TurboPixels: A Superpixel Segmentation Algorithm Suitable for Real-Time Embedded Applications
Source abstract
Abstract
Superpixel segmentation aims to produce a consistent grouping of pixels. In recent years, the importance of superpixel segmentation has increased in computer vision since it offers useful primitives for extracting image features and simplifies the complexity of other image processing steps. In this work, we propose the TurboPixels algorithm, whose main contribution is a hardware architecture for superpixel segmentation. Compared with previous approaches, our superpixels are computed without the need for iterative loops. This makes it possible to reduce algorithmic complexity and increases processing speed. The experimental results indicate that our approach enables a small-scale FPGA-based implementation suitable for embedded applications. In addition, the results demonstrate that robust superpixel segmentation can be achieved with processing speeds up to 86 times faster than in previous works in the current literature.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: CCD and CMOS Imaging Sensors · Image Processing Techniques and Applications · Advanced Image and Video Retrieval Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Computer Science Department, Instituto Nacional de Astrofísica, Óptica y Electrónica (INAOE), San Andrés Cholula 72840, Mexico
Industrial Engineering Department, Tecnológico Nacional de México, Instituto Tecnológico de Tuxtla Gutiérrez (ITTG), Tuxtla Gutiérrez 29050, Mexico
Mechatronics Engineering Department, Tecnológico Nacional de México, Instituto Tecnológico de Tuxtla Gutiérrez (ITTG), Tuxtla Gutiérrez 29050, Mexico
References (23)
Show source-provided references
1. SLIC superpixels compared to state-of-the-art superpixel methods10.1109/TPAMI.2012.120 ↗
2. Detection of ring cell cancer in histopathological images with region of interest determined by SLIC superpixels method10.1007/s00521-022-07183-8 ↗
3. GPU accelerated waterpixel algorithm for superpixel segmentation of hyperspectral images10.1007/s11227-021-03666-y ↗
4. Normalized cuts and image segmentation10.1109/34.868688 ↗
5. Salem, M., Ibrahim, A.F., and Ali, H.A. (2013, January 26–27). Automatic quick-shift method for color image segmentation. Proceedings of the 2013 8th International Conference on Computer Engineering & Systems (ICCES), Cairo, Egypt.10.1109/ICCES.2013.6707212 ↗
6. Csillik, O. (2017). Fast segmentation and classification of very high resolution remote sensing data using SLIC superpixels. Remote Sens., 9.10.3390/rs9030243 ↗
7. Superpixels extraction by an Intuitionistic fuzzy clustering algorithm10.22201/icat.24486736e.2021.19.2.1581 ↗
8. Yang, F., Sun, Q., Jin, H., and Zhou, Z. (2020, January 14–19). Superpixel segmentation with fully convolutional networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.10.1109/CVPR42600.2020.01398 ↗
9. Fuzzy superpixel-based image segmentation10.1016/j.patcog.2022.109045 ↗
10. Giordano, D., Murabito, F., Palazzo, S., and Spampinato, C. (2015, January 7–12). Superpixel-based video object segmentation using perceptual organization and location prior. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7299114 ↗
11. Contour detection and hierarchical image segmentation10.1109/TPAMI.2010.161 ↗
12. Robust superpixel tracking10.1109/TIP.2014.2300823 ↗
13. Video object segmentation with shape cue based on spatiotemporal superpixel neighbourhood10.1049/iet-cvi.2012.0189 ↗
14. Galasso, F., Cipolla, R., and Schiele, B. (2012, January 5–9). Video segmentation with superpixels. Proceedings of the Computer Vision–ACCV 2012: 11th Asian Conference on Computer Vision, Daejeon, Republic of Korea. Revised Selected Papers, Part I 11.
15. Cheng, J., Liu, J., Xu, Y., Yin, F., Wong, D.W.K., Lee, B.H., Cheung, C., Aung, T., and Wong, T.Y. (September, January 28). Superpixel classification for initialization in model based optic disc segmentation. Proceedings of the 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, San Diego, CA, USA.
16. Superpixel classification based optic disc and optic cup segmentation for glaucoma screening10.1109/TMI.2013.2247770 ↗
17. Superpixel segmentation: A benchmark10.1016/j.image.2017.04.007 ↗
18. Felzenszwalb, P.F., and Huttenlocher, D.P. (1998, January 23–25). Image segmentation using local variation. Proceedings of the 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No. 98CB36231), Santa Barbara, CA, USA.10.1109/CVPR.1998.698594 ↗
19. Ghimire, M., Regentova, E., and Muthukumar, V. (2020, January 5–8). A-SLIC: Acceleration of SLIC superpixel segmentation algorithm in a co-design framework. Proceedings of the 17th International Conference on Information Technology–New Generations (ITNG 2020), Las Vegas, NV, USA.10.1007/978-3-030-43020-7_90 ↗
20. Ghaderi, A., Ahlberg, C., Östgren, M., Ekstrand, F., and Ekström, M. (September, January 31). Fp-slic: A fully-pipelined fpga implementation of superpixel image segmentation. Proceedings of the 2022 25th Euromicro Conference on Digital System Design (DSD), Maspalomas, Spain.10.1109/DSD57027.2022.00024 ↗
21. An FPGA 2D-convolution unit based on the CAPH language10.1007/s11554-015-0535-1 ↗
22. Aguilar-González, A., and Arias-Estrada, M. (2016, January 22–24). An FPGA stereo matching processor based on the sum of hamming distances. Proceedings of the Applied Reconfigurable Computing: 12th International Symposium, ARC 2016, Mangaratiba, RJ, Brazil. Proceedings 12.
23. Vision meets robotics: The KITTI dataset10.1177/0278364913491297 ↗