GstInference Detection application

GstInference
Introduction
Getting started
Getting the code Building the plugin Quick Starting Guide
Supported architectures
InceptionV1 InceptionV2 InceptionV3 InceptionV4 TinyYoloV2 TinyYoloV3 YoloV2 ResNetV1 MobileNetV2 MobileNetV2 + SSD AlexNet
Supported backends
TensorFlow Tensorflow-Lite Coral from Google Caffe TensorRT ONNXRT ONNXRT ACL ONNXRT OpenVINO
Metadata and Signals
GstClassificationMeta GstInferenceMeta Signals
Overlay Elements
Inference Overlay
Utils Elements
InferenceFilter InferenceCrop InferenceDebug InferenceBin
Legacy pipelines
PC NANO TX2 Xavier IMX8
Example pipelines
Example applications
Classification Detection Hand Pose Recognition
Benchmarks
Model Zoo
Project Status
Releases Roadmap
Contact Us

This example receives an input video file and detects objects in each buffer, the possible objects to detect are available in the classes section. For each frame the application captures the signal emitted by GstInference, forwarding the prediction to a placeholder for external logic. Simultaneously, the pipeline displays the captured frames with every detected object marked with a label and a square. Note that the image currently being displayed not necessarily matches the one being handled by the signal. The display is meant for visualization and debugging purposes.

The detection example is based on TinyYoloV2, trained using the Pascal VOC dataset, more information can be found in YOLO: Real-Time Object Detection. A pre-trained model can be downloaded from the GstInference Model Zoo

This examples serves both as an example and as a starting point for detection application.

Pascal VOC Classes

The VOC dataset used for training TinyYoloV2 supports 20 classes for inference. Classes according to label ID:

1. aeroplane
2. bicycle
3. bird
4. boat
5. bottle
6. bus
7. car
8. cat
9. chair
10. cow
11. diningtable
12. dog
13. horse
14. motorbike
15. person
16. pottedplant
17. sheep
18. sofa
19. train
20. tvmonitor

Building the Example

The example builds along with the GstInference project. Make sure you follow the instructions in Building the Plug-In to make sure all the dependencies are correctly fulfilled.

Once the project is built the example may be built independently by running make within the example directory.

1 cd tests/examples/detection
2 make

The example is not meant to be installed.

Running the Example

The detection application provides a series of cmdline options to control the behavior of the example. The basic usage is:

./detection -m MODEL -f FILE -b BACKEND [-v]

-m|--model

Mandatory. Path to the TinyYoloV2 trained model

-f|--file

Mandatory. Path to the video file to be used.

If it is not set, a camera stream will be used.

-b|--backend

Mandatory. Name of the backed to be used. See Supported Backends for a list of possible options.

-v

Optional. Run verbosely.

You may always run --help for further details.

./detection --help
Usage:
  detection [OPTIONS] - GstInference Detection Example

Help Options:
  -h, --help                        Show help options
  --help-all                        Show all help options
  --help-gst                        Show GStreamer Options

Application Options:
  -v, --verbose                     Be verbose
  -m, --model                       Model path
  -f, --file                        File path
  -b, --backend                     Backend used for inference, example: tensorflow

Extending the Application

The example is composed of the following main files:

gstdetection.c

Source file with GStreamer logic

customlogic.c

Placeholder for custom logic

customlogic.h

Header file for custom logic source

Makefile

Build script

detection

Executable generated on build

The application can be extended by filling in the placeholders in customlogic.c. In the most simple cases, the information provided in handle_predictionshould suffice to react to the prediction.

 1 void
 2 handle_prediction (unsigned char *image, 
 3                    int width, 
 4                    int height,
 5                    unsigned int size,
 6                    BoundingBox * boxes,
 7                    int num_boxes)
 8 {
 9     /* FILLME: Handle image and prediction here */
10 }

image

Image data in RGB raster format.

width

The width of the image, in pixels

height

The height of the image, in pixels

size

The size of the total image, in bytes

boxes

An array of boxes with all detected objects in the frame

num_boxes

The length of the boxes array

Troubleshooting

The first debug level is GStreamer debug. You may execute the application with debug enabled by running:

1 ./detection --gst-debug=2

For advanced support, please Contact RidgeRun OR email to support@ridgerun.com with the output of the following command:

1 ./detection --gst-debug=2,videoinference:6,tinyyolo:6

Reporting a Bug

Please feel free to report bugs using GitHub's issue tracker.