Clique: Spatiotemporal Object Re-identification at the City Scale

TL;DR

Clique is a practical spatiotemporal object re-identification system for city-scale surveillance that clusters fuzzy features and optimizes camera sampling to achieve high accuracy and real-time performance.

Contribution

The paper introduces Clique, a novel re-identification engine that combines feature clustering and camera sampling strategies for efficient city-scale object tracking.

Findings

Achieved 0.87 recall at 5 on 70 queries

Operates at 830x real-time video processing speed

Effectively handles 25 hours of city surveillance videos

Abstract

Object re-identification (ReID) is a key application of city-scale cameras. While classic ReID tasks are often considered as image retrieval, we treat them as spatiotemporal queries for locations and times in which the target object appeared. Spatiotemporal reID is challenged by the accuracy limitation in computer vision algorithms and the colossal videos from city cameras. We present Clique, a practical ReID engine that builds upon two new techniques: (1) Clique assesses target occurrences by clustering fuzzy object features extracted by ReID algorithms, with each cluster representing the general impression of a distinct object to be matched against the input; (2) to search in videos, Clique samples cameras to maximize the spatiotemporal coverage and incrementally adds cameras for processing on demand. Through evaluation on 25 hours of videos from 25 cameras, Clique reached a high accuracy of 0.87 (recall at 5) across 70 queries and runs at 830x of video realtime in achieving high accuracy.