Hybrid SVM-CNN Classification Technique for Human–Vehicle Targets in an Automotive LFMCW Radar
Human–vehicle classification is an essential component to avoiding accidents in autonomous driving. The classification technique based on the automotive radar sensor has been paid more attention by related researchers, owing to its robustness to low-light conditions and severe weather. In the paper,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/12/3504 |
| _version_ | 1797564541645619200 |
|---|---|
| author | Qisong Wu Teng Gao Zhichao Lai Dianze Li |
| author_facet | Qisong Wu Teng Gao Zhichao Lai Dianze Li |
| author_sort | Qisong Wu |
| collection | DOAJ |
| description | Human–vehicle classification is an essential component to avoiding accidents in autonomous driving. The classification technique based on the automotive radar sensor has been paid more attention by related researchers, owing to its robustness to low-light conditions and severe weather. In the paper, we propose a hybrid support vector machine–convolutional neural network (SVM-CNN) approach to address the class-imbalance classification of vehicles and pedestrians with limited experimental radar data available. A two-stage scheme with the combination of feature-based SVM technique and deep learning-based CNN is employed. In the first stage, the modified SVM technique based on these distinct physical features is firstly used to recognize vehicles to effectively alleviate the imbalance ratio of vehicles to pedestrians in the data level. Then, the residual unclassified images will be used as inputs to the deep network for the subsequent classification, and we introduce a weighted false error function into deep network architectures to enhance the class-imbalance classification performance at the algorithm level. The proposed SVM-CNN approach takes full advantage of both the locations of underlying class in the entire Range-Doppler image and automatical local feature learning in the CNN with sliding filter bank to improve the classification performance. Experimental results demonstrate the superior performances of the proposed method with the <inline-formula> <math display="inline"> <semantics> <msub> <mi>F</mi> <mn>1</mn> </msub> </semantics> </math> </inline-formula> score of <inline-formula> <math display="inline"> <semantics> <mrow> <mn>0.90</mn> </mrow> </semantics> </math> </inline-formula> and area under the curve (AUC) of the receiver operating characteristic (ROC) of <inline-formula> <math display="inline"> <semantics> <mrow> <mn>0.99</mn> </mrow> </semantics> </math> </inline-formula> over several state-of-the-art methods with limited experimental radar data available in a 77 GHz automotive radar. |
| first_indexed | 2024-03-10T18:59:36Z |
| format | Article |
| id | doaj.art-cb3c5a1768cc41cba5b40ae4e8718c65 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T18:59:36Z |
| publishDate | 2020-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-cb3c5a1768cc41cba5b40ae4e8718c652023-11-20T04:30:56ZengMDPI AGSensors1424-82202020-06-012012350410.3390/s20123504Hybrid SVM-CNN Classification Technique for Human–Vehicle Targets in an Automotive LFMCW RadarQisong Wu0Teng Gao1Zhichao Lai2Dianze Li3Key Laboratory of Underwater Acoustic Signal Processing of Ministry of Education Southeast University, Nanjing 210096, ChinaKey Laboratory of Underwater Acoustic Signal Processing of Ministry of Education Southeast University, Nanjing 210096, ChinaKey Laboratory of Underwater Acoustic Signal Processing of Ministry of Education Southeast University, Nanjing 210096, ChinaKey Laboratory of Underwater Acoustic Signal Processing of Ministry of Education Southeast University, Nanjing 210096, ChinaHuman–vehicle classification is an essential component to avoiding accidents in autonomous driving. The classification technique based on the automotive radar sensor has been paid more attention by related researchers, owing to its robustness to low-light conditions and severe weather. In the paper, we propose a hybrid support vector machine–convolutional neural network (SVM-CNN) approach to address the class-imbalance classification of vehicles and pedestrians with limited experimental radar data available. A two-stage scheme with the combination of feature-based SVM technique and deep learning-based CNN is employed. In the first stage, the modified SVM technique based on these distinct physical features is firstly used to recognize vehicles to effectively alleviate the imbalance ratio of vehicles to pedestrians in the data level. Then, the residual unclassified images will be used as inputs to the deep network for the subsequent classification, and we introduce a weighted false error function into deep network architectures to enhance the class-imbalance classification performance at the algorithm level. The proposed SVM-CNN approach takes full advantage of both the locations of underlying class in the entire Range-Doppler image and automatical local feature learning in the CNN with sliding filter bank to improve the classification performance. Experimental results demonstrate the superior performances of the proposed method with the <inline-formula> <math display="inline"> <semantics> <msub> <mi>F</mi> <mn>1</mn> </msub> </semantics> </math> </inline-formula> score of <inline-formula> <math display="inline"> <semantics> <mrow> <mn>0.90</mn> </mrow> </semantics> </math> </inline-formula> and area under the curve (AUC) of the receiver operating characteristic (ROC) of <inline-formula> <math display="inline"> <semantics> <mrow> <mn>0.99</mn> </mrow> </semantics> </math> </inline-formula> over several state-of-the-art methods with limited experimental radar data available in a 77 GHz automotive radar.https://www.mdpi.com/1424-8220/20/12/3504millimeter-wave radarconvolutional neural networkhuman–vehicle classification |
| spellingShingle | Qisong Wu Teng Gao Zhichao Lai Dianze Li Hybrid SVM-CNN Classification Technique for Human–Vehicle Targets in an Automotive LFMCW Radar Sensors millimeter-wave radar convolutional neural network human–vehicle classification |
| title | Hybrid SVM-CNN Classification Technique for Human–Vehicle Targets in an Automotive LFMCW Radar |
| title_full | Hybrid SVM-CNN Classification Technique for Human–Vehicle Targets in an Automotive LFMCW Radar |
| title_fullStr | Hybrid SVM-CNN Classification Technique for Human–Vehicle Targets in an Automotive LFMCW Radar |
| title_full_unstemmed | Hybrid SVM-CNN Classification Technique for Human–Vehicle Targets in an Automotive LFMCW Radar |
| title_short | Hybrid SVM-CNN Classification Technique for Human–Vehicle Targets in an Automotive LFMCW Radar |
| title_sort | hybrid svm cnn classification technique for human vehicle targets in an automotive lfmcw radar |
| topic | millimeter-wave radar convolutional neural network human–vehicle classification |
| url | https://www.mdpi.com/1424-8220/20/12/3504 |
| work_keys_str_mv | AT qisongwu hybridsvmcnnclassificationtechniqueforhumanvehicletargetsinanautomotivelfmcwradar AT tenggao hybridsvmcnnclassificationtechniqueforhumanvehicletargetsinanautomotivelfmcwradar AT zhichaolai hybridsvmcnnclassificationtechniqueforhumanvehicletargetsinanautomotivelfmcwradar AT dianzeli hybridsvmcnnclassificationtechniqueforhumanvehicletargetsinanautomotivelfmcwradar |