IAM

OPENSOURCEFAN STUDYING
STUDYINGCOMPUTERSCIENCEANDMATH COMPUTERSCIENCE

Check out the latest superpixel benchmark — Superpixel Benchmark (2016) — and let me know your opinion! @david_stutz

ARTICLE

Paper “Superpixels: An Evaluation of the State-of-the-Art”

In the course of the last couple of semesters, I extended the initial comparison of superpixel algorithms in my bachelor thesis to a comprehensive comparison of 28 state-of-the-art algorithms on 5 datasets with regard to quantitative and qualitative performance. The results are now available on ArXiv.

Update. The source code of the benchmark and the evaluated superpixel algorithms can now be found on GitHub, see here.

Abstract

Superpixels group perceptually similar pixels to create visually meaningful entities while heavily reducing the number of primitives. As of these properties, superpixel algorithms have received much attention since their naming in~2003. By today, publicly available and well-understood superpixel algorithms have turned into standard tools in low-level vision. As such, and due to their quick adoption in a wide range of applications, appropriate benchmarks are crucial for algorithm selection and comparison. Until now, the rapidly growing number of algorithms as well as varying experimental setups hindered the development of a unifying benchmark. We present a comprehensive evaluation of 28 state-of-the-art superpixel algorithms utilizing a benchmark focussing on fair comparison and designed to provide new and relevant insights. To this end, we explicitly discuss parameter optimization and the importance of strictly enforcing connectivity. Furthermore, by extending well-known metrics, we are able to summarize algorithm performance independent of the number of generated superpixels, thereby overcoming a major limitation of available benchmarks. Furthermore, we discuss runtime, robustness against noise, blur and affine transformations, implementation details as well as aspects of visual quality. Finally, we present an overall ranking of superpixel algorithms which redefines the state-of-the-art and enables researchers to easily select appropriate algorithms and the corresponding implementations which themselves are made publicly available as part of our benchmark.

Paper (∼ 4.3MB)
@article{DBLP:journals/corr/IoffeS15,
    author    = {David Stutz and Alexander Hermans and Bastian Leibe},
    title     = {Superpixels: An Evaluation of the State-of-the-Art},
    journal   = {CoRR},
    volume    = {abs/1612.01601},
    year      = {2016},
    url       = {https://arxiv.org/abs/1612.01601},
}

What is your opinion on this article? Did you find it interesting or useful? Let me know your thoughts in the comments below or using the following platforms:

@david_stutz