Distraction detection system

Abstract

The utility model relates to the technical field of behavior analysis, and provides a distraction detection system which comprises a physiological signal detection module used for acquiring physiological signals; the physiological signals comprise an electroencephalogram signal, an electro-oculogram signal, an electrocardiosignal, a double-arm electromyographic signal, a throat mechanical signal, a neck mechanical signal, an elbow mechanical signal and a wrist mechanical signal; the physiological signal detection module comprises at least one physiological electric electrode and at least one pressure sensor; the signal acquisition module is used for collecting the physiological signals and transmitting the physiological signals to the signal processing module; and the signal processing module is used for carrying out data processing on the physiological signals and carrying out distraction detection according to a data processing result. According to the utility model, high-precision acquisition of various physiological signals can be realized; the pressure sensor can realize low detection lower limit, high pressure detection sensitivity and quick response, and has small influence on a user.

Description

TECHNICAL FIELD

[0001] The utility model relates to behavior analysis technical field especially relates to a distraction detection system. BACKGROUND

[0002] Distraction driving and thinking wandering will lead to the driver's attention cannot be fully concentrated on the driving task, reduce the driver's reaction to the outside world dangerous situation, is one of the key factors leading to road traffic safety accidents. Distraction driving is due to the influence of some objects, people or actions in or outside the vehicle, which leads to the driver's distraction; thinking wandering is that the driver's attention is reduced due to some unrelated thinking activities under the condition of no external interference. Research statistics show that about 80% of vehicle collision accidents are caused by driver distraction driving or thinking wandering. Although the domestic and foreign automobile industry has begun the related research work of intelligent auxiliary driving system and safe driving detection, the driver as the final controller of the vehicle still needs to maintain attention to ensure the safety of driving. Therefore, in order to avoid the traffic accidents caused by the driver's distraction driving and thinking wandering, it is urgent to carry out the detection research on distraction driving and thinking wandering.

[0003] There are three methods for evaluating the state of driver distraction driving and thinking wandering: driving environment parameter evaluation, vision-based driving behavior evaluation and physiological parameter evaluation. Driving environment parameter evaluation includes extracting vehicle speed, vehicle position, steering wheel angle and speed in vehicle driving, and analyzing the obtained parameters by numerical analysis method, but this method has poor real-time performance, and in a more complex driving environment, the obtained data will have large error. The vision-based driving behavior evaluation method mainly detects the behavior of the driver's hands, head and face, and analyzes the behavior related to distraction driving by means of deep learning method, but this method will consume a lot of computing power and energy in long time driving, and it is difficult to detect the distraction state in dark environment, and it cannot evaluate the state of the driver's thinking wandering. The physiological parameter evaluation method collects the electroencephalogram (EEG) signal, electrocardiogram (ECG) signal, electrooculogram (EOG) signal, respiration and joint movement information of the driver to evaluate the driver's vigilance, but the current physiological parameter evaluation method is limited by the single type of physiological signal collected, low real-time of distraction detection, and the problem that wearing physiological information collection device may affect the driver's operation, which leads to difficult further development.

[0004] In summary, the detection device in the prior art has the problems of single type of physiological signal collected, low real-time of distraction detection, and large influence of the device on the driver. UTILITY MODEL CONTENT

[0005] The utility model provides a kind of distraction detection system, to solve the physiological signal type of acquisition in prior art single, distraction detection real-time lower, the defect of big influence to user, realize the distraction detection of the physiological signal of acquisition multiple, distraction detection real-time higher, small influence to user.

[0006] The utility model provides a kind of distraction detection system, comprising:

[0007] Physiological signal detection module, the physiological signal detection module is used to obtain physiological signal;The physiological signal includes brain electrical signal, eye electrical signal, electrocardiogram signal, bimanual electromyogram signal, throat mechanics signal, neck mechanics signal, elbow mechanics signal and wrist mechanics signal;The physiological signal detection module includes at least one physiological electrical electrode and at least one pressure sensor;

[0008] Signal acquisition module, the signal acquisition module is used to collect the physiological signal, and the physiological signal is transmitted to signal processing module;

[0009] Signal processing module, the signal processing module is used to carry out data processing to the physiological signal, and carries out distraction detection according to data processing result.

[0010] According to the utility model provides a kind of distraction detection system, the physiological signal detection module is attached to the human skin surface of the preset position of the object to be measured, to carry out the acquisition of the physiological signal.

[0011] According to the utility model provides a kind of distraction detection system, the physiological electrical electrode is prepared by using the laser irradiation PI film of preset wavelength, preset laser power.

