301 results about "Driver Distractions" patented technology

The invention relates to the technical field of driving, and particularly discloses a mobile phone management and control method and a control system in a driving process. Vehicle running state data and mobile phone multi-mode sensing data are obtained, vehicle CAN bus information and mobile phone sensor data are combined, a motion coupling degree value is calculated on the basis of deviation of a steering wheel angle and mobile phone acceleration, the operation synchronization rate is analyzed through accelerator operation and gyroscope response, hand action coordination is evaluated, and the hand action coordination is evaluated. The method comprises the following steps: calculating a spatial constraint deviation value by combining a magnetometer orientation and a driving position coordinate offset degree; monitoring an abnormal posture of a driver; generating a risk assessment value by fusing three indexes; dynamically controlling a mobile phone function; according to the system, through multi-source data fusion and a hierarchical management and control strategy, emergency communication requirements are balanced on the premise of ensuring driving safety, distracted driving behaviors are accurately identified, and driving potential safety hazards caused by use of a mobile phone are solved.

The invention discloses a driver distraction detection method based on ResPrompt and double cross attention, and the method comprises the steps: inputting a front / side visual angle image of a driver distraction behavior into a linear embedding module and a ResPrompt module, carrying out the partitioning of the image through the linear embedding module, generating a feature vector, and generating a prompt vector of the image through the ResPrompt module; performing multi-scale feature extraction on the feature vector of the front / side view angle image and the most matched prompt vector by using a Swindow-Transfomer module to generate each view angle feature; and fusing the double-view-angle features by using a double-cross attention module, inputting the double-view-angle features into a classifier fusing center loss, and performing behavior detection on the features to generate a final detection result. According to the method, the accuracy and robustness of detection can be effectively improved, and reliable technical support is provided for safe operation of semi-automatic and automatic driving vehicles.

The invention provides a lightweight driver distraction behavior detection method, and belongs to the technical field of computer vision. The technical problems that a distraction driving detection algorithm model is complex in structure and large in parameter quantity, and model light weight and detection precision are unbalanced are solved. According to the technical scheme, the method comprises the following steps: S1, collecting distraction driving behavior data pictures, and constructing a distraction driving behavior data set; s2, a lightweight distracted driving detection network ASU-YOLO is constructed on the basis of the YOLOv8n model; s3, training the constructed ASU-YOLO network model by using the manufactured distraction driving behavior data set to obtain a lightweight distraction driving detection model; and S4, detecting distraction driving behaviors through the trained model. The method has the beneficial effects that the detection precision of the model is improved while the parameter quantity and the calculation quantity of the algorithm are reduced, the light weight of the model is realized, and the requirement of real-time detection is met.

The invention provides a driver distraction behavior recognition method based on a deep learning optimization YOLO fusion network model. The method comprises the following steps: constructing a vehicle driver distraction behavior standard image data set G20 in a highway scene; a deep learning-based driver distraction behavior recognition method in an expressway scene is researched, three models of YOLOv5, YOLOv8 and YOLOv11 for driver distraction behavior recognition are constructed, and the comprehensive detection performance of the models is analyzed and compared; the method comprises the following steps: constructing driver distraction behavior recognition models YOLOv11n-ECA, YOLOv11n-BiFPN-GLAS and YOLOv11n-SIoU based on an optimization method, and analyzing the improvement advantages and comprehensive detection performance of the driver distraction behavior recognition models; the improved methods are fused to construct an optimized fusion network YOLOv11n-Driver, and the test accuracy, the test recall rate, the F1-Score, the average precision and the consumed time of each image on a constructed G20 data set respectively reach 93.1%, 95.4%, 94.2%, 98.3% and 3.4 ms / image, so that a feasible method is provided for optimizing the recognition performance of a YOLO model on driver distraction behaviors in an expressway scene.

