according to claim 4, it is characterized in that, described step 3) in the detection of eye state parameter and mouth states parameter be utilize to position realization based on the multiple dimensioned eye detector of study and Mouth detection device.
8. the trainman's driving condition detection method based on video according to claim 5, is characterized in that, described step 3) in the deterministic process of eyes and face fatigue state as follows:
A). judge whether eye parameters PERCLOS is greater than setting value, if so, then judge that driver is in fatigue state, ends process, otherwise enter step b);
B). judge that whether frequency of wink is lower than setting value, if so, then judge that driver is in fatigue state, ends process, otherwise enter step c);
C). judge that blink duration is no and be greater than setting value, if be greater than, then judge that driver is in fatigue state, ends process, otherwise enter steps d);
D). judge whether face stretching degree is greater than setting threshold value, if be greater than, then judge that driver is in fatigue state, ends process, otherwise enter step 1) gather next frame video image.
9. the trainman's driving condition detection method based on video according to claim 2, it is characterized in that, described operational frequency parameters obtains by the log sheet calling locomotive, comprises the adjustment of driver to the operation of handle, the adjustment of speed, the operation of display button and locomotive pipe pressure.
10. the trainman's driving condition detection method based on video according to any one of claim 2-9, it is characterized in that, when number of times of leaving the post is greater than setting value, driver be in fatigue state and driver gestures abnormal time all by report to the police remind.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510194411.3A CN104732251B (en) | 2015-04-23 | 2015-04-23 | A kind of trainman's driving condition detection method based on video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510194411.3A CN104732251B (en) | 2015-04-23 | 2015-04-23 | A kind of trainman's driving condition detection method based on video |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104732251A true CN104732251A (en) | 2015-06-24 |
| CN104732251B CN104732251B (en) | 2017-12-22 |
Family
ID=53456126
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510194411.3A Active CN104732251B (en) | 2015-04-23 | 2015-04-23 | A kind of trainman's driving condition detection method based on video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104732251B (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105128627A (en) * | 2015-09-07 | 2015-12-09 | 湖南科技大学 | Overheat protection device for automobile |
| CN105469073A (en) * | 2015-12-16 | 2016-04-06 | 安徽创世科技有限公司 | Kinect-based call making and answering monitoring method of driver |
| CN105574487A (en) * | 2015-11-26 | 2016-05-11 | 中国第一汽车股份有限公司 | Facial feature based driver attention state detection method |
| CN105788176A (en) * | 2016-05-25 | 2016-07-20 | 厦门理工学院 | Fatigue driving monitoring and prompting method and system |
| CN105787438A (en) * | 2016-02-03 | 2016-07-20 | 郑州畅想高科股份有限公司 | Video-based locomotive driver driving state detection method and system |
| CN105825631A (en) * | 2016-04-26 | 2016-08-03 | 成都远控科技有限公司 | Video intelligent algorithm-based fatigue detection method and system |
| CN106778532A (en) * | 2016-11-28 | 2017-05-31 | 合肥工业大学 | Based on the driving posture feature sorting technique for removing differentiation size parameter |
| CN107126224A (en) * | 2017-06-20 | 2017-09-05 | 中南大学 | A kind of real-time monitoring of track train driver status based on Kinect and method for early warning and system |
| CN107194381A (en) * | 2017-07-06 | 2017-09-22 | 重庆邮电大学 | Driver status monitoring system based on Kinect |
| CN108583592A (en) * | 2017-12-30 | 2018-09-28 | 西安市地下铁道有限责任公司 | A kind of subway service on buses or trains job information acquisition intelligent detecting method |
| CN108830240A (en) * | 2018-06-22 | 2018-11-16 | 广州通达汽车电气股份有限公司 | Fatigue driving state detection method, device, computer equipment and storage medium |
| CN109002757A (en) * | 2018-06-04 | 2018-12-14 | 上海商汤智能科技有限公司 | Drive management method and system, vehicle intelligent system, electronic equipment, medium |
| US10328946B2 (en) | 2017-01-03 | 2019-06-25 | Ge Global Sourcing Llc | Alerter augmentation system |
| US10370012B2 (en) | 2017-03-09 | 2019-08-06 | Ge Global Sourcing Llc | Adaptive vehicle control system |