[0012] According to the utility model provides a kind of distraction detection system, the pressure sensor is obtained after the target substrate is stripped, and conductive material is spin-coated on the surface of the target substrate;Wherein, the target substrate is obtained after spin-coating PDMS film in the square opening silicon mold prepared in advance and solidification.

[0013] According to the utility model provides a kind of distraction detection system, the signal processing module utilizes one-dimensional resnet18 network to carry out data processing to the physiological signal.

[0014] According to the utility model provides a kind of distraction detection system, according to data processing result carries out distraction detection, specifically includes: detecting the staring, eyes look to right, adjusting panel, right hand sends short message, thinks other things, scratches head, drinks water, arranges hair, eyes look up, left bends, left hand mobile phone, turns back, eyes look down, right bends, right hand mobile phone, chats, eyes look left, yawns state in the driving process of driver.

[0015] The preset positions include forehead, wrist, arms, throat, neck and wrist.

[0016] According to the distraction detection system, the signal acquisition module collects the physiological signals by using a single-chip microcomputer.

[0017] According to the distraction detection system, the physiological electrode is prepared by using a laser direct writing graphene oxide film with preset wavelength and preset laser power.

[0018] According to the distraction detection system, the pressure sensor is prepared by using a device sensitive layer.

[0019] The distraction detection system comprises a physiological signal detection module, a signal acquisition module and a signal processing module. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the present application or 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 some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0021] Figure 1 is one of the structural schematic diagrams of the distraction detection system provided by the present application.

[0022] Figure 2It is the structure schematic view two of the distraction detection system provided by the utility model.

[0023] Figure 3 It is the flow schematic view of preparation pressure sensor of the distraction detection system provided by the utility model.

[0024] Figure 4 It is the schematic view of ECG signal collected of the distraction detection system provided by the utility model.

[0025] Figure 5 It is the schematic view of EOG signal collected of the distraction detection system provided by the utility model.

[0026] Figure 6 It is the schematic view of EMG signal collected of the distraction detection system provided by the utility model.

[0027] Figure 7 It is the schematic view of EEG signal collected of the distraction detection system provided by the utility model.

[0028] Figure 8 It is the test performance schematic view of the mechanical signal of the pressure sensor of the distraction detection system provided by the utility model.

[0029] Figure 9 The output resistance change schematic view of the graphene pressure sensor of the pressure sensor of the distraction detection system provided by the utility model under 0.1 Pa sound pressure. Specific implementation

[0030] In order to make the purpose, technical scheme and advantages of the utility model more clear, the technical scheme in the utility model will be described clearly and completely in combination with the drawings in the utility model, obviously, the described embodiment is a part of the embodiment of the utility model, rather than all the embodiment. Based on the embodiment in the utility model, all other embodiments obtained by the person skilled in the art without making creative labor belong to the scope of protection of the utility model.

[0031] The distraction detection system of the utility model will be described below in combination with Figures 1-9 The distraction detection system of the utility model, Figure 1 It is the structure schematic view one of the distraction detection system provided by the utility model, as Figure 1 The system comprises:

[0032] The physiological signal detection module 110 is used for acquiring physiological signals, and comprises at least one physiological electrode and at least one pressure sensor.

[0033] It should be noted that, in the embodiments of the present application, the physiological signal detection module 110 includes at least one physiological electrode and at least one pressure sensor, and the physiological signal detection module 110 is prepared by combining two-dimensional materials and micro-nano processing technology. The physiological signal detection module 110 can realize high-precision acquisition of physiological signals through the physiological electrode, and can realize low detection lower limit, high pressure detection sensitivity and fast response through the pressure sensor. The preparation of the pressure sensor and the physiological electrode will be further described in the subsequent embodiments.

[0034] As shown in Figure 2 , the physiological signal detection module 110 is installed on the skin surface of the measured object to acquire physiological signals. The physiological signals include electroencephalogram (EEG) signals, electrooculogram (EOG) signals, electrocardiogram (ECG) signals, electromyogram (EMG) signals at both arms, throat mechanical signals, neck mechanical signals, elbow mechanical signals and wrist mechanical signals.

[0035] The physiological signals will be further described below. Figure 4 The collected ECG signals are shown, and the signal-to-noise ratio is 45.3 dB; Figure 5 The EOG signals when looking up, looking down, looking left, looking right and blinking are shown; Figure 6 The EMG signals at the forearm under different grip strength are shown, and the EMG signals increase with the increase of grip strength; Figure 7 The time-frequency diagram of the EEG signals when closing eyes and opening eyes is shown, and when the volunteer closes eyes, the brain is in a relaxed state, and Alpha waves appear, with a frequency of about 10 Hz.

