TRACER: Efficient Object Re-Identification in Networked Cameras through Adaptive Query Processing

2025-07-12

AI Summary

To address low query efficiency and insufficient recall in cross-camera person re-identification (Re-ID) within large-scale camera networks, this paper proposes a video database management system supporting adaptive query processing. Existing approaches, constrained by local historical modeling and static query strategies, fail to balance accuracy and high-recall requirements. Our method innovatively employs recurrent neural networks to model long-term cross-camera historical associations, designs a probabilistic adaptive search framework, and dynamically optimizes sampling via an exploration-exploitation mechanism; it further supports incremental query window processing. End-to-end integration of synthetic data generation enables construction of the first multi-camera Re-ID benchmark dataset grounded in real-world traffic distributions. Evaluations across multiple benchmarks demonstrate a 3.9× average speedup in query efficiency over state-of-the-art methods, alongside significant improvements in recall and robustness.

Technology Category

• Computer Vision: Image and Video Retrieval
• Data Mining & Knowledge Management: Intelligent Query Processing
• Search and Optimization: Distributed Search

Application Category

• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Efficiently re-identifying and tracking objects across a network of cameras is crucial for applications like traffic surveillance. Spatula is the state-of-the-art video database management system (VDBMS) for processing Re-ID queries. However, it suffers from two limitations. Its spatio-temporal filtering scheme has limited accuracy on large camera networks due to localized camera history. It is not suitable for critical video analytics applications that require high recall due to a lack of support for adaptive query processing. In this paper, we present Tracer, a novel VDBMS for efficiently processing Re-ID queries using an adaptive query processing framework. Tracer selects the optimal camera to process at each time step by training a recurrent network to model long-term historical correlations. To accelerate queries under a high recall constraint, Tracer incorporates a probabilistic adaptive search model that processes camera feeds in incremental search windows and dynamically updates the sampling probabilities using an exploration-exploitation strategy. To address the paucity of benchmarks for the Re-ID task due to privacy concerns, we present a novel synthetic benchmark for generating multi-camera Re-ID datasets based on real-world traffic distribution. Our evaluation shows that Tracer outperforms the state-of-the-art cross-camera analytics system by 3.9x on average across diverse datasets.

Problem

• Improves object re-identification accuracy in large camera networks
• Enables adaptive query processing for high-recall video analytics
• Introduces synthetic benchmark for multi-camera Re-ID datasets

Innovation

• Adaptive query processing framework for Re-ID
• Recurrent network models long-term camera correlations
• Probabilistic adaptive search with exploration-exploitation strategy