Image superpixel segmentation based on hierarchical multi-level LI-SLIC

Di, Shuanhu; Liao, Miao; Zhao, Yuqian; Li, Yang; Zeng, Ye-zhan

doi:10.1016/j.optlastec.2020.106703

Cited by 25 publications

(10 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, the search range of each superpixel center can be adapted to the image content, but additional superpixels cannot be added in dense regions to improve boundary adherence. Di et al [15] adopted hierarchical multi-level SLIC (Li-SLIC) to adaptively segment texture-sparse and texture-dense regions. Li-SLIC decides whether to perform the segmentation again by evaluating the color standard deviation of each superpixel.…”

Section: Methodsmentioning

confidence: 99%

“…These methods treat pixels as nodes in the graph, and the edge weights between adjacent nodes are proportional to the similarity between the two nodes. Gradient-based algorithms [12,15,16] first obtain coarse segmentation by initial clustering, then iteratively refine the coarse clusters until a convergence condition is satisfied, such as the number of iterations or image quality criteria. This type of method usually starts from an initial seed set and finally assigns a superpixel label to each pixel.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Infrared Image Superpixel Segmentation Based on Seed Strategy of Contour Encoding

Zhang

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

Superpixel segmentation has become a crucial pre-processing tool to reduce computation in many computer vision applications. In this paper, a superpixel extraction algorithm based on a seed strategy of contour encoding (SSCE) for infrared images is presented, which can generate superpixels with high boundary adherence and compactness. Specifically, SSCE can solve the problem of superpixels being unable to self-adapt to the image content. First, a contour encoding map is obtained by ray scanning the binary edge map, which ensures that each connected domain belongs to the same homogeneous region. Second, according to the seed sampling strategy, each seed point can be extracted from the contour encoding map. The initial seed set, which is adaptively scattered based on the local structure, is capable of improving the capability of boundary adherence, especially for small regions. Finally, the initial superpixels limited by the image contour are generated by clustering and refined by merging similar adjacent superpixels in the region adjacency graph (RAG) to reduce redundant superpixels. Experimental results on a self-built infrared dataset and the public datasets BSD500 and 3Dircadb demonstrate the generalization ability in grayscale and medical images, and the superiority of the proposed method over several state-of-the-art methods in terms of accuracy and compactness.

show abstract

Section: Methodsmentioning

confidence: 99%

mentioning

confidence: 99%

Infrared Image Superpixel Segmentation Based on Seed Strategy of Contour Encoding

Zhang

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…erefore, the color intensity, texture, and other characteristics are similar, contained in the superpixels. After the superpixels clustering segmentation of the image, the local consistency of the players can be guaranteed, and the wrong segmentation of the ambiguous pixels on the edge of the players can be effectively avoided [23][24][25].…”

Section: Clustering Segmentation Of Superpixelsmentioning

confidence: 99%

Video Analysis and System Construction of Basketball Game by Lightweight Deep Learning under the Internet of Things

Yang

Jiang

Li³

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

With the explosive growth of sports video data on the internet platform, how to scientifically manage this information has become a major challenge in the current big data era. In this context, a new lightweight player segmentation algorithm is proposed to realize the automatic analysis of basketball game video. Firstly, semantic events are expressed by extracting group and global motion features. A complete basketball game video is divided into three stages, and a basketball event classification method integrating global group motion patterns and domain knowledge is proposed. Secondly, a player segmentation algorithm based on lightweight deep learning is proposed to detect basketball players, segment the players, and finally extract players’ spatial features based on deep learning to realize players’ pose estimation. As the experimental results indicate, when a proposed 2-stage classification algorithm is used to classify the videos, the accuracy of identifying layup, the shooting, and other 2-pointers are improved by 21.26% and 6.41%, respectively. And the accuracy of average events sees an improvement of 2.74%. The results imply that the 2-stage classification based on event-occ is effective. After comparing the four methods of classifying players, it is found that there is no significant difference among these four methods about the accuracy of segmenting. Nevertheless, when judged with the time that these methods take separately, FCN-CNN (Fully Convolutional Network-Convolutional Neural Network) based on superpixels has overwhelming advantages. The event analysis method of basketball game video proposed here can realize the automatic analysis of basketball video, which is beneficial to promoting the rapid development of basketball and even sports.

show abstract

“…Di et al. [16] proposed an ML‐LISLIC algorithm, a hierarchical multi‐level segmentation framework. Based on the simple linear iterative clustering algorithm, multiple discrimination and segmentation of the segmented image be added to increase the accuracy of superpixel segmentation.…”

Section: Introductionmentioning

confidence: 99%

“…Li et al [15] proposed a CONIC algorithm, which introduced contour rating into the non-iterative clustering framework to improve conventional simple non-iterative clustering, to balance segmentation accuracy and visual consistency. Di et al [16] proposed an ML-LISLIC algorithm, a hierarchical multi-level segmentation framework. Based on the simple linear iterative clustering algorithm, multiple discrimination and segmentation of the segmented image be added to increase the accuracy of superpixel segmentation.…”

Section: Introductionmentioning

confidence: 99%

Superpixel segmentation algorithm based on local network modularity increment

Liu

Dai

Guo

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

Superpixel segmentation is a kind of image preprocessing technology and a popular research direction in image processing. The purpose of superpixel segmentation is to reduce the complexity of image processing. The most widely applied Simple Linear Iterative Clustering (SLIC) superpixel segmentation algorithm has high operating efficiency. However, under-segmentation is prone to occur when the number of given superpixel regions is too small. In order to improve the segmentation accuracy, the superpixel segmentation algorithm based on local network modularity increment (LocalNet) from the perspective of network community detection is proposed here. The adjacency network is constructed according to the colour similarity of image pixels, the local community centre is found by the degree of network nodes, and the local network structure of the community is constructed. The modularity increment is employed as the boundary constraint to improve the segmentation accuracy of superpixel segmentation. Through the experimental comparison with the SLIC algorithm, its improved algorithm, and the algorithm proposed in recent years, the results show that our LocalNet algorithm significantly improves in segmentation accuracy Furthermore, the segmentation effect has obvious advantages under the premise that the segmentation speed is not much different from that of the other five algorithms.

show abstract

Image superpixel segmentation based on hierarchical multi-level LI-SLIC

Cited by 25 publications

References 26 publications

Infrared Image Superpixel Segmentation Based on Seed Strategy of Contour Encoding

Infrared Image Superpixel Segmentation Based on Seed Strategy of Contour Encoding

Video Analysis and System Construction of Basketball Game by Lightweight Deep Learning under the Internet of Things

Superpixel segmentation algorithm based on local network modularity increment

Contact Info

Product

Resources

About