# Addressing Ambiguity in Multi-target Tracking by Hierarchical Strategy

## TL;DR

This paper introduces a hierarchical multi-target tracking method that improves detection association and reduces identity switches using a novel scoring system, ConfRank, leading to competitive results.

## Contribution

The paper proposes a hierarchical tracking framework with ConfRank scoring for better detection linking and identity preservation in multi-target tracking.

## Key findings

- Achieves lower identity switches compared to state-of-the-art methods.
- Effectively recovers missed detections through hierarchical association.
- Demonstrates competitive performance on multiple datasets.

## Abstract

This paper presents a novel hierarchical approach for the simultaneous tracking of multiple targets in a video. We use a network flow approach to link detections in low-level and tracklets in high-level. At each step of the hierarchy, the confidence of candidates is measured by using a new scoring system, ConfRank, that considers the quality and the quantity of its neighborhood. The output of the first stage is a collection of safe tracklets and unlinked high-confidence detections. For each individual detection, we determine if it belongs to an existing or is a new tracklet. We show the effect of our framework to recover missed detections and reduce switch identity. The proposed tracker is referred to as TVOD for multi-target tracking using the visual tracker and generic object detector. We achieve competitive results with lower identity switches on several datasets comparing to state-of-the-art.