| CN110136381A (en) * | 2018-02-07 | 2019-08-16 | 中国石油化工股份有限公司 | A kind of well drilling operation site personnel standing monitoring and warning system |
| CN110618635A (en) * | 2019-10-08 | 2019-12-27 | 中兴飞流信息科技有限公司 | Train cab operation specification monitoring system based on AI technology |
| CN111052127A (en) * | 2018-09-12 | 2020-04-21 | 北京嘀嘀无限科技发展有限公司 | System and method for fatigue detection |
| CN112149482A (en) * | 2019-06-28 | 2020-12-29 | 深圳市商汤科技有限公司 | Method, device and equipment for detecting on-duty state of driver and computer storage medium |
| CN112230760A (en) * | 2020-09-17 | 2021-01-15 | 淮南师范学院 | Analysis system and method based on combination of user operation and biological characteristics |
| US10915769B2 (en) | 2018-06-04 | 2021-02-09 | Shanghai Sensetime Intelligent Technology Co., Ltd | Driving management methods and systems, vehicle-mounted intelligent systems, electronic devices, and medium |
| US10970571B2 (en) | 2018-06-04 | 2021-04-06 | Shanghai Sensetime Intelligent Technology Co., Ltd. | Vehicle control method and system, vehicle-mounted intelligent system, electronic device, and medium |
| US11065958B2 (en) | 2017-01-03 | 2021-07-20 | Transportation Ip Holdings, Llc | Control system and method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1830389A (en) * | 2006-04-21 | 2006-09-13 | 太原理工大学 | Device for monitoring fatigue driving state and its method |
| CN101090482A (en) * | 2006-06-13 | 2007-12-19 | 唐琎 | Driver fatigue monitoring system and method based on image process and information mixing technology |
| US20090097707A1 (en) * | 2007-10-12 | 2009-04-16 | Samsung Techwin Co., Ltd. | Method of controlling digital image processing apparatus for face detection, and digital image processing apparatus employing the method |
| CN102393989A (en) * | 2011-07-28 | 2012-03-28 | 山西智济电子科技有限公司 | Real-time monitoring system of driver working state |
| CN102426757A (en) * | 2011-12-02 | 2012-04-25 | 上海大学 | Safety driving monitoring system based on mode identification and method thereof |
-
2015
- 2015-04-23 CN CN201510194411.3A patent/CN104732251B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1830389A (en) * | 2006-04-21 | 2006-09-13 | 太原理工大学 | Device for monitoring fatigue driving state and its method |
| CN101090482A (en) * | 2006-06-13 | 2007-12-19 | 唐琎 | Driver fatigue monitoring system and method based on image process and information mixing technology |
| US20090097707A1 (en) * | 2007-10-12 | 2009-04-16 | Samsung Techwin Co., Ltd. | Method of controlling digital image processing apparatus for face detection, and digital image processing apparatus employing the method |
| CN102393989A (en) * | 2011-07-28 | 2012-03-28 | 山西智济电子科技有限公司 | Real-time monitoring system of driver working state |
| CN102426757A (en) * | 2011-12-02 | 2012-04-25 | 上海大学 | Safety driving monitoring system based on mode identification and method thereof |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105128627A (en) * | 2015-09-07 | 2015-12-09 | 湖南科技大学 | Overheat protection device for automobile |
| CN105574487A (en) * | 2015-11-26 | 2016-05-11 | 中国第一汽车股份有限公司 | Facial feature based driver attention state detection method |
| CN105469073A (en) * | 2015-12-16 | 2016-04-06 | 安徽创世科技有限公司 | Kinect-based call making and answering monitoring method of driver |
| CN105787438A (en) * | 2016-02-03 | 2016-07-20 | 郑州畅想高科股份有限公司 | Video-based locomotive driver driving state detection method and system |
| CN105825631B (en) * | 2016-04-26 | 2018-01-16 | 成都远控科技有限公司 | fatigue detection method and system based on video intelligent algorithm |
| CN105825631A (en) * | 2016-04-26 | 2016-08-03 | 成都远控科技有限公司 | Video intelligent algorithm-based fatigue detection method and system |
| CN105788176B (en) * | 2016-05-25 | 2018-01-26 | 厦门理工学院 | Fatigue driving monitors based reminding method and system |
| CN105788176A (en) * | 2016-05-25 | 2016-07-20 | 厦门理工学院 | Fatigue driving monitoring and prompting method and system |
| CN106778532A (en) * | 2016-11-28 | 2017-05-31 | 合肥工业大学 | Based on the driving posture feature sorting technique for removing differentiation size parameter |
| CN106778532B (en) * | 2016-11-28 | 2019-05-31 | 合肥工业大学 | Based on the driving posture feature classification method for removing differentiation size parameter |
| US11065958B2 (en) | 2017-01-03 | 2021-07-20 | Transportation Ip Holdings, Llc | Control system and method |
| US10328946B2 (en) | 2017-01-03 | 2019-06-25 | Ge Global Sourcing Llc | Alerter augmentation system |
| US10370012B2 (en) | 2017-03-09 | 2019-08-06 | Ge Global Sourcing Llc | Adaptive vehicle control system |
