A Real-Time Tracking Algorithm for Multi-Target UAV Based on Deep Learning
UAV technology is a basic technology aiming to help realize smart living and the construction of smart cities. Its vigorous development in recent years has also increased the presence of unmanned aerial vehicles (UAVs) in people’s lives, and it has been increasingly used in logistics, transportation...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/1/2 |
| _version_ | 1827624012898893824 |
|---|---|
| author | Tao Hong Hongming Liang Qiye Yang Linquan Fang Michel Kadoch Mohamed Cheriet |
| author_facet | Tao Hong Hongming Liang Qiye Yang Linquan Fang Michel Kadoch Mohamed Cheriet |
| author_sort | Tao Hong |
| collection | DOAJ |
| description | UAV technology is a basic technology aiming to help realize smart living and the construction of smart cities. Its vigorous development in recent years has also increased the presence of unmanned aerial vehicles (UAVs) in people’s lives, and it has been increasingly used in logistics, transportation, photography and other fields. However, the rise in the number of drones has also put pressure on city regulation. Using traditional methods to monitor small objects flying slowly at low altitudes would be costly and ineffective. This study proposed a real-time UAV tracking scheme that uses the 5G network to transmit UAV monitoring images to the cloud and adopted a machine learning algorithm to detect and track multiple targets. Aiming at the difficulties in UAV detection and tracking, we optimized the network structure of the target detector yolo4 (You Only Look Once V4) and improved the target tracker DeepSORT, adopting the detection-tracking mode. In order to verify the reliability of the algorithm, we built a data set containing 3200 pictures of four UAVs in different environments, conducted training and testing on the model, and achieved 94.35% tracking accuracy and 69FPS detection speed under the GPU environment. The model was then deployed on ZCU104 to prove the feasibility of the scheme. |
| first_indexed | 2024-03-09T11:59:49Z |
| format | Article |
| id | doaj.art-a6608a0651814f92b7bdca45ef17ce75 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T11:59:49Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-a6608a0651814f92b7bdca45ef17ce752023-11-30T23:04:46ZengMDPI AGRemote Sensing2072-42922022-12-01151210.3390/rs15010002A Real-Time Tracking Algorithm for Multi-Target UAV Based on Deep LearningTao Hong0Hongming Liang1Qiye Yang2Linquan Fang3Michel Kadoch4Mohamed Cheriet5Yunnan Innovation Institute·BUAA, Kunming 650233, ChinaSchool of Electronic and Information Engineering, Beihang University, Beijing 100191, ChinaAVIC Chengdu Aircraft Design and Research Institute, Chengdu 610041, ChinaYunnan Innovation Institute·BUAA, Kunming 650233, ChinaÉcole de Technologie Supérieure (ETS), University of Quebec, Montreal, QC H2L 2C4, CanadaÉcole de Technologie Supérieure (ETS), University of Quebec, Montreal, QC H2L 2C4, CanadaUAV technology is a basic technology aiming to help realize smart living and the construction of smart cities. Its vigorous development in recent years has also increased the presence of unmanned aerial vehicles (UAVs) in people’s lives, and it has been increasingly used in logistics, transportation, photography and other fields. However, the rise in the number of drones has also put pressure on city regulation. Using traditional methods to monitor small objects flying slowly at low altitudes would be costly and ineffective. This study proposed a real-time UAV tracking scheme that uses the 5G network to transmit UAV monitoring images to the cloud and adopted a machine learning algorithm to detect and track multiple targets. Aiming at the difficulties in UAV detection and tracking, we optimized the network structure of the target detector yolo4 (You Only Look Once V4) and improved the target tracker DeepSORT, adopting the detection-tracking mode. In order to verify the reliability of the algorithm, we built a data set containing 3200 pictures of four UAVs in different environments, conducted training and testing on the model, and achieved 94.35% tracking accuracy and 69FPS detection speed under the GPU environment. The model was then deployed on ZCU104 to prove the feasibility of the scheme.https://www.mdpi.com/2072-4292/15/1/2UAV5Gmulti-target detection and trackingYOLOv4DeepSORT |
| spellingShingle | Tao Hong Hongming Liang Qiye Yang Linquan Fang Michel Kadoch Mohamed Cheriet A Real-Time Tracking Algorithm for Multi-Target UAV Based on Deep Learning Remote Sensing UAV 5G multi-target detection and tracking YOLOv4 DeepSORT |
| title | A Real-Time Tracking Algorithm for Multi-Target UAV Based on Deep Learning |
| title_full | A Real-Time Tracking Algorithm for Multi-Target UAV Based on Deep Learning |
| title_fullStr | A Real-Time Tracking Algorithm for Multi-Target UAV Based on Deep Learning |
| title_full_unstemmed | A Real-Time Tracking Algorithm for Multi-Target UAV Based on Deep Learning |
| title_short | A Real-Time Tracking Algorithm for Multi-Target UAV Based on Deep Learning |
| title_sort | real time tracking algorithm for multi target uav based on deep learning |
| topic | UAV 5G multi-target detection and tracking YOLOv4 DeepSORT |
| url | https://www.mdpi.com/2072-4292/15/1/2 |
| work_keys_str_mv | AT taohong arealtimetrackingalgorithmformultitargetuavbasedondeeplearning AT hongmingliang arealtimetrackingalgorithmformultitargetuavbasedondeeplearning AT qiyeyang arealtimetrackingalgorithmformultitargetuavbasedondeeplearning AT linquanfang arealtimetrackingalgorithmformultitargetuavbasedondeeplearning AT michelkadoch arealtimetrackingalgorithmformultitargetuavbasedondeeplearning AT mohamedcheriet arealtimetrackingalgorithmformultitargetuavbasedondeeplearning AT taohong realtimetrackingalgorithmformultitargetuavbasedondeeplearning AT hongmingliang realtimetrackingalgorithmformultitargetuavbasedondeeplearning AT qiyeyang realtimetrackingalgorithmformultitargetuavbasedondeeplearning AT linquanfang realtimetrackingalgorithmformultitargetuavbasedondeeplearning AT michelkadoch realtimetrackingalgorithmformultitargetuavbasedondeeplearning AT mohamedcheriet realtimetrackingalgorithmformultitargetuavbasedondeeplearning |