Instance Segmentation of Dense and Overlapping Objects via Layering
Long Chen (LfB, RWTH Aachen),* Yuli Wu (RWTH Aachen University), Dorit Merhof (RWTH Aachen University)
The 33rd British Machine Vision Conference
Abstract
Instance segmentation aims to delineate each individual object of interest in an image. State-of-the-art approaches achieve this goal by either partitioning semantic segmentations or refining coarse representations of detected objects. In this work, we propose a novel approach to solve the problem via object layering, i.e. by distributing crowded, even overlapping objects into different layers. By grouping spatially separated objects in the same layer, instances can be effortlessly isolated by extracting connected components in each layer. In comparison to previous methods, our approach is not affected by complex object shapes or object overlaps. With minimal post-processing, our method yields very competitive results on a diverse line of datasets: C. elegans (BBBC), Overlapping Cervical Cells (OCC) and cultured neuroblastoma cells (CCDB). The source code is publicly available.Video
Citation
@inproceedings{Chen_2022_BMVC,
author = {Long Chen and Yuli Wu and Dorit Merhof},
title = {Instance Segmentation of Dense and Overlapping Objects via Layering},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0400.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by