Superpixels: An evaluation of the state-of-the-art

• Published in: Computer vision and image understanding Vol. 166; pp. 1 - 27
• Main Authors: Stutz, David, Hermans, Alexander, Leibe, Bastian
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.01.2018
• Subjects: Benchmark; Evaluation; Image segmentation; Perceptual grouping; Superpixel segmentation; Superpixels; Benchmark; Image segmentation; Evaluation; Superpixels; Superpixel segmentation; Perceptual grouping
• ISSN: 1077-3142; 1090-235X
• DOI: 10.1016/j.cviu.2017.03.007

•An extensive evaluation of 28 superpixel algorithms on 5 datasets.•Explicit discussion of parameter optimization, including superpixel connectivity.•Presentation of visual quality, algorithm runtime, and a performance-based ranking.•The evaluated implementations as well as the benchmark are publicly available. Superpixels group perceptually similar pixels to create visually meaningful entities while heavily reducing the number of primitives for subsequent processing steps. As of these properties, superpixel algorithms have received much attention since their naming in 2003 (Ren and Malik, 2003). By today, publicly available 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 insights relevant for applications. 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 at http://www.davidstutz.de/projects/superpixel-benchmark/.