Vehicle recognition pipeline via DeepSort on aerial image datasets

Muhammad Hanzla; Muhammad Ovais Yusuf; Naif Al Mudawi; Touseef Sadiq; Nouf Abdullah Almujally; Hameedur Rahman; Abdulwahab Alazeb; Asaad Algarni

doi:10.3389/fnbot.2024.1430155

Vehicle recognition pipeline via DeepSort on aerial image datasets

Front Neurorobot. 2024 Aug 16:18:1430155. doi: 10.3389/fnbot.2024.1430155. eCollection 2024.

Authors

Muhammad Hanzla¹, Muhammad Ovais Yusuf¹, Naif Al Mudawi², Touseef Sadiq³, Nouf Abdullah Almujally⁴, Hameedur Rahman¹, Abdulwahab Alazeb², Asaad Algarni⁵

Affiliations

¹ Faculty of Computing and AI, Air University, Islamabad, Pakistan.
² Department of Computer Science, College of Computer Science and Information System, Najran University, Najran, Saudi Arabia.
³ Department of Information and Communication Technology, Centre for Artificial Intelligence Research, University of Agder, Grimstad, Norway.
⁴ Department of Information Systems, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University, Riyadh, Saudi Arabia.
⁵ Department of Computer Sciences, Faculty of Computing and Information Technology, Northern Border University, Rafha, Saudi Arabia.

Abstract

Introduction: Unmanned aerial vehicles (UAVs) are widely used in various computer vision applications, especially in intelligent traffic monitoring, as they are agile and simplify operations while boosting efficiency. However, automating these procedures is still a significant challenge due to the difficulty of extracting foreground (vehicle) information from complex traffic scenes.

Methods: This paper presents a unique method for autonomous vehicle surveillance that uses FCM to segment aerial images. YOLOv8, which is known for its ability to detect tiny objects, is then used to detect vehicles. Additionally, a system that utilizes ORB features is employed to support vehicle recognition, assignment, and recovery across picture frames. Vehicle tracking is accomplished using DeepSORT, which elegantly combines Kalman filtering with deep learning to achieve precise results.

Results: Our proposed model demonstrates remarkable performance in vehicle identification and tracking with precision of 0.86 and 0.84 on the VEDAI and SRTID datasets, respectively, for vehicle detection.

Discussion: For vehicle tracking, the model achieves accuracies of 0.89 and 0.85 on the VEDAI and SRTID datasets, respectively.

Keywords: DeepSort; deep learning; dynamic environments; object recognition; path planning; remote sensing; unmanned aerial vehicles.

Grants and funding

The author(s) declare financial support was received for the research, authorship, and/or publication of this article. The authors are thankful to the Deanship of Scientific Research at Najran University for funding this work under the Research Group Funding program grant code (NU/RG/SERC/13/18). This research is sup- ported by Princess Nourah bint Abdulrahman University Researchers Supporting Project number (PNURSP2024R410), Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia. The authors extend their appreciation to the Deanship of Scientific Research at Northern Border University, Arar, KSA for funding this research work through the project number “NBU-FFR-2024-231-09.”