Moving target classification and tracking from real-time video

TLDR

The paper presents an end‑to‑end approach that extracts, classifies, and tracks moving targets in real‑time video. Targets are detected via pixel‑wise frame differencing, classified into human, vehicle, or background using a metric with temporal consistency, and tracked with temporal differencing and template matching. The system robustly identifies targets, rejects background clutter, and maintains tracking over long distances and times despite occlusions, appearance changes, and motion cessation.

Abstract

This paper describes an end-to-end method for extracting moving targets from a real-time video stream, classifying them into predefined categories according to image-based properties, and then robustly tracking them. Moving targets are detected using the pixel wise difference between consecutive image frames. A classification metric is applied these targets with a temporal consistency constraint to classify them into three categories: human, vehicle or background clutter. Once classified targets are tracked by a combination of temporal differencing and template matching. The resulting system robustly identifies targets of interest, rejects background clutter and continually tracks over large distances and periods of time despite occlusions, appearance changes and cessation of target motion.