[0036] Further, in some embodiments, the physiological signal detection module is attached to the skin surface of the measured object at a predetermined position to acquire the physiological signals.

[0037] Further, in some embodiments, as shown in Figure 2 , the predetermined position includes forehead, wrist, both arms, throat, neck and wrist.

[0038] The signal acquisition module 120 is used to collect the physiological signals and transmit the physiological signals to the signal processing module.

[0039] After the physiological signals are acquired, the signal acquisition module 120 is used to collect the physiological signals and transmit the physiological signals to the signal processing module 130 for subsequent processing.

[0040] It can be understood that the present application does not specifically limit the way of collecting physiological signals and the specific transmission method, which can be selected according to the actual situation.

[0041] In one embodiment, the physiological signal is collected by a single-chip microcomputer.

[0042] In another embodiment, the physiological signal is transmitted to the signal processing module 130 by WiFi.

[0043] The signal processing module 130 is configured to process the physiological signal and detect distraction based on the processing result.

[0044] It should be understood that the position of the signal processing module 130 is not limited, and the signal processing module 130 can be arranged in the cloud (e.g. Figure 2 It can also be arranged in the hardware part.

[0045] Further, in the embodiment of the present application, the distraction detection system can be regarded as a flexible wearable electronic skin with multi-modal perception function.

[0046] In some embodiments, the signal processing module 130 processes the physiological signal by using a one-dimensional resnet18 network. Specifically, the one-dimensional resnet18 network is used as a device monitoring model to process one-dimensional physiological signals. The construction and training process of the one-dimensional resnet18 network are not described in detail. The one-dimensional resnet18 network is used to process the physiological signal in this embodiment, and the inference speed of the model can be ensured to meet the real-time monitoring requirements by adjusting the one-dimensional resnet18 network.

[0047] During data processing, the physiological signal can be first cleaned of missing values and outliers to ensure data quality.

[0048] In some embodiments, the distraction detection is performed based on the processing result, specifically including: detecting the driver's staring, looking right, adjusting the panel, right-hand texting, thinking about other things, scratching the head, drinking water, arranging the hair, looking up, left bending, left-hand texting, turning back, looking down, right bending, right-hand texting, chatting, looking left, and yawning state.

[0049] Specifically, the present application also develops a distraction driving and thought wandering detection algorithm and system based on high-performance physiological electrodes and pressure sensors.

[0050] The present application is suitable for all scenes requiring distraction detection, including distraction driving and thought wandering detection.

[0051] The preparation of the physiological electricity electrode is further described below. In some embodiments, the physiological electricity electrode is prepared by irradiating a PI film with a laser having a preset wavelength and a preset laser power.

[0052] Specifically, it can be understood that graphene is a two-dimensional material with good mechanical properties, electrical properties, high electron mobility and low biological toxicity, and is an ideal physiological electricity electrode. The graphene physiological electricity electrode is prepared by the method of laser direct writing of a polyimide film (PI film).

[0053] In the specific implementation process, the PI film is irradiated with a laser having a preset wavelength and a preset laser power, and the size of the obtained graphene sensing unit is 1 cm*1 cm. Then, the signal is led out through the two side leads.

[0054] In one specific embodiment, the preset wavelength is 450 nm, and the preset laser power is 260 mW / cm 2 .

[0055] In some other embodiments, the physiological electricity electrode is prepared by laser direct writing of a graphene oxide film having a preset wavelength and a preset laser power.

[0056] Specifically, the physiological electricity electrode can also be prepared by laser direct writing of a graphene oxide film.

[0057] Further, the physiological electricity electrode can also be prepared by using a graphene aqueous solution. In some embodiments, a commercial electrode can also be used as the physiological electricity electrode.

[0058] The preparation of the pressure sensor is further described below. In some embodiments, the pressure sensor is obtained by spin-coating a conductive material on the surface of a target substrate after peeling off the target substrate, wherein the target substrate is obtained by spin-coating a PDMS film in a square opening silicon mold prepared in advance and then solidifying.

[0059] Specifically, the preparation of the sensing unit of the pressure sensor of the present embodiment also uses graphene. The preparation process is as shown in Figure 3 Specifically, first, a silicon mold with a square opening is prepared. Under the action of a wet process, the square opening forms a pyramid structure. Then, a PDMS film is spin-coated in the square opening silicon mold prepared in advance. After the PDMS film is solidified, the PDMS is peeled off to form a PDMS substrate (i.e. target substrate) with a pyramid structure. Then, an aqueous graphene oxide solution or other conductive material is spin-coated on the surface of the PDMS of the target substrate. After reduction, the conductive materials of the two identical PDMS substrates are laminated.

