000177415 001__ 177415 000177415 005__ 20181203022726.0 000177415 0247_ $$2doi$$a10.1109/TPAMI.2012.120 000177415 022__ $$a0162-8828 000177415 02470 $$2ISI$$a000308755000017 000177415 037__ $$aARTICLE 000177415 245__ $$aSLIC Superpixels Compared to State-of-the-art Superpixel Methods 000177415 269__ $$a2012 000177415 260__ $$aLos Alamitos$$bInstitute of Electrical and Electronics Engineers$$c2012 000177415 300__ $$a8 000177415 336__ $$aJournal Articles 000177415 500__ $$aA previous version of this article was published as a EPFL Technical Report in 2010: https://infoscience.epfl.ch/record/149300. Supplementary material can be found at: http://ivrg.epfl.ch/research/superpixels 000177415 520__ $$aComputer vision applications have come to rely increasingly on superpixels in recent years, but it is not always clear what constitutes a good superpixel algorithm. In an effort to understand the benefits and drawbacks of existing methods, we empirically compare five state-of-the-art superpixel algorithms for their ability to adhere to image boundaries, speed, memory efficiency, and their impact on segmentation performance. We then introduce a new superpixel algorithm, simple linear iterative clustering (SLIC), which adapts a k-means clustering approach to efficiently generate superpixels. Despite its simplicity, SLIC adheres to boundaries as well as or better than previous methods. At the same time, it is faster and more memory efficient, improves segmentation performance, and is straightforward to extend to supervoxel generation. 000177415 6531_ $$aSuperpixels 000177415 6531_ $$aSegmentation 000177415 6531_ $$aClustering 000177415 6531_ $$ak-means 000177415 6531_ $$aNCCR-MICS/EMSP 000177415 6531_ $$aNCCR-MICS 000177415 700__ $$0242495$$aAchanta, Radhakrishna$$g172126 000177415 700__ $$0245251$$aShaji, Appu$$g188751 000177415 700__ $$0242712$$aSmith, Kevin$$g163328 000177415 700__ $$0242715$$aLucchi, Aurélien$$g185205 000177415 700__ $$0240252$$aFua, Pascal$$g112366 000177415 700__ $$0241946$$aSüsstrunk, Sabine$$g125681 000177415 773__ $$j34$$k11$$q2274 - 2282$$tIEEE Transactions on Pattern Analysis and Machine Intelligence 000177415 8564_ $$uhttp://ivrg.epfl.ch/research/superpixels$$zURL 000177415 8564_ $$s8910790$$uhttps://infoscience.epfl.ch/record/177415/files/Superpixel_PAMI2011-2.pdf$$yn/a$$zn/a 000177415 909C0 $$0252320$$pIVRL$$xU10429 000177415 909C0 $$0252087$$pCVLAB$$xU10659 000177415 909CO $$ooai:infoscience.tind.io:177415$$pIC$$particle 000177415 917Z8 $$x125681 000177415 917Z8 $$x125681 000177415 917Z8 $$x125681 000177415 937__ $$aEPFL-ARTICLE-177415 000177415 973__ $$aEPFL$$rREVIEWED$$sPUBLISHED 000177415 980__ $$aARTICLE