| CN107126224A (en) * | 2017-06-20 | 2017-09-05 | 中南大学 | A kind of real-time monitoring of track train driver status based on Kinect and method for early warning and system |
| CN107194381A (en) * | 2017-07-06 | 2017-09-22 | 重庆邮电大学 | Driver status monitoring system based on Kinect |
| CN108583592A (en) * | 2017-12-30 | 2018-09-28 | 西安市地下铁道有限责任公司 | A kind of subway service on buses or trains job information acquisition intelligent detecting method |
| CN110136381B (en) * | 2018-02-07 | 2023-04-07 | 中国石油化工股份有限公司 | On-spot personnel of drilling operation monitoring early warning system that stands |
| CN110136381A (en) * | 2018-02-07 | 2019-08-16 | 中国石油化工股份有限公司 | A kind of well drilling operation site personnel standing monitoring and warning system |
| US10915769B2 (en) | 2018-06-04 | 2021-02-09 | Shanghai Sensetime Intelligent Technology Co., Ltd | Driving management methods and systems, vehicle-mounted intelligent systems, electronic devices, and medium |
| CN109002757A (en) * | 2018-06-04 | 2018-12-14 | 上海商汤智能科技有限公司 | Drive management method and system, vehicle intelligent system, electronic equipment, medium |
| US10970571B2 (en) | 2018-06-04 | 2021-04-06 | Shanghai Sensetime Intelligent Technology Co., Ltd. | Vehicle control method and system, vehicle-mounted intelligent system, electronic device, and medium |
| CN108830240A (en) * | 2018-06-22 | 2018-11-16 | 广州通达汽车电气股份有限公司 | Fatigue driving state detection method, device, computer equipment and storage medium |
| CN111052127A (en) * | 2018-09-12 | 2020-04-21 | 北京嘀嘀无限科技发展有限公司 | System and method for fatigue detection |
| CN112149482A (en) * | 2019-06-28 | 2020-12-29 | 深圳市商汤科技有限公司 | Method, device and equipment for detecting on-duty state of driver and computer storage medium |
| CN110618635A (en) * | 2019-10-08 | 2019-12-27 | 中兴飞流信息科技有限公司 | Train cab operation specification monitoring system based on AI technology |
| CN112230760A (en) * | 2020-09-17 | 2021-01-15 | 淮南师范学院 | Analysis system and method based on combination of user operation and biological characteristics |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104732251B (en) | 2017-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104732251A (en) | Video-based method of detecting driving state of locomotive driver | |
| Tipprasert et al. | A method of driver’s eyes closure and yawning detection for drowsiness analysis by infrared camera | |
| CN101639894B (en) | Method for detecting train driver behavior and fatigue state on line and detection system thereof | |
| CN105208343B (en) | Can be used for intelligent monitor system and the method for video monitoring equipment | |
| CN101593425B (en) | Machine vision based fatigue driving monitoring method and system | |
| CN102393989B (en) | Real-time monitoring system of driver working state | |
| CN101577812B (en) | Method and system for post monitoring | |
| CN104183091B (en) | System for adjusting sensitivity of fatigue driving early warning system in self-adaptive mode | |
| Liu et al. | Drowsiness detection based on eyelid movement | |
| CN103150870B (en) | Train motorman fatigue detecting method based on videos | |
| CN101655907B (en) | Trainman driving state monitoring intelligent alarm system | |
| CN104809887B (en) | A kind of retrograde detection method of vehicle on expressway and autoalarm | |
| TW201112180A (en) | Driver monitoring system and its method thereof | |
| CN206023052U (en) | A kind of HV Transmission Line Routing Inspection robot | |
| CN105894735B (en) | A kind of intelligent vehicle-mounted fatigue monitoring system and method | |
| CN103340637A (en) | System and method for driver alertness intelligent monitoring based on fusion of eye movement and brain waves | |
| CN104794855A (en) | Driver's attention comprehensive assessment system | |
| Katyal et al. | Safe driving by detecting lane discipline and driver drowsiness | |
| CN104068868A (en) | Method and device for monitoring driver fatigue on basis of machine vision | |
| CN103700220A (en) | Fatigue driving monitoring device | |
| Anjali et al. | Real-time nonintrusive monitoring and detection of eye blinking in view of accident prevention due to drowsiness | |
| Hemadri et al. | Detection of drowsiness using fusion of yawning and eyelid movements | |
| CN107585026A (en) | A kind of anti-fatigue-driving system | |
| CN106408877A (en) | Rail traffic driver fatigue state monitoring method | |
| Du et al. | Driver fatigue detection based on eye state analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |