Unsupervised Dynamic Textures Segmentation

Haindl, Michal; Mikeš, Stanislav

doi:10.1007/978-3-642-40261-6_52

Cited by 6 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Algorithms exist that segment smoke and other natural phenomena from general backgrounds [30,31,32,33]. These methods provide various ways to detect areas with dynamic texture based on spatiotemporal filters [30], optical flow motion field [31].…”

Section: Sparse Estimationmentioning

confidence: 99%

Dense Motion Estimation for Smoke

Chen

Hall

2017

Computer Vision – ACCV 2016

View full text Add to dashboard Cite

Abstract. Motion estimation for highly dynamic phenomena such as smoke is an open challenge for Computer Vision. Traditional dense motion estimation algorithms have difficulties with non-rigid and large motions, both of which are frequently observed in smoke motion. We propose an algorithm for dense motion estimation of smoke. Our algorithm is robust, fast, and has better performance over different types of smoke compared to other dense motion estimation algorithms, including state of the art and neural network approaches. The key to our contribution is to use skeletal flow, without explicit point matching, to provide a sparse flow. This sparse flow is upgraded to a dense flow. In this paper we describe our algorithm in greater detail, and provide experimental evidence to support our claims.

show abstract

Section: Sparse Estimationmentioning

confidence: 99%

Dense Motion Estimation for Smoke

Chen

Hall

2017

Computer Vision – ACCV 2016

View full text Add to dashboard Cite

show abstract

“…Generative models have been proposed to directly model image intensities with linear dynamical systems [12,7], then used for segmentation by iterative fitting [4,5]. Most recent works proposed ad hoc, handcrafted descriptors [6,20]. Spatiotemporal filters [15] were proposed early as a way to extract optical flow [22], though the responses to a bank of such oriented filters actually provide much richer information than optical flow.…”

Section: Related Workmentioning

confidence: 99%

Learning similarity metrics for dynamic scene segmentation

Teney

Brown

Kit

et al. 2015

2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

This paper addresses the segmentation of videos with arbitrary motion, including dynamic textures, using novel motion features and a supervised learning approach. Dynamic textures are commonplace in natural scenes, and exhibit complex patterns of appearance and motion (e.g. water, smoke, swaying foliage). These are difficult for existing segmentation algorithms, often violate the brightness constancy assumption needed for optical flow, and have complex segment characteristics beyond uniform appearance or motion. Our solution uses custom spatiotemporal filters that capture texture and motion cues, along with a novel metric-learning framework that optimizes this representation for specific objects and scenes. This is used within a hierarchical, graph-based segmentation setting, yielding state-of-the-art results for dynamic texture segmentation. We also demonstrate the applicability of our approach to general object and motion segmentation, showing significant improvements over unsupervised segmentation and results comparable to the best task specific approaches.

show abstract

Dynamic Texture Feature Extraction Based on multi-scale Convolutional Autoencoder

Zhu

2021

2021 4th International Conference on Intelligent Autonomous Systems (ICoIAS)

View full text Add to dashboard Cite

Unsupervised Dynamic Textures Segmentation

Cited by 6 publications

References 16 publications

Dense Motion Estimation for Smoke

Dense Motion Estimation for Smoke

Learning similarity metrics for dynamic scene segmentation

Dynamic Texture Feature Extraction Based on multi-scale Convolutional Autoencoder

Contact Info

Product

Resources

About