A system (1) for efficiently determining a driving behaviour of a driver driving a vehicle. The system includes a 3-axis accelerometer (2) generating accelerometer data (3), a direction sensor (4) generating direction data (5) and orientation sensor (6) generating orientation and angular velocity data (7), all placed inside the vehicle. The system (1) also includes a processing unit (8) which processes the accelerometer data (3), the direction data (5) and the orientation data (7), and calibrates the accelerometer data (3) to generate a calibrated accelerometer data (9). The calibrated accelerometer data (9) is used in determining the driving behaviour of the driver of the vehicle and generate Driving Deficiency Alerts, including but not limited to Over-speeding. Hard acceleration. Sudden Braking, Fast Cornering, Quick Lane Changing, Distracted Driving, Dangerous Driving over bumps and Crash Detection.

The invention discloses a driver distracted driving behavior recognition method based on comparative learning and real-time edge calculation, and relates to the technical field of intelligent traffic monitoring. Comprises: obtaining a target data set; a Yov5 detection model is constructed, and the Yov5 detection model is pre-trained; changing a pre-trained Yov5 detection model into a Yov5 classification model, and performing training again on the target data set to obtain a trained PT model; improving the PT model based on a comparative learning method; performing BN layer pruning on the improved PT model, and performing quantization processing on the PT model after pruning; converting the PT model into an ONNX model, then converting the ONNX model into an RKNN model, and pre-compiling the ONNX model; and finally, performing real-time reasoning on an edge computing platform by using the pre-compiled RKNN model. According to the method, the model learns the feature extractor with the characterization capability by utilizing comparative learning, so that the accuracy of driver behavior classification is effectively improved.

The disclosure relates to technology for monitoring driver attentiveness in a vehicle. A driver distraction system collects vehicle data and scene information from the vehicle while traveling on a route. The vehicle data and scene information are then processed to generate a reference heat map. At the same time, the driver distraction system may capture a gaze of a driver to track a gaze direction and duration of the driver while driving the vehicle on the route. The gaze direction and duration are processed to generate a driver gaze heat map. The driver gaze heat map and reference heat map are analyzed to determine a level of driver distraction of the driver in the vehicle, and a recommendation or warning is output to the driver of the vehicle according to the level of driver distraction.

The invention relates to an assistance system (9) and to a corresponding method (15) for warning a driver (2) in an assisted or partially automated driving mode of a motor vehicle (1). Accordingly, when the driver (2) is first distracted, a distraction warning (14) is output after the expiry of a first warning period during which the driver (2) was distracted. If the driver (2) is distracted again within a predefined repetition period, then a distraction warning (14) is output to the driver (2) after a shorter second warning time. The invention also relates to a correspondingly configured motor vehicle (1).

The invention relates to the technical field of automobile data recorders, in particular to an AI intelligent driving behavior analysis automobile data recorder, which is used for acquiring the real-time vehicle condition in front of a driving vehicle and the driving behavior of a driver in the vehicle and acquiring the driving behavior data of the driver based on the acquisition of the driving behavior data of the driver. The feature extraction module is used for extracting hand actions and eye actions in the driving behaviors of the driver, the hand actions are used as judgment criteria for standardizing the driving behaviors, and the eye actions are used as compensation basis for judging the concentration of the driver; the driving behavior is scored and predicted through a driving behavior scoring model pre-constructed by a risk prediction module, a scoring threshold value of dangerous driving and a scoring threshold value of distracted driving are set, risk-based judgment is carried out according to the score of the driving behavior, and warning is carried out through a warning module according to the judged driving behavior risk-based judgment. Therefore, the driver is reminded to correct the driving behavior in time, and traffic accidents are avoided.

A computer system is provided and is programmed to: (1) receive sensor data associated with a primary vehicle; (2) determine a current condition of a driver of the primary vehicle based upon the sensor data of the primary vehicle; (3) determine a threat level for the primary vehicle based upon the current condition of the driver of the primary vehicle and the sensor data of the primary vehicle; (4) activate at least one action in the primary vehicle based upon the threat level for the primary vehicle; and / or (5) electronically transmit the threat level of the primary vehicle to one or more additional vehicles.

