Retrieval in Long Surveillance Videos using User Described Motion and Object Attributes

TL;DR

This paper introduces a content-based retrieval method for long surveillance videos that uses user-defined motion and object attributes, employing lightweight processing, hashing, and dynamic programming to efficiently find matching video segments.

Contribution

The paper presents a novel retrieval approach combining low-level feature extraction, hashing, and dynamic programming to handle long, low-contrast surveillance videos with occlusions and complex routes.

Findings

Effective retrieval of long routes in surveillance videos

Robust motion estimation in low-contrast conditions

Demonstrated application in counting and abandoned object detection

Abstract

We present a content-based retrieval method for long surveillance videos both for wide-area (Airborne) as well as near-field imagery (CCTV). Our goal is to retrieve video segments, with a focus on detecting objects moving on routes, that match user-defined events of interest. The sheer size and remote locations where surveillance videos are acquired, necessitates highly compressed representations that are also meaningful for supporting user-defined queries. To address these challenges we archive long-surveillance video through lightweight processing based on low-level local spatio-temporal extraction of motion and object features. These are then hashed into an inverted index using locality-sensitive hashing (LSH). This local approach allows for query flexibility as well as leads to significant gains in compression. Our second task is to extract partial matches to the user-created query and assembles them into full matches using Dynamic Programming (DP). DP exploits causality to assemble the indexed low level features into a video segment which matches the query route. We examine CCTV and Airborne footage, whose low contrast makes motion extraction more difficult. We generate robust motion estimates for Airborne data using a tracklets generation algorithm while we use Horn and Schunck approach to generate motion estimates for CCTV. Our approach handles long routes, low contrasts and occlusion. We derive bounds on the rate of false positives and demonstrate the effectiveness of the approach for counting, motion pattern recognition and abandoned object applications.