Details
Programming Language:
Intel OpenVINO ToolKit:
Docker (Ubuntu OpenVINO pre-installed):	mmphego/intel-openvino
Hardware Used:	Intel(R) Core(TM) i7-8750H CPU @ 2.20GHz
Device:	CPU
Blog Post
Visitors

The people counter application will demonstrate how to create a smart video IoT solution using Intel® hardware and software tools. The app will detect people in a designated area, providing the number of people in the frame, average duration of people in frame, and total count.

The counter will use the Inference Engine included in the Intel® Distribution of OpenVINO™ Toolkit. The model used should be able to identify people in a video frame. The app should count the number of people in the current frame, the duration that a person is in the frame (time elapsed between entering and exiting a frame) and the total count of people. It then sends the data to a local web server using the Paho MQTT Python package.

You will choose a model to use and convert it with the Model Optimizer.

• 6th to 10th generation Intel® Core™ processor with Iris® Pro graphics or Intel® HD Graphics.
• OR use of Intel® Neural Compute Stick 2 (NCS2)
• OR Udacity classroom workspace for the related course

• Intel® Distribution of OpenVINO™ toolkit 2019 R3 release
• Node v6.17.1
• Npm v3.10.10
• CMake
• MQTT Mosca server

Utilize the classroom workspace, or refer to the relevant instructions for your operating system for this step.

• Linux/Ubuntu
• Mac
• Windows

Utilize the classroom workspace, or refer to the relevant instructions for your operating system for this step.

• Linux/Ubuntu
• Mac
• Windows

There are three components that need to be running in separate terminals for this application to work:

• MQTT Mosca server
• Node.js* Web server
• FFmpeg server

From the main directory:

• For MQTT/Mosca server:

  cd webservice/server
  npm install
  

• For Web server:

  cd ../ui
  npm install
  

  Note: If any configuration errors occur in mosca server or Web server while using npm install, use the below commands:

  sudo npm install npm -g
  rm -rf node_modules
  npm cache clean
  npm config set registry "http://registry.npmjs.org"
  npm install
  

It is up to you to decide on what model to use for the application. You need to find a model not already converted to Intermediate Representation format (i.e. not one of the Intel® Pre-Trained Models), convert it, and utilize the converted model in your application.

Note that you may need to do additional processing of the output to handle incorrect detections, such as adjusting confidence threshold or accounting for 1-2 frames where the model fails to see a person already counted and would otherwise double count.

If you are otherwise unable to find a suitable model after attempting and successfully converting at least three other models, you can document in your write-up what the models were, how you converted them, and why they failed, and then utilize any of the Intel® Pre-Trained Models that may perform better.

Note: In order to run the app locally export the 2 envvars (See: #a-note-on-running-locally)

export CAMERA_FEED_SERVER="http://localhost:3004"
export MQTT_SERVER="ws://localhost:3002"

In order to run the application execute the following script:

bash runme.sh

This script with start the mosca server, ffserver, webui and app in the background - assuming that the install NPM step was followed.

From the main directory:

• Create a network bridge to communicate between the containers.

docker network create -d bridge openvino

• Build the docker container for the mosca-server.

docker build -t mmphego/mosca-server -f Dockerfile-mosca-server .

• Run the container while exposing port 3001 and 3002.

docker run \
-p 3002:3002 \
-p 3001:3001 \
--network="openvino" \
--name "mosca-server" \
-ti mmphego/mosca-server

You should see the following message, if successful:

Mosca server started.

cd webservice/server/node-server
node ./server.js

You should see the following message, if successful:

Mosca server started.

• Build the docker container for the Web UI

docker build -t mmphego/webui -f Dockerfile-ui .

• Run the container while exposing port 3000.

docker run \
-p 3000:3000 \
--network="openvino" \
--name "webui" \
-ti mmphego/webui

You should see the following log output:

> intel-people-counter-app@0.1.0 dev /app/webservice/ui
> cross-env NODE_ENV=development webpack-dev-server --history-api-fallback --watch --hot --inline

Project is running at http://0.0.0.0:3000/

webpack: Compiled successfully.

Open new terminal and run below commands.

cd webservice/ui
npm run dev

You should see the following message in the terminal.

webpack: Compiled successfully

docker run \
-p 3004:3004 \
--network="openvino" \
--name "ffmpeg-server" \
-ti mmphego/ffmpeg-server

You should see the following output:

Sat May 23 05:51:10 2020 FFserver started.

