Demo Team / radar_outdoor_moving_object_test Public

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.

Creating your first impulse (100% complete)

Acquire data

Every Machine Learning project starts with data. You can capture data from a development board or your phone, or import data you already collected.

Design an impulse

Teach the model to interpret previously unseen data, based on historical data. Use this to categorize new data, or to find anomalies in sensor readings.


Package the complete impulse up, from signal processing code to trained model, and deploy it on your device. This ensures that the impulse runs with low latency and without requiring a network connection.

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

You are viewing a public Edge Impulse project. Clone this project to add data or make changes.


Data collected
349 items

Project info

Project ID 93362
Project version 1
License No license attached