The invention provides an automobile driver driving behavior identification method and device. The method comprises the following steps: constructing an original identification model comprising an encoder based on a depth separable convolutional network and a decoder based on a compression excitation network; training the original recognition model through the driving behavior sample data and the training configuration data to obtain a driver distraction recognition model; deploying the driver distraction identification model to a vehicle-mounted hardware platform of a target vehicle; in the process that a driver drives the target vehicle, video stream data collected by a cabin camera on the target vehicle is obtained; performing driving behavior recognition processing according to the driver distraction recognition model and the video stream data to obtain a recognition result; and determining the current driving behavior of the driver according to the identification result. Therefore, the method and the device can identify the driving behavior of the driver in real time, are good in accuracy and stability, do not need the driver to wear detection equipment, and ensure the driving experience and comfort of the driver.

The invention provides a driver distracted driving detection method and device, terminal equipment and a program product, and the method comprises the steps: obtaining a real-time image of a vehicle driven by a driver when the driving speed of the vehicle is greater than a preset speed threshold value; determining a real-time head pose and a real-time sight angle corresponding to each real-time image; the real-time head pose comprises a real-time head pitch angle and a real-time head yaw angle; the real-time sight angle comprises a real-time sight pitch angle and a real-time sight yaw angle; if the continuous preset number of the real-time head poses are within the preset head pose range and the real-time sight angles exceed the preset sight angle range, it is judged that the driver has the distracted driving behavior. According to the method, whether the driver has the distracted driving behavior or not can be judged by combining the real-time head posture and the real-time sight angle of the driver in the vehicle driving process, whether the driver has the distracted driving behavior or not can be more accurately determined, and misjudgment is avoided.

The invention relates to an assistance system (9) and a corresponding method (15) for warning a driver (2) in an assisted or partially automated driving mode of a motor vehicle (1). Accordingly, if the driver (2) is distracted for the first time, a distraction warning (14) is issued after a first warning period during which the driver (2) was distracted. If the driver (2) is distracted again within a predetermined repetition period, a distraction warning (14) is then issued to the driver (2) after a shorter second warning period. The invention also relates to a correspondingly equipped motor vehicle (1).

The invention discloses an auxiliary display method and system for an automobile central control large screen, and the method comprises the steps: firstly, collecting the real-time state of an automobile after ignition, reading the biological characteristics of a driver, and carrying out the data monitoring of an environment to judge a driving scene; dynamically distributing a screen area according to the scene risk level and the task priority; judging the priorities of the voice, the gesture and the touch screen according to the scene risk level; according to the method, early warning information is improved and automatic reminding is carried out when a driver is distracted to drive, priority display content on a screen is distributed according to different scenes, unnecessary content is folded and hidden in a specific scene, information priority display in different scenes is improved, the distraction scenes of the driver are reduced, and the driving safety is improved in a high-risk scene of a highway section. The screen improves the priority of voice interaction, and the risk that a driver is distracted during high-speed driving is avoided.

The invention relates to the technical field of vehicles, in particular to a steering wheel gesture interaction method and device, a vehicle and a storage medium, and the method comprises the steps: obtaining a first monitoring gesture of a first area of a steering wheel and a second monitoring gesture of a second area; and determining a to-be-executed function according to the first monitoring gesture and the second monitoring gesture, and controlling the vehicle to execute the to-be-executed function. Therefore, the problem that a driver is easily distracted and safety risks are generated due to a steering wheel interaction mode in the related technology is solved, accurate control over the vehicle multimedia system and the communication function is achieved by recognizing different steering wheel interaction gestures, and operation convenience and safety in the driving process are improved.

