Driver Behavior Analytics Reference Implementation

Version: 2022.1   Published: 05/05/2021  

Last Updated: 06/28/2022


The Driver Behavior Analytics Reference Implementation uses video injection and analytics, rule engine, and event recording services to monitor driver behavior. Develop the solution that provides alerts and stored video clips to drivers and fleet managers with this reference implementation.

Select Configure & Download to download the reference implementation and the software listed below. 

Configure & Download

Screenshot of running Driver Behavior Analytics


  • Time to Complete: Approximately 60 minutes
  • Programming Language: C++, Python*
  • Available Software: Intel® Distribution of OpenVINO™ toolkit 2021 Release

Recommended Hardware

The hardware below is recommended for use with this reference implementation. See the Recommended Hardware page for other suggestions. 

Target System Requirements

  • Ubuntu* 20.04 LTS
  • 6th to 10th Generation Intel® Core™ processors with Intel® Iris® Plus graphics or Intel® HD Graphics

How It Works

The application uses the inference engine included in the Intel® Distribution of OpenVINO™ toolkit and is designed to detect and track driver behavior and driver actions to ensure safe driving.  

Using deep learning models, video streams, and analytics running on in-vehicle computers, it detects driver’s drowsiness states and distraction behaviors, and provides real time alerts to driver, and analytics per driver, truck and route over time.

Architecture Diagram

Get Started

Step 1: Install the Reference Implementation 

Select Configure & Download to download the reference implementation and then follow the steps below to install it. 

Configure & Download

NOTE: If the host system already has Docker* images and containers, you might encounter errors while building the reference implementation packages. If you do encounter errors, refer to the Troubleshooting section at the end of this document before starting the reference implementation installation.

1. Open a new terminal, go to the downloaded folder and unzip the downloaded RI package.


​2. Go to the driver_behavior_analytics/ directory.

cd driver_behavior_analytics /


​3. Change permission of the executable edgesoftware file.

chmod 755 edgesoftware


4. Run the command below to install the Reference Implementation.

./edgesoftware install


5. During the installation, you will be prompted for the Product Key. The Product Key is contained in the email you received from Intel confirming your download.

Screenshot of Product Key

6. When the installation is complete, you see the message “Installation of package complete” and the installation status for each module.

Screenshot of Install Success


NOTE: If you encounter any issues, please refer to the Troubleshooting section at the end of this document. Installation failure logs will be available at the path:  /var/log/esb-cli/Driver_Behavior_Analytics_2022.1/output.log

7.   In order to start the application, change the directory using the cd command printed at the end of the installation process: 



Step 2: Run the Application



1. Run the application. 

   Copy and run the make webui command from the end of the installation log:

make webui EII_BASE=<INSTALL_PATH>/driver_behavior_analytics/Driver_Behavior_Analytics_<version>/IEdgeInsights REPO_FOLDER=<INSTALL_PATH>/driver_behavior_analytics/Driver_Behavior_Analytics_<version>/Driver_Behavior_Analytics/EII-DriverBehavior-UseCase

For example: 

make webui EII_BASE=/home/intel/driver_behavior_analytics/Driver_Behavior_Analytics_2022.1/IEdgeInsights REPO_FOLDER=/home/intel/driver_behavior_analytics/Driver_Behavior_Analytics_2022.1/Driver_Behavior_Analytics/EII-DriverBehavior-UseCase


2. Open the Web UI: Go to on your web browser.

Screenshot of Web UI


3. If you installed your ThingsBoard Cloud Server and you have enabled S3 Bucket Server on your AWS account, you can provide your configured AWS Access Key ID, AWS Secret Access Key, Thingsboard IP, Thingsboard Port and Thingsboard Device token on Cloud Data Configuration tab. After you complete the Cloud configuration, make sure you click on the Save Credentials and Save Token buttons. Now you can import the ThingsBoard dashboard as described at the end of Set Up ThingsBoard* Cloud Data to enable all dashboard features, including the cloud storage.


Screenshot of Thingsboard Access Token


NOTE: If you don't have an AWS account, you will not be able to access Storage Cloud. You can still enable the ThingsBoard Cloud Data if you configured it locally or on another machine.


4. Access the Driver Behavior Analytics Dashboard with the following steps. 

  • Go to sidebar and select Run Use Case.
    Screenshot of selecting run use case
  • Configure the use case by selecting the video sample and the device for all UDF models.

    Model Descriptions
    Head Pose: Estimates the head(s) position in the video frame.
    Facial Landmarks: Determines the facial landmarks of the identified people.
    Face Detection: Detects the face(s) in the video frame.

    Screenshot of configuring the use case
  • Click on the Browse button and search for one of the sample videos delivered with the application at the following path:
    <INSTALL_PATH>/driver_behavior_analytics/Driver_Behavior_Analytics_2022.1/Driver_Behavior_Analytics/EII-DriverBehavior-UseCase/config/VideoIngestion/test_videos/  and select one of the two available. 

    Screenshot of selecting a video
  • After selecting the video sample, select the device for all UDF models. Options include CPU, GPU, or HETERO:CPU,GPU. Click on Run Use Case. 

    NOTE: To use a GPU or a HETERO:CPU,GPU combination device, you must set the proper group for the GPU device with the command:

    sudo chown root:video /dev/dri/renderD128


  • The application will start the Visualizer App that will detect yawns, blinks, drowsiness and distraction status as in the following image:
    Screenshot of Visualizer App

5. After the visualiser starts, you can go to the ThingsBoard link and check the alerts sent by the reference implementation. If you configured the AWS credentials, you will also have access to video snapshots taken by the application on the video stream. 

