Pedestrian and Animal Recognition Using Doppler Radar Signature and Deep Learning
Pedestrian occurrences in images and videos must be accurately recognized in a number of applications that may improve the quality of human life. Radar can be used to identify pedestrians. When distinct portions of an object move in front of a radar, micro-Doppler signals are produced that may be ut...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/9/3456 |
| _version_ | 1797502791978057728 |
|---|---|
| author | Danny Buchman Michail Drozdov Tomas Krilavičius Rytis Maskeliūnas Robertas Damaševičius |
| author_facet | Danny Buchman Michail Drozdov Tomas Krilavičius Rytis Maskeliūnas Robertas Damaševičius |
| author_sort | Danny Buchman |
| collection | DOAJ |
| description | Pedestrian occurrences in images and videos must be accurately recognized in a number of applications that may improve the quality of human life. Radar can be used to identify pedestrians. When distinct portions of an object move in front of a radar, micro-Doppler signals are produced that may be utilized to identify the object. Using a deep-learning network and time–frequency analysis, we offer a method for classifying pedestrians and animals based on their micro-Doppler radar signature features. Based on these signatures, we employed a convolutional neural network (CNN) to recognize pedestrians and animals. The proposed approach was evaluated on the MAFAT Radar Challenge dataset. Encouraging results were obtained, with an AUC (Area Under Curve) value of 0.95 on the public test set and over 0.85 on the final (private) test set. The proposed DNN architecture, in contrast to more common shallow CNN architectures, is one of the first attempts to use such an approach in the domain of radar data. The use of the synthetic radar data, which greatly improved the final result, is the other novel aspect of our work. |
| first_indexed | 2024-03-10T03:41:10Z |
| format | Article |
| id | doaj.art-8b6f31d0c1d34782866b0b8b139145fc |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T03:41:10Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-8b6f31d0c1d34782866b0b8b139145fc2023-11-23T09:18:45ZengMDPI AGSensors1424-82202022-05-01229345610.3390/s22093456Pedestrian and Animal Recognition Using Doppler Radar Signature and Deep LearningDanny Buchman0Michail Drozdov1Tomas Krilavičius2Rytis Maskeliūnas3Robertas Damaševičius4Department of Applied Informatics, Vytautas Magnus University, 44404 Kaunas, LithuaniaJVC Sonderus, 05200 Vilnius, LithuaniaDepartment of Applied Informatics, Vytautas Magnus University, 44404 Kaunas, LithuaniaDepartment of Applied Informatics, Vytautas Magnus University, 44404 Kaunas, LithuaniaDepartment of Applied Informatics, Vytautas Magnus University, 44404 Kaunas, LithuaniaPedestrian occurrences in images and videos must be accurately recognized in a number of applications that may improve the quality of human life. Radar can be used to identify pedestrians. When distinct portions of an object move in front of a radar, micro-Doppler signals are produced that may be utilized to identify the object. Using a deep-learning network and time–frequency analysis, we offer a method for classifying pedestrians and animals based on their micro-Doppler radar signature features. Based on these signatures, we employed a convolutional neural network (CNN) to recognize pedestrians and animals. The proposed approach was evaluated on the MAFAT Radar Challenge dataset. Encouraging results were obtained, with an AUC (Area Under Curve) value of 0.95 on the public test set and over 0.85 on the final (private) test set. The proposed DNN architecture, in contrast to more common shallow CNN architectures, is one of the first attempts to use such an approach in the domain of radar data. The use of the synthetic radar data, which greatly improved the final result, is the other novel aspect of our work.https://www.mdpi.com/1424-8220/22/9/3456doppler radarmicro-Doppler signaturepedestrian recognitionanimal recognitiondeep learning |
| spellingShingle | Danny Buchman Michail Drozdov Tomas Krilavičius Rytis Maskeliūnas Robertas Damaševičius Pedestrian and Animal Recognition Using Doppler Radar Signature and Deep Learning Sensors doppler radar micro-Doppler signature pedestrian recognition animal recognition deep learning |
| title | Pedestrian and Animal Recognition Using Doppler Radar Signature and Deep Learning |
| title_full | Pedestrian and Animal Recognition Using Doppler Radar Signature and Deep Learning |
| title_fullStr | Pedestrian and Animal Recognition Using Doppler Radar Signature and Deep Learning |
| title_full_unstemmed | Pedestrian and Animal Recognition Using Doppler Radar Signature and Deep Learning |
| title_short | Pedestrian and Animal Recognition Using Doppler Radar Signature and Deep Learning |
| title_sort | pedestrian and animal recognition using doppler radar signature and deep learning |
| topic | doppler radar micro-Doppler signature pedestrian recognition animal recognition deep learning |
| url | https://www.mdpi.com/1424-8220/22/9/3456 |
| work_keys_str_mv | AT dannybuchman pedestrianandanimalrecognitionusingdopplerradarsignatureanddeeplearning AT michaildrozdov pedestrianandanimalrecognitionusingdopplerradarsignatureanddeeplearning AT tomaskrilavicius pedestrianandanimalrecognitionusingdopplerradarsignatureanddeeplearning AT rytismaskeliunas pedestrianandanimalrecognitionusingdopplerradarsignatureanddeeplearning AT robertasdamasevicius pedestrianandanimalrecognitionusingdopplerradarsignatureanddeeplearning |