Interpretable Human Activity Recognition for Subtle Robbery Detection in Surveillance Videos

TL;DR

This paper introduces a pose-driven, interpretable system for real-time detection of subtle street robberies in surveillance videos, suitable for edge devices.

Contribution

It combines pose estimation, handcrafted features, and a Random Forest classifier into a real-time, interpretable pipeline for detecting subtle robbery events.

Findings

Effective detection on staged and internet videos

Generalizes across different scenes and viewpoints

Runs in real-time on NVIDIA Jetson Nano

Abstract

Non-violent street robberies (snatch-and-run) are difficult to detect automatically because they are brief, subtle, and often indistinguishable from benign human interactions in unconstrained surveillance footage. This paper presents a hybrid, pose-driven approach for detecting snatch-and-run events that combines real-time perception with an interpretable classification stage suitable for edge deployment. The system uses a YOLO-based pose estimator to extract body keypoints for each tracked person and computes kinematic and interaction features describing hand speed, arm extension, proximity, and relative motion between an aggressor-victim pair. A Random Forest classifier is trained on these descriptors, and a temporal hysteresis filter is applied to stabilize frame-level predictions and reduce spurious alarms. We evaluate the method on a staged dataset and on a disjoint test set collected from internet videos, demonstrating promising generalization across different scenes and camera viewpoints. Finally, we implement the complete pipeline on an NVIDIA Jetson Nano and report real-time performance, supporting the feasibility of proactive, on-device robbery detection.