[0060] In one embodiment, the square opening silicon mold has an opening size of 10 µm.

[0061] Figure 8 The device pressure detection sensitivity of the pressure sensor prepared by the preparation method provided in the embodiment is 62.2 kPa -1 . Figure 9 The resistance signal change of the pressure sensor prepared by the preparation method provided in the embodiment when the sound pressure is 0.1 Pa is shown, and the red and black parts respectively correspond to the resistance values when the device senses the pressure and the pressure is removed. It can be observed that the change of the device resistance when the pressure is applied is obviously higher than the test noise, which indicates that the device can realize the detection of 0.1 Pa sound pressure.

[0062] In other embodiments, the pressure sensor is prepared by using the device sensitive layer.

[0063] Specifically, the pressure sensor can also be prepared by using the device sensitive layer. In some embodiments, a strain sensor can also be used as a pressure sensor for mechanical signal monitoring.

[0064] The distraction detection system provided by the utility model discloses a physiological signal detection module, the physiological signal detection module is used for obtaining physiological signal, the physiological signal includes electroencephalogram signal, electrooculogram signal, electrocardiogram signal, bimanual myoelectric signal, throat mechanical signal, neck mechanical signal, elbow mechanical signal and wrist mechanical signal, the physiological signal detection module includes at least one physiological electrode and at least one pressure sensor, signal acquisition module, the signal acquisition module is used for collecting the physiological signal, and the physiological signal is transmitted to the signal processing module, signal processing module, the signal processing module is used for carrying out data processing to the physiological signal, and carries out distraction detection according to data processing result. The utility model discloses a physiological signal detection through physiological electrode and pressure sensor, wherein the physiological electrode can realize the high-precision acquisition of multiple physiological signals, and the mechanical sensor can realize low detection lower limit, high pressure detection sensitivity and fast response, and has little influence on the user. On the basis of high-performance physiological electrode and pressure sensor, the signal acquisition module is used for the real-time collection and uploading of physiological signal, and the signal processing module is used for real-time distraction detection, so that the problems of single physiological signal type, low real-time distraction detection and great influence on the user in the prior art are solved.

[0065] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected to achieve the purposes of the embodiments according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0066] Through the description of the above embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software and the necessary general hardware platform, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0067] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to part of the technical features; and these modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A distraction detection system characterized by, The application relates to a physiological signal detection device and a physiological signal detection method. The physiological signal detection device comprises a physiological signal detection module, a signal collection module and a signal processing module. The physiological signal detection module is used for acquiring physiological signals. The physiological signals include electroencephalogram signals, electrooculogram signals, electrocardiogram signals, biceps electromyogram signals, throat mechanical signals, neck mechanical signals, elbow mechanical signals and wrist mechanical signals. The physiological signal detection module comprises at least one physiological electrode and at least one pressure sensor. The signal collection module is used for collecting the physiological signals and transmitting the physiological signals to the signal processing module.

2. The distraction detection system of claim 1, wherein, The signal processing module is used for data processing of the physiological signals and distraction detection according to the data processing result.

3. The distraction detection system of claim 1, wherein, The physiological signal detection module is attached to the skin surface of a preset position of a to-be-detected object to acquire the physiological signals.

4. The distraction detection system of claim 1, wherein, The physiological electrode is prepared by using a PI film irradiated by laser with a preset wavelength and a preset laser power.

5. The distraction detection system of claim 1, wherein, The pressure sensor is obtained by spin-coating conductive material on the surface of a target substrate after the target substrate is peeled off.

6. The distraction detection system of claim 1, wherein, The target substrate is obtained by spin-coating a PDMS film in a square opening silicon mold. The signal processing module uses a one-dimensional resnet18 network to process the physiological signals.

7. The distraction detection system of claim 2, wherein, The distraction detection according to the data processing result comprises the following steps.

8. The distraction detection system of claim 1, wherein, The distraction detection according to the data processing result comprises the following steps.

9. The distraction detection system of claim 1, wherein, The distraction detection according to the data processing result comprises the following steps.

10. The distraction detection system of claim 1, wherein, The distraction detection according to the data processing result comprises the following steps. The preset position comprises a forehead, wrists, arms, a throat, a neck and wrists. The signal collection module collects the physiological signals by using a single-chip microcomputer. The physiological electrode is prepared by using a graphene oxide film directly written by laser with a preset wavelength and a preset laser power. The pressure sensor is prepared by using a device sensitive layer. The pressure sensor is prepared by using a device sensitive layer.

Images