X-LINUX-AI - object detection using armNN TensorFlow Lite parser

Revision as of 18:45, 1 July 2020 by Philip Sage (talk | contribs)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

This article explains how to experiment with armNN[1] applications for object detection based on the COCO SSD MobileNet v1 model using the TensorFlow Lite parser.

1 Description[edit]

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

C/C++ armNN Lite object detection application using TensorFlow Lite parser

The application demonstrates a computer vision use case for object detection where frames are grabbed from a camera input (/dev/videox) and analyzed by a neural network model interpreted by the armNN[1] framework.
A Gstreamer pipeline is used to stream camera frames (using v4l2src), to display a preview (using waylandsink) and to execute neural network inference (using appsink).
The result of the inference is displayed on the preview. The overlay is done using GtkWidget with cairo.
This combination is quite simple and efficient in terms of CPU overhead.

The model used with this application is the COCO SSD MobileNet v1 downloaded from the object detection overview[2].

2 Installation[edit]

2.1 Install from the OpenSTLinux AI package repository[edit]

Warning.png 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:

Board $> apt-get install armnn-tfl-cv-apps-object-detection-c++

Then restart the demo launcher:

Board $> systemctl restart weston@root

2.2 Source code location[edit]

  • in the Openembedded OpenSTLinux Distribution:
<Distribution Package installation directory>/layers/meta-st/meta-st-stm32mpu-ai/recipes-samples/armnn-cv-apps/files/tfl-object-detection/src
  • on GitHub:
https://github.com/STMicroelectronics/meta-st-stm32mpu-ai/tree/dunfell/recipes-samples/armnn-cv-apps/files/tfl-object-detection/src

2.3 Re-generate the package from OpenSTLinux Distribution (optional)[edit]

Using the Openembedded OpenSTLinux Distribution, you are able to rebuild the application.

Info.png If not already installed, the X-LINUX-AI OpenSTLinux Distribution need to be installed by following this link


  • Set up the build environment:
PC $> cd <Distribution Package installation directory>
PC $> source layers/meta-st/scripts/envsetup.sh
  • Rebuild the application:
PC $> bitbake armnn-tfl-cv-apps-object-detection-c++ -c compile

The generated binary is available here:

<Distribution Package installation directory>/<build directory>/tmp-glibc/work/cortexa7t2hf-neon-vfpv4-ostl-linux-gnueabi/armnn-tfl-cv-apps-object-detection-c++/1.0-r0/armnn-tfl-cv-apps-object-detection-c++-1.0/tfl-object-detection/src

3 How to use the application[edit]

3.1 Launching via the demo launcher[edit]

Launch cpp armnn tfl object detection.png

3.2 Executing with the command line[edit]

The objdetect_armnn_tfl_gst_gtk C/C++ application is located in the userfs partition:

/usr/local/demo-ai/computer-vision/armnn-tfl-object-detection/bin/objdetect_armnn_tfl_gst_gtk

It accepts the following input parameters:

Usage: ./objdetect_armnn_tfl_gst_gtk -m <model .tflite> -l <label .txt file>                                                          
                                                                                                                                      
-m --model_file <.tflite file path>:  .tflite model to be executed                                                                    
-l --label_file <label file path>:    name of file containing labels                                                                  
-b --backend <device>:                preferred backend device to run layers on by default. Possible choices: CpuAcc, CpuRef          
-i --image <directory path>:          image directory with image to be classified                                                     
-v --video_device <n>:                video device (default /dev/video0)                                                              
--crop:                               if set, the nn input image is cropped (with the expected nn aspect ratio) before being resized, 
                                      else the nn imput image is only resized to the nn input size (could cause picture deformation). 
--frame_width  <val>:                 width of the camera frame (default is 640)                                                      
--frame_height <val>:                 height of the camera frame (default is 480)                                                     
--framerate <val>:                    framerate of the camera (default is 15fps)                                                      
--input_mean <val>:                   model input mean (default is 127.5)                                                             
--input_std  <val>:                   model input standard deviation (default is 127.5)                                               
--help:                               show this help 

3.3 Testing with COCO SSD MobileNet V1[edit]

The model used for test is the detect.tflite downloaded from object detection overview[2]

Info.png 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
Board $> /usr/local/demo-ai/computer-vision/armnn-tfl-object-detection/bin/launch_bin_objdetect_armnn_tfl_coco_ssd_mobilenet.sh
  • launch object detection based on the pictures located in /usr/local/demo-ai/computer-vision/models/mobilenet/testdata directory
Board $> /usr/local/demo-ai/computer-vision/armnn-tfl-object-detection/bin/launch_bin_objdetect_armnn_tfl_coco_ssd_mobilenet_testdata.sh
Info.png 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]