An inside cabin sensor system, having an integrated, single hardware part comprising a camera sub-system and an integrated radar sub-system is proposed. A proposed system provides related information for covering the following applications inside a vehicle: Child Presence Detection (CPD), Driver Drowsiness & Fatigue (F), Driver Distraction (DD) as a safety-relevant function, complemented by Intrusion & Proximity Alert (IPA), Seat Occupancy Detection (SOD), Face Recognition (FR), and optional applications such as Driver Emotion (ES), Passenger Classification (PC), Airbag Suppression (AS), Airbag Activation (AA), Mobile Phone Detection (MP), Gesture Detection (GD) and Vital Signs Detection (VS). A proposed system utilizes Artificial Intelligence (AI)-related data processing for data processing, using radar point cloud data, calculated by said radar sensors. The proposed system utilizes Artificial Intelligence (AI)-related data processing for data processing, using video-captured data. The proposed system utilizes Artificial Intelligence (AI) -related data processing for sensor data fusion, using radar sensor and video sensor data.

Method and apparatus, including computer programs, for providing a driver distraction signal and / or a system degradation signal indicating a reliability of the driver distraction signal, based on a gaze of a driver of a vehicle. Images of the driver of the vehicle are received, which contain information indicating a gaze of the driver. For each image, a gaze region for the driver is determined, including a gaze point and a gaze uncertainty value. For each image, the gaze region is associated with a region among several regions around the vehicle, wherein the regions include at least one pre-defined attentive region and at least one pre-defined inattentive region. Based on the determined gaze region, the gaze uncertainty value, and the region for a plurality of images, a driver distraction level and / or system degradation level indicating a reliability of the driver distraction level are determined.

The invention discloses a railway driver distraction behavior identification method based on a visual large model, and belongs to the technical field of railway safety monitoring. Comprises: constructing a data set; based on the data set, training the visual big language model by adopting a LoRA method to obtain a fine-tuning visual big language model; obtaining human body key point information on the original video data frame, and generating a skeleton diagram; and inputting the skeleton graph into the fine-tuning visual large language model, and outputting description information of the image and a corresponding cue word. According to the method, the technical route of lightweight posture recognition and visual large language model analysis is fused, and the posture of the driver is captured by adopting a character key point detection tool; meanwhile, a visual large language model is introduced, and correlation analysis of operation behaviors and environment equipment is achieved by constructing a driving scene knowledge graph; the performance bottleneck of a traditional monitoring system is broken through, a technical template capable of being copied and popularized is formed, and the method has important practical significance for improving the intrinsic safety level of railway transportation.

The invention relates to the technical field of vehicle interior light control, in particular to a vehicle interior light intelligent control device and a control method thereof.The control method includes the following steps that firstly, a front face image of a driver is collected through an in-vehicle camera, and working condition signals of the vehicle speed, steering lamps and the vehicle door state are obtained through a vehicle-mounted CAN bus; and 2, identifying a distraction action sequence of a driver by using a target detection model based on a target detection algorithm, and calculating an index of a fatigue state PERCLOS and an average eye closing duration # imgabs0 # in continuously acquired N frames of images. In the invention, based on image information acquired by a camera in a vehicle and a CAN bus working condition signal, the target detection algorithm and the fatigue identification index are fused, so that the driver distraction action sequence is identified, and the driver distraction action sequence is identified. Real-time identification of distraction and fatigue states of the driver is realized; when the state of a driver is abnormal, gradual prompting or warning can be rapidly carried out through lamplight, and the initiative, safety and comfort of man-machine interaction in a vehicle are effectively improved.

A method for detecting distraction of a driver in a driver monitoring system is disclosed. The method includes receiving a first image including the driver within a vehicle. The method includes determining a gaze class corresponding to the first image among a plurality of gaze classes by using a first model in response to the receiving the first image. The plurality of gaze classes includes a first gaze class indicating that the driver is gazing in a front direction and a second gaze class indicating that the driver is gazing in a non-front direction. The method includes determining whether the distraction of the driver is present in the first image based on the gaze class corresponding to the first image.

