PolyTrack: Tracking with Bounding Polygons

TL;DR

PolyTrack introduces a fast multi-object tracking and segmentation method using bounding polygons, improving tracking accuracy in urban driving scenarios by combining heatmaps, polygon segmentation, and Kalman filtering.

Contribution

The paper proposes a novel approach that replaces bounding boxes with bounding polygons for object detection and tracking, tailored for automated driving applications.

Findings

Effective polygon-based segmentation for objects in urban scenes

Reduced ID switches with Kalman filter integration

Competitive performance on MOTS and KITTIMOTS datasets

Abstract

In this paper, we present a novel method called PolyTrack for fast multi-object tracking and segmentation using bounding polygons. Polytrack detects objects by producing heatmaps of their center keypoint. For each of them, a rough segmentation is done by computing a bounding polygon over each instance instead of the traditional bounding box. Tracking is done by taking two consecutive frames as input and computing a center offset for each object detected in the first frame to predict its location in the second frame. A Kalman filter is also applied to reduce the number of ID switches. Since our target application is automated driving systems, we apply our method on urban environment videos. We trained and evaluated PolyTrack on the MOTS and KITTIMOTS datasets. Results show that tracking polygons can be a good alternative to bounding box and mask tracking. The code of PolyTrack is available at https://github.com/gafaua/PolyTrack.