Segmentation of Moving Objects in Traffic Video Datasets

Anusha Aswath, Renu Rameshan, Biju Krishnan, Senthil Ponkumar

2020

Abstract

In this paper, we aim to automate segmentation of multiple moving objects in video datasets specific to traffic use case. This automation is achieved in two steps. First, we generate bounding boxes using our proposed multi-object tracking algorithm based on convolutional neural network (CNN) model which is capable of re-identification. Second, we convert the various tracked objects into pixel masks using an instance segmentation algorithm. The proposed method of tracking has shown promising results with high precision and success rate in traffic video datasets specifically when there is severe object occlusion and frequent camera motion present in the video. Generating instance aware pixel masks for multiple object instances of a video dataset for ground truth is a tedious task. The proposed method offers interactive corrections with human-in-the-loop to improve the bounding boxes and the pixel masks as the video sequence proceeds. It exhibits powerful generalization capabilities and hence the proposed tracker and segmentation network was applied as a part of an annotation tool to reduce human effort and time.

Download


Paper Citation


in Harvard Style

Aswath A., Rameshan R., Krishnan B. and Ponkumar S. (2020). Segmentation of Moving Objects in Traffic Video Datasets. In Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-397-1, pages 321-332. DOI: 10.5220/0008940403210332


in Bibtex Style

@conference{icpram20,
author={Anusha Aswath and Renu Rameshan and Biju Krishnan and Senthil Ponkumar},
title={Segmentation of Moving Objects in Traffic Video Datasets},
booktitle={Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2020},
pages={321-332},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008940403210332},
isbn={978-989-758-397-1},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Segmentation of Moving Objects in Traffic Video Datasets
SN - 978-989-758-397-1
AU - Aswath A.
AU - Rameshan R.
AU - Krishnan B.
AU - Ponkumar S.
PY - 2020
SP - 321
EP - 332
DO - 10.5220/0008940403210332