X-LINUX-AI - object detection using Coral Edge TPU TensorFlow Lite Python runtime

Applicable for STM32MP13x lines, STM32MP15x lines

This article explains how to experiment with Coral Edge TPU[1] applications for object detection based on the COCO SSD MobileNet v1 model using TensorFlow Lite Python runtime.

1 Description[edit]

The object detection[2] neural network model allows identification and localization of a known object within an image.

Python Coral Edge TPU object detection application

The application enables three main features :

  • A camera streaming preview implemented using Gstreamer
  • A NN inference based on the camera (or test data pictures) inputs is being ran by the Coral Edge TPU[1] TensorFlow Lite[3] interpreter
  • A user interface implemented using Python GTK.

With this application the inference of the NN is mainly handled by the Coral Edge TPU[1], while the CPU deals mostly with the streaming camera and GUI.

The model used with this application is the COCO SSD MobileNet v1 downloaded from the object detection overview[2] and converted for the Coral Edge TPU.

2 Installation[edit]

2.1 Install from the OpenSTLinux AI package repository[edit]

Warning white.png Warning
The software package is provided AS IS, and by downloading it, you agree to be bound to the terms of the software license agreement (SLA). The detailed content licenses can be found here.

After having configured the AI OpenSTLinux package you can install X-LINUX-AI components for this application:

 apt-get install tflite-cv-apps-edgetpu-object-detection-python

Then restart the demo launcher:

- For OpenSTLinux distribution with a version lower than 4.0 use

 systemctl restart weston@root

- For other OpenSTLinux distribution use :

 systemctl restart weston-launch

2.2 Source code location[edit]

The objdetect_tfl.py Python script is available:

  • in the Openembedded OpenSTLinux Distribution with X-LINUX-AI Expansion Package:
<Distribution Package installation directory>/layers/meta-st/meta-st-stm32mpu-ai/recipes-samples/tflite-cv-apps-edgetpu/files/object-detection/python/objdetect_tfl.py
  • on the target:
/usr/local/demo-ai/computer-vision/tflite-object-detection-edgetpu/python/objdetect_tfl.py
  • on GitHub:
https://github.com/STMicroelectronics/meta-st-stm32mpu-ai/tree/v2.2.0/recipes-samples/tflite-cv-apps-edgetpu/files/object-detection/python/objdetect_tfl.py

3 How to use the application[edit]

3.1 Launching via the demo launcher[edit]

Demo launcher

3.2 Executing with the command line[edit]

The Python script objdetect_tfl.py application is located in the userfs partition:

/usr/local/demo-ai/computer-vision/tflite-object-detection-edgetpu/python/objdetect_tfl.py

It accepts the following input parameters:

usage: objdetect_tfl.py [-h] [-i IMAGE] [-v VIDEO_DEVICE] [--frame_width FRAME_WIDTH] [--frame_height FRAME_HEIGHT] [--framerate FRAMERATE] [-m MODEL_FILE] [-l LABEL_FILE] [-e EXT_DELEGATE]
                        [-p {std,max}] [--edgetpu] [--input_mean INPUT_MEAN] [--input_std INPUT_STD] [--validation] [--num_threads NUM_THREADS] [--maximum_detection MAXIMUM_DETECTION]
                        [--threshold THRESHOLD]

options:
  -h, --help            show this help message and exit
  -i IMAGE, --image IMAGE
                        image directory with image to be classified
  -v VIDEO_DEVICE, --video_device VIDEO_DEVICE
                        video device (default /dev/video0)
  --frame_width FRAME_WIDTH
                        width of the camera frame (default is 320)
  --frame_height FRAME_HEIGHT
                        height of the camera frame (default is 240)
  --framerate FRAMERATE
                        framerate of the camera (default is 15fps)
  -m MODEL_FILE, --model_file MODEL_FILE
                        .tflite model to be executed
  -l LABEL_FILE, --label_file LABEL_FILE
                        name of file containing labels
  -e EXT_DELEGATE, --ext_delegate EXT_DELEGATE
                        external_delegate_library path
  -p {std,max}, --perf {std,max}
                        [EdgeTPU ONLY] Select the performance of the Coral EdgeTPU
  --edgetpu             enable Coral EdgeTPU acceleration
  --input_mean INPUT_MEAN
                        input mean
  --input_std INPUT_STD
                        input standard deviation
  --validation          enable the validation mode
  --num_threads NUM_THREADS
                        Select the number of threads used by tflite interpreter to run inference
  --maximum_detection MAXIMUM_DETECTION
                        Adjust the maximum number of object detected in a frame accordingly to your NN model (default is 10)
  --threshold THRESHOLD
                        threshold of accuracy above which the boxes are displayed (default 0.60)

3.3 Testing with COCO SSD MobileNet V1[edit]

The model used for test is the detect_edgetpu.tflite downloaded from the object detection overview[2] and converted for the Coral Edge TPU. If you are interested, please take a look at how this model has been converted.

Info white.png Information
The different objects the neural network is able to detect are listed in the labels.txt file located in the target:

/usr/local/demo-ai/computer-vision/models/coco_ssd_mobilenet/labels.txt


To ease launching of the application, two shell scripts are available:

  • launch object detection based on camera frame inputs
/usr/local/demo-ai/computer-vision/tflite-object-detection-edgetpu/python/launch_python_objdetect_tfl_edgetpu_coco_ssd_mobilenet.sh
  • launch object detection based on the pictures located in /usr/local/demo-ai/computer-vision/models/mobilenet/testdata directory
 /usr/local/demo-ai/computer-vision/tflite-object-detection-edgetpu/python/launch_python_objdetect_tfl_edgetpu_coco_ssd_mobilenet_testdata.sh
Info white.png Information
Note that you need to populate the testdata directory with your own data sets.

The pictures are then randomly read from the testdata directory

4 References[edit]