The invention discloses an intelligent visual cabin monitoring method based on multiple cameras and a vehicle, and belongs to the field of automobile intelligent cabins, and the method comprises the steps: obtaining the face information and the head posture of a driver through an IR camera, executing a driver state monitoring strategy according to the face information and the head posture of the driver, and obtaining a judgment result and alarm information, the judgment result and the alarm information are sent to a corresponding module of the whole vehicle; the condition in a cockpit is obtained through the wide-angle camera, a cockpit monitoring strategy is executed according to the condition in the cockpit to obtain the expression of a passenger or the state of an object, and the expression of the passenger or the state of the object is sent to a corresponding module of the whole vehicle. According to the invention, a cabin monitoring technology using a plurality of cameras as sensors is adopted, driver detection, passenger detection and cabin detection can be carried out, behaviors such as distraction and fatigue of a driver which are not beneficial to driving safety can be monitored, whether children, pets, wallets and the like are left in the cabin is checked, and financial loss of the driver is avoided.

Some embodiments relate to driver or occupant monitoring using vision language models (VLMs). Any number of DNNs in a detection pipeline may be replaced with a VLM, and the VLM may be prompted to determine whether a corresponding feature is present in an image or sampled frames from a video. To facilitate using the VLM(s) to control one or more downstream actions, the VLM(s) may be prompted using structured inputs, and a designated output format for a corresponding structured output may be enforced in any suitable manner. As such, any number of VLMs may be used to perform any number of driver and / or occupant monitoring tasks (e.g., driver drowsiness detection, driver distraction detection, driver or occupant out-of-position detection, driver or occupant identification, seatbelt usage detection, occupant presence detection, occupant classification, child presence detection, gesture recognition, occlusion detection, and / or others).

A method of operation for a compute system comprising: monitoring a phone sensor array to detect a trigger; calculating a position of a cell phone based on the trigger and sensor data from the phone sensor array; predicting a driver distraction event by analyzing the sensor data and the position of the cell phone; compiling a driver distraction evaluation based on the driver distraction event and a sensor data packet from an in-vehicle sensor array; generating a distraction rating for display on a device based on the driver distraction evaluation.

The invention relates to the technical field of intelligent driving, in particular to a vehicle control method, device and equipment based on electroencephalogram signals, a medium and a program.The method comprises the steps that the electroencephalogram signals of a driver under at least one dynamic visual stimulus are obtained; generating a matching result according to matching of the electroencephalogram signal and a reference signal of the at least one dynamic visual stimulation, and determining target visual stimulation from the at least one visual stimulation according to the matching result; a target control intention expected by the driver is determined according to the target visual stimulation, and the vehicle is controlled to execute corresponding operation according to the target control intention. Therefore, the problems that in the related technology, the interaction mode of a driver and a vehicle control system mainly depends on physical buttons, touch screens or voice instructions to achieve control over vehicle parts, distracted driving is easily caused, driving safety is affected, and the user experience feeling is poor are solved.

The invention discloses an attention reminding algorithm for intelligent driving based on multiple modes, and relates to the technical field of intelligent driving and active safety, and the algorithm comprises the steps: firstly, collecting data in real time through a multi-mode sensor group, carrying out the alignment, and then calculating the quantization features, such as the fixation deviation degree, the steering wheel disturbance entropy and the heart rate variability; then, mapping scores by adopting an S-type function, analyzing a historical sequence by utilizing a long short-term memory network to generate a dynamic weight, and performing adjustment and weighted calculation on a single-mode score in combination with an environment complexity weight to obtain a comprehensive attention score; and finally, according to the continuous driving duration, calculating a linear decreasing dynamic reminding threshold value, executing dual logic judgment in combination with the environmental risk level, and triggering graded feedback through sound and light or vibration. According to the method, the problems of poor adaptability and high false alarm rate of traditional single-mode monitoring in a dynamic environment are effectively solved, the robustness of the system is improved, and adaptive evaluation and accurate early warning of driver distraction behaviors in a complex scene are realized.

