The TEDDY Framework: An Efficient Framework for Target Tracking Using Edge-Based Distributed Smart Cameras with Dynamic Camera Selection
Multi-camera target tracking is a critical technology for continuous monitoring in large-scale environments, with applications in smart cities, security surveillance, and emergency response. However, existing tracking systems often suffer from high computational costs and energy inefficiencies, part...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/6/3052 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Multi-camera target tracking is a critical technology for continuous monitoring in large-scale environments, with applications in smart cities, security surveillance, and emergency response. However, existing tracking systems often suffer from high computational costs and energy inefficiencies, particularly in resource-constrained edge computing environments. Traditional methods typically rely on static or heuristic-based camera selection, leading to redundant computations and suboptimal resource allocation. This paper introduces a novel framework for efficient single-target tracking using edge-based distributed smart cameras with dynamic camera selection. The proposed framework employs context-aware dynamic camera selection, activating only the cameras most likely to detect the target based on its predicted trajectory. This approach is designed for resource-constrained environments and significantly reduces computational load and energy consumption while maintaining high tracking accuracy. The framework was evaluated through two experiments. In the first, single-person tracking was conducted across multiple routes with various target behaviors, demonstrating the framework’s effectiveness in optimizing resource utilization. In the second, the framework was applied to a simulated urban traffic light adjustment system for emergency vehicles, achieving significant reductions in computational load while maintaining equivalent tracking accuracy compared to an always-on camera system. These findings highlight the robustness, scalability, and energy efficiency of the framework in edge-based camera networks. Furthermore, the framework enables future advancements in dynamic resource management and scalable tracking technologies. |
|---|---|
| ISSN: | 2076-3417 |