Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
Radar-Based Multi-Target Classification Using Deep Learning
Real-time, radar-based human activity and target recognition has several applications in various fields. Examples include hand gesture recognition, border and home surveillance, pedestrian recognition for automotive safety and fall detection for assisted living. This dissertation sought to improve t...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
Department of Statistical Sciences
2023
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| _version_ | 1867614002831425536 |
|---|---|
| access_status_str | Open Access |
| author | Mashanda, Nyasha Ernest |
| author2 | Watson, Neil |
| author_browse | Mashanda, Nyasha Ernest Watson, Neil |
| author_facet | Watson, Neil Mashanda, Nyasha Ernest |
| author_sort | Mashanda, Nyasha Ernest |
| collection | Thesis |
| description | Real-time, radar-based human activity and target recognition has several applications in various fields. Examples include hand gesture recognition, border and home surveillance, pedestrian recognition for automotive safety and fall detection for assisted living. This dissertation sought to improve the speed and accuracy of a previously developed model classifying human activity and targets using radar data for outdoor surveillance purposes. An improvement in accuracy and speed of classification helps surveillance systems to provide reliable results on time. For example, the results can be used to intercept trespassers, poachers or smugglers. To achieve these objectives, radar data was collected using a C-band pulse-Doppler radar and converted to spectrograms using the Short-time Fourier transform (STFT) algorithm. Spectrograms of the following classes were utilised in classification: one human walking, two humans walking, one human running, moving vehicles, a swinging sphere and clutter/noise. A seven-layer residual network was proposed, which utilised batch normalisation (BN), global average pooling (GAP), and residual connections to achieve a classification accuracy of 92.90% and 87.72% on the validation and test data, respectively. Compared to the previously proposed model, this represented a 10% improvement in accuracy on the validation data and a 3% improvement on the test data. Applying model quantisation provided up to 3.8 times speedup in inference, with a less than 0.4% accuracy drop on both the validation and test data. The quantised model could support a range of up to 89.91 kilometres in real-time, allowing it to be used in radars that operate within this range. |
| format | Thesis |
| id | oai:open.uct.ac.za:11427/37606 |
| institution | University of Cape Town (South Africa) |
| language | eng |
| last_indexed | 2026-06-10T12:45:07.461Z |
| license_str | Not specified — see source repository |
| provenance_str_mv | Harvested via OAI-PMH from UCTD — University of Cape Town Open Access Repository |
| publishDate | 2023 |
| publishDateRange | 2023 |
| publishDateSort | 2023 |
| publisher | Department of Statistical Sciences |
| publisherStr | Department of Statistical Sciences |
| record_format | dspace |
| source_str | UCTD — University of Cape Town Open Access Repository |
| spelling | oai:open.uct.ac.za:11427/37606 Radar-Based Multi-Target Classification Using Deep Learning Mashanda, Nyasha Ernest Watson, Neil Gaffar, Yunus Abdul Berndt, Robert Statistical Sciences Real-time, radar-based human activity and target recognition has several applications in various fields. Examples include hand gesture recognition, border and home surveillance, pedestrian recognition for automotive safety and fall detection for assisted living. This dissertation sought to improve the speed and accuracy of a previously developed model classifying human activity and targets using radar data for outdoor surveillance purposes. An improvement in accuracy and speed of classification helps surveillance systems to provide reliable results on time. For example, the results can be used to intercept trespassers, poachers or smugglers. To achieve these objectives, radar data was collected using a C-band pulse-Doppler radar and converted to spectrograms using the Short-time Fourier transform (STFT) algorithm. Spectrograms of the following classes were utilised in classification: one human walking, two humans walking, one human running, moving vehicles, a swinging sphere and clutter/noise. A seven-layer residual network was proposed, which utilised batch normalisation (BN), global average pooling (GAP), and residual connections to achieve a classification accuracy of 92.90% and 87.72% on the validation and test data, respectively. Compared to the previously proposed model, this represented a 10% improvement in accuracy on the validation data and a 3% improvement on the test data. Applying model quantisation provided up to 3.8 times speedup in inference, with a less than 0.4% accuracy drop on both the validation and test data. The quantised model could support a range of up to 89.91 kilometres in real-time, allowing it to be used in radars that operate within this range. 2023-03-31T07:39:58Z 2023-03-31T07:39:58Z 2022 2023-03-29T09:18:12Z Master Thesis Masters MSc http://hdl.handle.net/11427/37606 eng application/pdf Department of Statistical Sciences Faculty of Science |
| spellingShingle | Statistical Sciences Mashanda, Nyasha Ernest Radar-Based Multi-Target Classification Using Deep Learning |
| thesis_degree_str | Master's |
| title | Radar-Based Multi-Target Classification Using Deep Learning |
| title_full | Radar-Based Multi-Target Classification Using Deep Learning |
| title_fullStr | Radar-Based Multi-Target Classification Using Deep Learning |
| title_full_unstemmed | Radar-Based Multi-Target Classification Using Deep Learning |
| title_short | Radar-Based Multi-Target Classification Using Deep Learning |
| title_sort | radar based multi target classification using deep learning |
| topic | Statistical Sciences |
| url | http://hdl.handle.net/11427/37606 |
| work_keys_str_mv | AT mashandanyashaernest radarbasedmultitargetclassificationusingdeeplearning |