Lightweight PVIDNet: A Priority Vehicles Detection Network Model Based on Deep Learning for Intelligent Traffic Lights
Minimizing human intervention in engines, such as traffic lights, through automatic applications and sensors has been the focus of many studies. Thus, Deep Learning (DL) algorithms have been studied for traffic signs and vehicle identification in an urban traffic context. However, there is a lack of...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/21/6218 |
| _version_ | 1797549227599986688 |
|---|---|
| author | Rodrigo Carvalho Barbosa Muhammad Shoaib Ayub Renata Lopes Rosa Demóstenes Zegarra Rodríguez Lunchakorn Wuttisittikulkij |
| author_facet | Rodrigo Carvalho Barbosa Muhammad Shoaib Ayub Renata Lopes Rosa Demóstenes Zegarra Rodríguez Lunchakorn Wuttisittikulkij |
| author_sort | Rodrigo Carvalho Barbosa |
| collection | DOAJ |
| description | Minimizing human intervention in engines, such as traffic lights, through automatic applications and sensors has been the focus of many studies. Thus, Deep Learning (DL) algorithms have been studied for traffic signs and vehicle identification in an urban traffic context. However, there is a lack of priority vehicle classification algorithms with high accuracy, fast processing, and a lightweight solution. For filling those gaps, a vehicle detection system is proposed, which is integrated with an intelligent traffic light. Thus, this work proposes (1) a novel vehicle detection model named Priority Vehicle Image Detection Network (PVIDNet), based on <inline-formula><math display="inline"><semantics><mrow><mi>Y</mi><mi>O</mi><mi>L</mi><msub><mi>O</mi><mrow><mi>V</mi><mn>3</mn></mrow></msub></mrow></semantics></math></inline-formula>, (2) a lightweight design strategy for the PVIDNet model using an activation function to decrease the execution time of the proposed model, (3) a traffic control algorithm based on the Brazilian Traffic Code, and (4) a database containing Brazilian vehicle images. The effectiveness of the proposed solutions were evaluated using the Simulation of Urban MObility (SUMO) tool. Results show that PVIDNet reached an accuracy higher than 0.95, and the waiting time of priority vehicles was reduced by up to 50%, demonstrating the effectiveness of the proposed solution. |
| first_indexed | 2024-03-10T15:10:40Z |
| format | Article |
| id | doaj.art-1a8c12c5a091492d93c91f1cc02f5a7b |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T15:10:40Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-1a8c12c5a091492d93c91f1cc02f5a7b2023-11-20T19:18:47ZengMDPI AGSensors1424-82202020-10-012021621810.3390/s20216218Lightweight PVIDNet: A Priority Vehicles Detection Network Model Based on Deep Learning for Intelligent Traffic LightsRodrigo Carvalho Barbosa0Muhammad Shoaib Ayub1Renata Lopes Rosa2Demóstenes Zegarra Rodríguez3Lunchakorn Wuttisittikulkij4Department of Computer Science, Federal University of Lavras, Minas Gerais 37200-000, BrazilDepartment of Electrical Engineering, Chulalongkorn University, Bangkok 10330, ThailandDepartment of Computer Science, Federal University of Lavras, Minas Gerais 37200-000, BrazilDepartment of Computer Science, Federal University of Lavras, Minas Gerais 37200-000, BrazilDepartment of Electrical Engineering, Chulalongkorn University, Bangkok 10330, ThailandMinimizing human intervention in engines, such as traffic lights, through automatic applications and sensors has been the focus of many studies. Thus, Deep Learning (DL) algorithms have been studied for traffic signs and vehicle identification in an urban traffic context. However, there is a lack of priority vehicle classification algorithms with high accuracy, fast processing, and a lightweight solution. For filling those gaps, a vehicle detection system is proposed, which is integrated with an intelligent traffic light. Thus, this work proposes (1) a novel vehicle detection model named Priority Vehicle Image Detection Network (PVIDNet), based on <inline-formula><math display="inline"><semantics><mrow><mi>Y</mi><mi>O</mi><mi>L</mi><msub><mi>O</mi><mrow><mi>V</mi><mn>3</mn></mrow></msub></mrow></semantics></math></inline-formula>, (2) a lightweight design strategy for the PVIDNet model using an activation function to decrease the execution time of the proposed model, (3) a traffic control algorithm based on the Brazilian Traffic Code, and (4) a database containing Brazilian vehicle images. The effectiveness of the proposed solutions were evaluated using the Simulation of Urban MObility (SUMO) tool. Results show that PVIDNet reached an accuracy higher than 0.95, and the waiting time of priority vehicles was reduced by up to 50%, demonstrating the effectiveness of the proposed solution.https://www.mdpi.com/1424-8220/20/21/6218intelligent traffic lightdeep learningimage detectionvehicle classification |
| spellingShingle | Rodrigo Carvalho Barbosa Muhammad Shoaib Ayub Renata Lopes Rosa Demóstenes Zegarra Rodríguez Lunchakorn Wuttisittikulkij Lightweight PVIDNet: A Priority Vehicles Detection Network Model Based on Deep Learning for Intelligent Traffic Lights Sensors intelligent traffic light deep learning image detection vehicle classification |
| title | Lightweight PVIDNet: A Priority Vehicles Detection Network Model Based on Deep Learning for Intelligent Traffic Lights |
| title_full | Lightweight PVIDNet: A Priority Vehicles Detection Network Model Based on Deep Learning for Intelligent Traffic Lights |
| title_fullStr | Lightweight PVIDNet: A Priority Vehicles Detection Network Model Based on Deep Learning for Intelligent Traffic Lights |
| title_full_unstemmed | Lightweight PVIDNet: A Priority Vehicles Detection Network Model Based on Deep Learning for Intelligent Traffic Lights |
| title_short | Lightweight PVIDNet: A Priority Vehicles Detection Network Model Based on Deep Learning for Intelligent Traffic Lights |
| title_sort | lightweight pvidnet a priority vehicles detection network model based on deep learning for intelligent traffic lights |
| topic | intelligent traffic light deep learning image detection vehicle classification |
| url | https://www.mdpi.com/1424-8220/20/21/6218 |
| work_keys_str_mv | AT rodrigocarvalhobarbosa lightweightpvidnetapriorityvehiclesdetectionnetworkmodelbasedondeeplearningforintelligenttrafficlights AT muhammadshoaibayub lightweightpvidnetapriorityvehiclesdetectionnetworkmodelbasedondeeplearningforintelligenttrafficlights AT renatalopesrosa lightweightpvidnetapriorityvehiclesdetectionnetworkmodelbasedondeeplearningforintelligenttrafficlights AT demosteneszegarrarodriguez lightweightpvidnetapriorityvehiclesdetectionnetworkmodelbasedondeeplearningforintelligenttrafficlights AT lunchakornwuttisittikulkij lightweightpvidnetapriorityvehiclesdetectionnetworkmodelbasedondeeplearningforintelligenttrafficlights |