Screenshot of ThingsBoard Dashboard




6. You can also check the cloud storage from the Reference Implementation Storage tab.

Screenshot of cloud video clips



Run in Parallel with Vehicle Event Recording Reference Implementation  

To run this task, you will need to download and install the Vehicle Event Recording Reference Implementation. 


Steps to Run the Application 

  1. Change directory to Driver Behavior Analytics Use Case path on terminal 1:
    cd <INSTALL_PATH>/driver_behavior_analytics/Driver_Behavior_Analytics_2022.1/Driver_Behavior_Analytics/EII-DriverBehavior-UseCase

    Screenshot of use case path on terminal 1

  2.  Change directory to Vehicle Event Recording Use Case path on terminal 2: 
    cd <INSTALL_PATH>/vehicle_event_recording/Vehicle_Event_Recording_2022.2/Vehicle_Event_Recording/EII-EVMSC-UseCase

    Screenshot of use case path on terminal 2

  3. Run the following command on terminal 1 to start the webserver application. Copy and run the make webui command from the end of the installation log: 
    make webui EII_BASE=<INSTALL_PATH>/driver_behavior_analytics/Driver_Behavior_Analytics_2022.1/IEdgeInsights REPO_FOLDER=<INSTALL_PATH>/driver_behavior_analytics/Driver_Behavior_Analytics_2022.1/Driver_Behavior_Analytics/EII-DriverBehavior-UseCase
  4. Run the following command on terminal 2 to start the webserver application. Copy and run the make webui command from the end of the installation log: 
    make webui EII_BASE=<INSTALL_PATH>/driver_behavior_analytics/Driver_Behavior_Analytics_2022.1/IEdgeInsights REPO_FOLDER=<INSTALL_PATH>/vehicle_event_recording/Vehicle_Event_Recording_2022.2/Vehicle_Event_Recording/EII-EVMSC-UseCase

    Screenshot of command in terminal 2

  5. Open your browser and go to 
  6. Configure Driver Behavior Analytics by setting the video source, the target and click on Run Use Case. 
  7. Wait for Visualizer to get up and running. 
  8. Open the Vehicle Event Recording page by going to address 
  9. Configure all available cameras with the desired videos and set the target for each one (CPU or GPU) and click Run Use CaseScreenshot of run use case


At this point, Driver Behavior Analytics will close and then both use cases will start. 

Screenshot of both use cases running

NOTE: If you reinstall the first reference implementation, you must also reinstall the second reference implementation. 

Summary and Next Steps

This application successfully implements Intel® Distribution of OpenVINO™ toolkit plugins for detecting and tracking driver behavior. It can be extended further to provide support for feed from network stream (RTSP camera), and the algorithm can be optimized for better performance.

As a next step, try the following: 

Use deep learning models and driver facing camera video streams to detect driver’s drowsiness, distraction state and behaviors to provide real time alerts to driver. This reference implementation uses Intel® Distribution of OpenVINO™ toolkit Open Model Zoo pre-trained models and 3rd party models, but you can extend it to use your own models.

Learn More

To continue your learning, see the following guides and software resources:

Known Issues

Uninstall Reference Implementation

If you uninstall one of the reference implementations, you need to reinstall the other reference implementations because the Docker images will be cleared. 


Installation Failure

If the host system already has Docker images and its containers running, you will have issues during the RI installation. You must stop/force stop existing containers and images.

  • To remove all stopped containers, dangling images, and unused networks: 

    sudo docker system prune --volumes
  • To stop Docker containers: 

    sudo docker stop $(sudo docker ps -aq)
  • To remove Docker containers:

    sudo docker rm $(sudo docker ps -aq)
  • To remove all Docker images:

    sudo docker rmi -f $(sudo docker images -aq)

Docker Image Build Failure

If Docker image build on corporate network fails, follow the steps below.

  1. Get DNS server using the command: 
    nmcli dev show | grep 'IP4.DNS'
  2. Configure Docker to use the server. Paste the line below in the  /etc/docker/daemon.json file:
    { "dns": ["<dns-server-from-above-command>"]} 
  3. Restart Docker: 
    sudo systemctl daemon-reload && sudo systemctl restart docker

Installation Failure Due to Ubuntu Timezone Setting 

While building the reference implementation, if you see  /etc/timezone && apt-get install -y tzdata && ln -sf /usr/share/zoneinfo/${HOST_TIME_ZONE} /etc/localtime && dpkg-reconfigure -f noninteractive tzdata' returned a non-zero code: 1 make: *** [config] Error 1 

Run the following command in your terminal: 

sudo timedatectl set-local-rtc 0

Installation Encoding Issue 

While building the reference implementation, if you see ERROR: 'latin-1' codec can't encode character '\u2615' in position 3: ordinal not in range(256) 

Run the following command in your terminal: 

export LANG=en_US.UTF-8

Can't Connect to Docker Daemon

If you can't connect to Docker Daemon at http+docker://localhost, run the following command in your terminal: 

sudo usermod -aG docker $USER

Log out and log in to Ubuntu.  

Check before retrying to install if group Docker is available for you by running the following command in a terminal: 


The output should contain Docker.

Support Forum 

If you're unable to resolve your issues, contact the Support Forum.  

Product and Performance Information


Performance varies by use, configuration and other factors. Learn more at