Demo Team / radar_outdoor_moving_object_test
This is your Edge Impulse project. From here you acquire new training data, design impulses and train models.
About this project
This project uses the Open Radar Initiative Outdoor Moving Object Dataset to classify object types based on their radar signature.
The dataset has 4 labelled classes for person, uav, bicycle, and vehicle signatures. The data is provided in the form of a 2d spectrogram reading. For example here is the radar signature of a person.
In this project, the images are scaled to a like-sized 2d input image. This allows for processing spectra of both short (high speed objects) and long (low speed objects) spectra equally, but will introduce model artifacts when deployed. It is recommended to generate your own spectra from raw time series sensor data using edge impulse tools if cloning this project.
Download block output
| Title | Type | Size | |
|---|---|---|---|
| Image training data | NPY file | 146 windows | |
| Image training labels | NPY file | 146 windows | |
| Image testing data | NPY file | 80 windows | |
| Image testing labels | NPY file | 80 windows | |
| NN Classifier model | TensorFlow Lite (float32) | 412 KB | |
| NN Classifier model | TensorFlow Lite (int8 quantized) | 106 KB | |
| NN Classifier model | TensorFlow SavedModel | 395 KB | |
| NN Classifier model | Keras h5 model | 381 KB |
Clone project
Summary
Data collected
349 itemsProject info
| Project ID | 45122 |
| Project version | 1 |
| License | No license attached |
