Cell Tracking-by-detection using Elliptical Bounding Boxes

TL;DR

This paper introduces a data-efficient cell tracking method using elliptical shape approximation and generic detectors, reducing annotation needs while maintaining competitive accuracy.

Contribution

It presents a novel tracking-by-detection approach that uses elliptical cell shape modeling and global data association, minimizing the need for extensive annotated data.

Findings

Achieves competitive detection and tracking accuracy with less annotated data.

Uses elliptical shape approximation to model cells as Gaussian distributions.

Employs a global data association algorithm based on probability distance metrics.

Abstract

Cell detection and tracking are paramount for bio-analysis. Recent approaches rely on the tracking-by-model evolution paradigm, which usually consists of training end-to-end deep learning models to detect and track the cells on the frames with promising results. However, such methods require extensive amounts of annotated data, which is time-consuming to obtain and often requires specialized annotators. This work proposes a new approach based on the classical tracking-by-detection paradigm that alleviates the requirement of annotated data. More precisely, it approximates the cell shapes as oriented ellipses and then uses generic-purpose oriented object detectors to identify the cells in each frame. We then rely on a global data association algorithm that explores temporal cell similarity using probability distance metrics, considering that the ellipses relate to two-dimensional Gaussian distributions. Our results show that our method can achieve detection and tracking results competitively with state-of-the-art techniques that require considerably more extensive data annotation. Our code is available at: https://github.com/LucasKirsten/Deep-Cell-Tracking-EBB.