High-dimensional features of adaptive superpixels for visually degraded images

Abstract

This study presents a novel and highly efficient superpixel algorithm, namely, depth-fused adaptive superpixel (DFASP), which can generate accurate superpixels in a degraded image. In many applications, particularly in actual scenes, vision degradation, such as motion blur, overexposure, and underexposure, often occurs. Well-known color-based superpixel algorithms are incapable of producing accurate superpixels in degraded images because of the ambiguity of color information caused by vision degradation. To eliminate this ambiguity, we use depth and color information to generate superpixels. We map the depth and color information to a high-dimensional feature space. Then, we develop a fast multilevel clustering algorithm to produce superpixels. Furthermore, we design an adaptive mechanism to adjust the color and depth information automatically during pixel clustering. Experimental results demonstrate that regardless of boundary recall, under segmentation error, run time, or achievable segmentation accuracy, DFASP is better than state-of-the-art superpixel methods.

References

[1] RadhakrishnaA, SusstrunkS. Superpixels and Polygons Using Simple Non-iterative Clustering, 2017 IEEE Conference on Computer Vision and Pattern Rec ognition (CVPR), 2017,

[2] GiordanoD, MurabitoF, PalazzoS, SpampinatoC. Superpixel-based Video Object Segmentation Using Perceptual Organization and Location Prior, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015,

[3] Liang X., Shen X., Feng J., Lin L. and Yan S., Semantic Object Parsing with Graph LSTM, European Conference on Computer Vision, 125 (2016).

[4] D YeoD, SonJ, HanB, HanJ H. Super-pixel-based Tracking-by-Segmentation Using Markov Chains, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017,

[5] YoubaoT, WuX. Saliency Detection via Combining Region-level and Pixel-level Predictions with CNNs, 2016, Springer, Cham, European Conference on Computer Vision

[6] StutzD, HermansA, LeibeB. Superpixels: An Evaluation of the State-of-the-Art, Computer Vision and Image Understanding, 2017,

[7] LiuM Y, TuzelO, RamalingamS, ChellappaR. Entropy Rate Superpixel Segmentation, 2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011,

[8] Van den BerghM, BoixX, RoigG, de CapitaniB, Van GoolS. Superpixels Extracted via Energy-driven Sampling, 2012, Springer, Berlin, Heidelberg, European Conference on Computer Vision

[9] ShajiA, SmithK, LucchiA, FuaP, Susstrunk. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34: 2274

[10] RadhakrishnaA, SusstrunkS. Superpixels and Polygons Using Simple Non-iterative Clustering, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017,

[11] JampaniV, SunD, Ming-YuL, Ming-HsuanY, KautzJ. Superpixel Sampling Networks, European Conference on Computer Vision, 2018,

[12] Dhillon, JS, GuanY, KulisB. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2007, 29: 1944

[13] ZhengqinL, ChenJ. Superpixel Segmentation Using Linear Spectral Clustering, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015,

[14] Shi Jianbo and Jitendra Malik, Normalized Cuts and Image Segmentation, Departmental Papers (CIS), 107 (2000).

[15] SilbermanN, HoiemD, KohliP, FergusR. Indoor Segmentation and Support Inference from RGBD Images, 2012, Berlin, Heidelberg, European Conference on Computer Vision Springer