The invention relates to the field of vehicle intelligent control, in particular to a vehicle control method and device and a vehicle. Compared with a traditional mode depending on visual perception and a machine learning model, the driving state of the driver and the vehicle driving risk data are detected at the same time, the misjudgment limitation of single perception is avoided, for example, potential risks can be judged in an auxiliary mode through abnormal states such as distraction and fatigue of the driver. Secondly, whether active safety intervention is triggered or not can be determined by analyzing driving risk data in real time, the passive situation that a traditional algorithm focuses on protection after collision is changed, and real-time monitoring of danger in the driving process is achieved. The target intervention strategy is matched according to the driving state and the driving risk data, corresponding safety operation is executed, a complete closed loop from detection and analysis to active intervention is formed, the risk is actively reduced before an accident occurs, and the defect that the traditional technology lacks an active prevention mechanism is overcome.

The invention provides a driving emotion early warning method and system based on voice analysis, relates to the technical field of voice emotion recognition, and effectively solves the interference problem of vehicle-mounted dynamic strong noise by deploying a microphone array and a noise sensor in a cockpit and combining multi-channel noise reduction algorithms such as beam forming and linear beam minimum variance. A high-quality voice instruction is extracted from a source; on the basis, the driving intention of the clear voice signal is accurately recognized by using the deep neural network, so that the accuracy is remarkably improved; more importantly, according to the method, the instability Ls and the high interactive friction probability Pf are recognized innovatively through calculation instructions, real-time quantitative evaluation on the man-machine interaction fluency is achieved, when the interactive friction probability Pf exceeds a preset threshold value, the system can automatically trigger self-adaptive strategy adjustment, and therefore the situation that a driver is distracted due to recognition errors is avoided, and user experience is improved. And the interaction experience and the driving safety are greatly enhanced.

Driver insurance and risk management scores are calculated per driver based on vehicle and driver behavior data collected during driving sessions. Often one vehicle is shared by multiple drivers and one driver can drive multiple vehicles. The present disclosure securely tracks the individual drivers, stores, and retrieves associated driver data for analysis on the edge (vehicle) in near real time. Data collected is analyzed at various time intervals (each trip, daily, monthly) to produce the scores. The goal of the proposed solution minimizes cost associated with data transmission and cloud storage, tracks long term driver driving history on the edge for near real time analysis of driver behavior, minimizes driver distraction due to user device while driving, securely stores and retrieves driver driving data on the edge device associated with the driver, restricts access to the driver driving data, and restricts user device access to servers and telematic units.

The present application relates to a technology for monitoring driver attention in a vehicle. A driver distraction system collects vehicle data and scene information from the vehicle traveling on a route. The vehicle data and scene information are then processed to generate a reference heat map. Simultaneously, the driver distraction system can capture the driver's gaze to track the driver's gaze direction and duration while driving the vehicle on the route. The gaze direction and duration are processed to generate a driver gaze heat map. By analyzing the driver gaze heat map and the reference heat map, the driver distraction level of the driver in the vehicle is determined, and based on the driver distraction level, a suggestion or reminder warning is output to the driver of the vehicle.

The invention provides a distracted driving detection method based on depth separable convolution and multi-spectrum attention, and the method comprises the following steps: firstly, carrying out the efficient feature extraction of an input driver image through a feature extraction module based on depth separable convolution, so as to reduce the calculation complexity of a model and the number of parameters; secondly, a multi-spectrum attention mechanism is designed and integrated, and the capturing capability of the model on key features is enhanced through self-adaptive attention on different spectrum information, so that the accuracy of distraction driving detection is improved; secondly, carrying out diversified processing on training data by adopting a data enhancement technology so as to improve the generalization ability of the model; and finally, constructing a deep neural network architecture containing a maximum pooling layer and a classifier, and realizing real-time detection and classification of distraction driving behaviors. Compared with the prior art, the method has the following advantages: 1) by introducing the depth separable convolution, the calculation amount and the parameter scale of the model are significantly reduced, and the training and reasoning efficiency is improved; 2) a multi-spectrum attention mechanism enhances the attention capability of the model on key features, and improves the accuracy of distraction driving detection; 3) an optimized data enhancement strategy improves the generalization performance of the model and reduces the risk of overfitting; and 4) the whole model is simple in architecture and convenient to deploy and expand in practical application.