RAMOTS: A Real-Time System for Aerial Multi-Object Tracking based on Deep Learning and Big Data Technology

2025-02-06

AI Summary

To address the trade-off between accuracy and real-time performance in aerial multi-object tracking (MOT) caused by highly variable viewpoints, small object scales, and low-resolution UAV video, this paper proposes an end-to-end real-time tracking system. Methodologically, it deeply integrates Apache Kafka and Spark Streaming into the aerial MOT pipeline to establish a high-throughput, fault-tolerant, and scalable real-time processing architecture; further, it synergistically combines YOLOv8/v10 for detection with BoTSORT and ByteTrack for tracking. Evaluated on VisDrone2019-MOT, the system achieves HOTA of 48.14 and MOTA of 43.51, while sustaining 28 FPS inference speed on a single GPU. This work significantly enhances both algorithmic practicality and engineering deployability, delivering a production-ready solution for airborne visual perception under resource-constrained conditions.

Technology Category

• Computer Vision: Motion & Tracking
• Machine Learning: Hardware-aware ML
• Intelligent Robots: Multi-Robot Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Tracking, profiling, and countermeasures against them

Abstract

Multi-object tracking (MOT) in UAV-based video is challenging due to variations in viewpoint, low resolution, and the presence of small objects. While other research on MOT dedicated to aerial videos primarily focuses on the academic aspect by developing sophisticated algorithms, there is a lack of attention to the practical aspect of these systems. In this paper, we propose a novel real-time MOT framework that integrates Apache Kafka and Apache Spark for efficient and fault-tolerant video stream processing, along with state-of-the-art deep learning models YOLOv8/YOLOv10 and BYTETRACK/BoTSORT for accurate object detection and tracking. Our work highlights the importance of not only the advanced algorithms but also the integration of these methods with scalable and distributed systems. By leveraging these technologies, our system achieves a HOTA of 48.14 and a MOTA of 43.51 on the Visdrone2019-MOT test set while maintaining a real-time processing speed of 28 FPS on a single GPU. Our work demonstrates the potential of big data technologies and deep learning for addressing the challenges of MOT in UAV applications.

Problem

• Real-time multi-object tracking in UAV videos
• Integration of big data and deep learning technologies
• Improving accuracy and efficiency in aerial object tracking

Innovation

• Integrates Apache Kafka and Spark
• Uses YOLOv8/YOLOv10 models
• Implements BYTETRACK/BoTSORT algorithms