| Details | |
|---|---|
| Programming Language: | Python 3.5 or 3.6 |
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.
Utilize the classroom workspace, or refer to the relevant instructions for your operating system for this step.
Object Detection Model Zoo https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md contains many pre-trained models on the coco dataset. Intel openVINO already contains extensions for custom layers used in TensorFlow Object Detection Model Zoo.
Else for Downloading the model from the GitHub repository of Tensorflow Object Detection Model Zoo by the following command:
wget http://download.tensorflow.org/models/object_detection/faster_rcnn_inception_v2_coco_2018_01_28.tar.gz
Extracting the tar.gz file using the following commands:
```
tar -xvf faster_rcnn_inception_v2_coco_2018_01_28.tar.gz
```
Make separate directory by following commands:
```
mkdir ssd_mo_model
mkdir faster_rcnn_inception_v2_coco_2018_01_28
```
For Changing the directory to the extracted folder of the downloaded models we can use these commands:
```
cd faster_rcnn_inception_v2_coco_2018_01_28
```
The model can't be the existing models provided by Intel. So, converting the TensorFlow model to Intermediate Representation (IR) or OpenVINO IR format. The command used is given below:
```
python /opt/intel/openvino/deployment_tools/model_optimizer/mo.py --input_model faster_rcnn_inception_v2_coco_2018_01_28/frozen_inference_graph.pb --tensorflow_use_custom_operations_config /opt/intel/openvino/deployment_tools/model_optimizer/extensions/front/tf/faster_rcnn_support.json --tensorflow_object_detection_api_pipeline_config faster_rcnn_inception_v2_coco_2018_01_28/pipeline.config --reverse_input_channels -o folder_name
```
Model-1: Ssd_inception_v2_coco_2018_01_28
Converted the model into intermediate representation by using the following command. Further, this model lacked accuracy as it didn't detect people correctly in the video.
```
python /opt/intel/openvino/deployment_tools/model_optimizer/mo.py --input_model ssd_inception_v2_coco_2018_01_28/frozen_inference_graph.pb --tensorflow_use_custom_operations_config /opt/intel/openvino/deployment_tools/model_optimizer/extensions/front/tf/ssd_v2_support.json --tensorflow_object_detection_api_pipeline_config ssd_inception_v2_coco_2018_01_28/pipeline.config --reverse_input_channels -o ssd_inception
```
Model-2: Faster_rcnn_inception_v2_coco_2018_01_28
Converted the model to intermediate representation using the following command. Model -2 i.e. Faster_rcnn_inception_v2_coco, performed really well in the output video. After using a threshold of 0.4, the model works better than all the previous approaches.
```
python /opt/intel/openvino/deployment_tools/model_optimizer/mo.py --input_model faster_rcnn_inception_v2_coco_2018_01_28/frozen_inference_graph.pb --tensorflow_use_custom_operations_config /opt/intel/openvino/deployment_tools/model_optimizer/extensions/front/tf/faster_rcnn_support.json --tensorflow_object_detection_api_pipeline_config faster_rcnn_inception_v2_coco_2018_01_28/pipeline.config --reverse_input_channels -o faster_rcnn_inception_v2_coco_2018_01_28
```
1.ssd_inception_v2_coco and faster_rcnn_inception_v2_coco
In terms of latency, several insights were drawn. It could be clearly seen that the Latency (microseconds) is very low in case of OpenVINO.
| Models | Latency (ms) |
|---|---|
| ssd_inception_v2_coco (OpenVINO) | 166 |
| faster_rcnn_inception_v2_coco (OpenVINO) | 898 |
Edge Computing is regarded as ideal for operations with extreme latency concerns. On the other hand Cloud Computing is more suitable for projects and organizations which deal with massive data storage.So,for medium scale companies that have budget limitations can use edge computing to save financial cost.
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 installNote: 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.
From the main directory:
cd webservice/server/node-server
node ./server.js
You should see the following message, if successful:
Mosca server started.
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
Open new terminal and run the below commands.
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.
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:
CAMERA_FEED_SERVER: "http://localhost:3004"
...
MQTT_SERVER: "ws://localhost:3002"