Heterogeneous Fusion of Camera and mmWave Radar Sensor of Optimizing Convolutional Neural Networks for Parking Meter System
In this article, a novel heterogeneous fusion of convolutional neural networks that combined an RGB camera and an active mmWave radar sensor for the smart parking meter is proposed. In general, the parking fee collector on the street outdoor surroundings by traffic flows, shadows, and reflections ma...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/8/4159 |
| _version_ | 1797603507081052160 |
|---|---|
| author | Chi-Chia Sun Yong-Ye Lin Wei-Jia Hong Gene-Eu Jan |
| author_facet | Chi-Chia Sun Yong-Ye Lin Wei-Jia Hong Gene-Eu Jan |
| author_sort | Chi-Chia Sun |
| collection | DOAJ |
| description | In this article, a novel heterogeneous fusion of convolutional neural networks that combined an RGB camera and an active mmWave radar sensor for the smart parking meter is proposed. In general, the parking fee collector on the street outdoor surroundings by traffic flows, shadows, and reflections makes it an exceedingly tough task to identify street parking regions. The proposed heterogeneous fusion convolutional neural networks combine an active radar sensor and image input with specific geometric area, allowing them to detect the parking region against different tough conditions such as rain, fog, dust, snow, glare, and traffic flow. They use convolutional neural networks to acquire output results along with the individual training and fusion of RGB camera and mmWave radar data. To achieve real-time performance, the proposed algorithm has been implemented on a GPU-accelerated embedded platform Jetson Nano with a heterogeneous hardware acceleration methodology. The experimental results exhibit that the accuracy of the heterogeneous fusion method can reach up to 99.33% on average. |
| first_indexed | 2024-03-11T04:32:07Z |
| format | Article |
| id | doaj.art-84e5ceb46de94d50b1fedec5fc597dca |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T04:32:07Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-84e5ceb46de94d50b1fedec5fc597dca2023-11-17T21:19:55ZengMDPI AGSensors1424-82202023-04-01238415910.3390/s23084159Heterogeneous Fusion of Camera and mmWave Radar Sensor of Optimizing Convolutional Neural Networks for Parking Meter SystemChi-Chia Sun0Yong-Ye Lin1Wei-Jia Hong2Gene-Eu Jan3Department of Electrical Engineering, National Formosa University, Huwei 632, TaiwanDepartment of Electro-Optical Engineering, National Formosa University, Huwei 632, TaiwanDepartment of Electrical Engineering, National Formosa University, Huwei 632, TaiwanDepartment of Electrical Engineering, National Taipei University, New Taipei City 237, TaiwanIn this article, a novel heterogeneous fusion of convolutional neural networks that combined an RGB camera and an active mmWave radar sensor for the smart parking meter is proposed. In general, the parking fee collector on the street outdoor surroundings by traffic flows, shadows, and reflections makes it an exceedingly tough task to identify street parking regions. The proposed heterogeneous fusion convolutional neural networks combine an active radar sensor and image input with specific geometric area, allowing them to detect the parking region against different tough conditions such as rain, fog, dust, snow, glare, and traffic flow. They use convolutional neural networks to acquire output results along with the individual training and fusion of RGB camera and mmWave radar data. To achieve real-time performance, the proposed algorithm has been implemented on a GPU-accelerated embedded platform Jetson Nano with a heterogeneous hardware acceleration methodology. The experimental results exhibit that the accuracy of the heterogeneous fusion method can reach up to 99.33% on average.https://www.mdpi.com/1424-8220/23/8/4159parking meterembedded computerconvolutional neural networksmmWave radar |
| spellingShingle | Chi-Chia Sun Yong-Ye Lin Wei-Jia Hong Gene-Eu Jan Heterogeneous Fusion of Camera and mmWave Radar Sensor of Optimizing Convolutional Neural Networks for Parking Meter System Sensors parking meter embedded computer convolutional neural networks mmWave radar |
| title | Heterogeneous Fusion of Camera and mmWave Radar Sensor of Optimizing Convolutional Neural Networks for Parking Meter System |
| title_full | Heterogeneous Fusion of Camera and mmWave Radar Sensor of Optimizing Convolutional Neural Networks for Parking Meter System |
| title_fullStr | Heterogeneous Fusion of Camera and mmWave Radar Sensor of Optimizing Convolutional Neural Networks for Parking Meter System |
| title_full_unstemmed | Heterogeneous Fusion of Camera and mmWave Radar Sensor of Optimizing Convolutional Neural Networks for Parking Meter System |
| title_short | Heterogeneous Fusion of Camera and mmWave Radar Sensor of Optimizing Convolutional Neural Networks for Parking Meter System |
| title_sort | heterogeneous fusion of camera and mmwave radar sensor of optimizing convolutional neural networks for parking meter system |
| topic | parking meter embedded computer convolutional neural networks mmWave radar |
| url | https://www.mdpi.com/1424-8220/23/8/4159 |
| work_keys_str_mv | AT chichiasun heterogeneousfusionofcameraandmmwaveradarsensorofoptimizingconvolutionalneuralnetworksforparkingmetersystem AT yongyelin heterogeneousfusionofcameraandmmwaveradarsensorofoptimizingconvolutionalneuralnetworksforparkingmetersystem AT weijiahong heterogeneousfusionofcameraandmmwaveradarsensorofoptimizingconvolutionalneuralnetworksforparkingmetersystem AT geneeujan heterogeneousfusionofcameraandmmwaveradarsensorofoptimizingconvolutionalneuralnetworksforparkingmetersystem |