Open new terminal and run the below commands.

wget https://github.com/vot/ffbinaries-prebuilt/releases/download/v3.4/ffserver-3.4-linux-64.zip
sudo unzip ffserver-3.4-linux-64.zip /usr/local/bin
sudo ffserver -f ./ffmpeg/server.conf

Open a new terminal to run the code.

You must configure the environment to use the Intel® Distribution of OpenVINO™ toolkit one time per session by running the following command:

source /opt/intel/openvino/bin/setupvars.sh -pyver 3.5

You should also be able to run the application with Python 3.6, although newer versions of Python will not work with the app.

When running Intel® Distribution of OpenVINO™ toolkit Python applications on the CPU, the CPU extension library is required. This can be found at:

/opt/intel/openvino/deployment_tools/inference_engine/lib/intel64/

Depending on whether you are using Linux or Mac, the filename will be either libcpu_extension_sse4.so or libcpu_extension.dylib, respectively. (The Linux filename may be different if you are using a AVX architecture)

Though by default application runs on CPU, this can also be explicitly specified by -d CPU command-line argument:

python main.py -i resources/Pedestrian_Detect_2_1_1.mp4 -m your-model.xml -l /opt/intel/openvino/deployment_tools/inference_engine/lib/intel64/libcpu_extension_sse4.so -d CPU -pt 0.6 | ffmpeg -v warning -f rawvideo -pixel_format bgr24 -video_size 768x432 -framerate 24 -i - http://0.0.0.0:3004/fac.ffm

If you are in the classroom workspace, use the “Open App” button to view the output. If working locally, to see the output on a web based interface, open the link http://0.0.0.0:3004 in a browser.

In order to see what is going inside the docker we need to sync the displays with --env DISPLAY=$DISPLAY --volume="/tmp/.X11-unix:/tmp/.X11-unix:rw".

docker build -t "$USER/$(basename $PWD)" .
xhost +
docker run --rm -ti \
--volume "$PWD":/app \
--env DISPLAY=$DISPLAY \
--volume="/tmp/.X11-unix:/tmp/.X11-unix:rw" \
 "$USER/$(basename $PWD)" \
 bash -c "source /opt/intel/openvino/bin/setupvars.sh &&python main.py -i resources/Pedestrian_Detect_2_1_1.mp4 -m models/ssd_mobilenet_v2_coco.xml"
xhost -

To run on the Intel® Neural Compute Stick, use the -d MYRIAD command-line argument:

python3.5 main.py -d MYRIAD -i resources/Pedestrian_Detect_2_1_1.mp4 -m your-model.xml -pt 0.6 | ffmpeg -v warning -f rawvideo -pixel_format bgr24 -video_size 768x432 -framerate 24 -i - http://0.0.0.0:3004/fac.ffm

To see the output on a web based interface, open the link http://0.0.0.0:3004 in a browser.

Note: The Intel® Neural Compute Stick can only run FP16 models at this time. The model that is passed to the application, through the -m <path_to_model> command-line argument, must be of data type FP16.

To get the input video from the camera, use the -i CAM command-line argument. Specify the resolution of the camera using the -video_size command line argument.

For example:

python main.py -i CAM -m your-model.xml -l /opt/intel/openvino/deployment_tools/inference_engine/lib/intel64/libcpu_extension_sse4.so -d CPU -pt 0.6 | ffmpeg -v warning -f rawvideo -pixel_format bgr24 -video_size 768x432 -framerate 24 -i - http://0.0.0.0:3004/fac.ffm

To see the output on a web based interface, open the link http://0.0.0.0:3004 in a browser.

Note: User has to give -video_size command line argument according to the input as it is used to specify the resolution of the video or image file.

The servers herein are configured to utilize the Udacity classroom workspace. As such, to run on your local machine, you will need to change the below file:

webservice/ui/src/constants/constants.js

The CAMERA_FEED_SERVER and MQTT_SERVER both use the workspace configuration. You can change each of these as follows:

export CAMERA_FEED_SERVER="http://localhost:3004"
export MQTT_SERVER="ws://localhost:3002"

• Dockerize the application (hint: docker-compose)
• Benchmark application on various devices.
• Run VTune profiling software to find any bottlenecks.