Superpixels by Bilateral Geodesic Distance

Zhou, Yuanfeng; Pan, Xiao; Wang, Wenping; Yin, Yilong; Zhang, Caiming

doi:10.1109/tcsvt.2016.2589781

Cited by 15 publications

(13 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Superpixel generated by different methods with 500 clusters: (a) original image; (b) our method; (c) BGD [ZPW*16]; (d) SLIC [ASS*12]; (e) Turbopixels [LSK*09]; (f) VCells [WW12]; (g) LRW [SDWL14]; (h) MSLIC [LYYH16]; (i) LSC [LC15]; (j) GGM [CG16]; (k) DBSCAN [SHL*16]; (l) IMSLIC [LYLH18]. The last row shows the magnified details in sequence.…”

Section: Methodsmentioning

confidence: 99%

“…Comparisons with Turbopixels [LSK*09], LRW [SDWL14], SLIC [ASS*12], VCells [WW12], DBSCAN [SHL*16], BGD [ZPW*16], MSLIC [LYYH16], IMSLIC [LYLH18], LSC [LC15] and GGM [CG16] on the BSDS500 benchmark: (a) boundary recall; (b) achievable segmentation accuracy; (c) under‐segmentation error.…”

Section: Methodsmentioning

confidence: 99%

“…Based on this, Zhou et al . [ZPW*16, PZLZ17] proposed a bilateral geodesic distance (BGD) to improve the boundary adherence at weak boundaries, and we refer it as BGD. Shen et al .…”

Section: Related Workmentioning

confidence: 99%

“…In this paper, we measure the similarity of pixels from two aspects: colour homogeneity and spatial compactness. In some previous algorithms [WZG*13, ZPW*16], instead of using traditional Euclidean distance, they presented a measure called geodesic distance to improve the segmentation results. Some other algorithms [LC15] calculated the similarity in a 10‐dimensional feature space combining colours and coordinates.…”

Section: Agglomerative Clustering With Quadratic Error Minimizationmentioning

confidence: 99%

See 3 more Smart Citations

Superpixel Generation by Agglomerative Clustering With Quadratic Error Minimization

Dong

Chen

Yao

et al. 2018

Computer Graphics Forum

View full text Add to dashboard Cite

Superpixel segmentation is a popular image pre‐processing technique in many computer vision applications. In this paper, we present a novel superpixel generation algorithm by agglomerative clustering with quadratic error minimization. We use a quadratic error metric (QEM) to measure the difference of spatial compactness and colour homogeneity between superpixels. Based on the quadratic function, we propose a bottom‐up greedy clustering algorithm to obtain higher quality superpixel segmentation. There are two steps in our algorithm: merging and swapping. First, we calculate the merging cost of two superpixels and iteratively merge the pair with the minimum cost until the termination condition is satisfied. Then, we optimize the boundary of superpixels by swapping pixels according to their swapping cost to improve the compactness. Due to the quadratic nature of the energy function, each of these atomic operations has only O(1) time complexity. We compare the new method with other state‐of‐the‐art superpixel generation algorithms on two datasets, and our algorithm demonstrates superior performance.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

“…Based on this, Zhou et al . [ZPW*16, PZLZ17] proposed a bilateral geodesic distance (BGD) to improve the boundary adherence at weak boundaries, and we refer it as BGD. Shen et al .…”

Section: Related Workmentioning

confidence: 99%

Section: Agglomerative Clustering With Quadratic Error Minimizationmentioning

confidence: 99%

See 2 more Smart Citations

Superpixel Generation by Agglomerative Clustering With Quadratic Error Minimization

Dong

Chen

Yao

et al. 2018

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…The first class is based on clustering, such as SLIC [1], LSC [4], DBSCAN [28], Turbopixel [11], SEEDS [32], SSBC [39], SBGD [41] and HEWCVT [40]. This class takes superpixels as clusters of pixels.…”

Section: Related Workmentioning

confidence: 99%

Weighted superpixel segmentation

Qian¹,

Zhang

2019

Vis Comput

Self Cite

View full text Add to dashboard Cite

Image boundaries and regularity are two important factors in superpixel segmentation. Balancing the influence of image boundaries and regularity is key to producing superpixels. In this paper, we present a novel superpixel segmentation algorithm, called weighted superpixel segmentation (WSS), which is capable of generating superpixels with high boundary adherence and regular shape in a linear time. In WSS, superpixels are generated according to a distance metric defined by the combination of a weight function term, color distance term and plane distance term. Unlike other superpixel algorithms, the weight function is calculated for each pixel to determine the weight of the color distance term and plane distance term in the distance metric. To increase superpixel regularity, superpixel seeds are initialized in a hexagonal manner. Then, we use the distance metric to obtain the initial superpixels. Determining the seed search range is an essential factor to improve algorithm accuracy; thus, a dynamic circle search range is designed in our algorithm that can provide better superpixel results. Finally, a merging strategy is applied to obtain the final superpixels and ensure that the number of superpixels agrees with expectations. Experimental results demonstrate that WSS performs as well as or even better than the existing methods in terms of several commonly used evaluation metrics in superpixel segmentation.

show abstract

Simultaneous segmentation and correction model for color medical and natural images with intensity inhomogeneity

Yang

Jia

2019

Vis Comput

View full text Add to dashboard Cite

Superpixels by Bilateral Geodesic Distance

Cited by 15 publications

References 35 publications

Superpixel Generation by Agglomerative Clustering With Quadratic Error Minimization

Superpixel Generation by Agglomerative Clustering With Quadratic Error Minimization

Weighted superpixel segmentation

Simultaneous segmentation and correction model for color medical and natural images with intensity inhomogeneity

Contact Info

Product

Resources

About