A novel optical flow-based representation for temporal video segmentation

Download
2017-01-01
Akpınar, Samet
Alpaslan, Ferda Nur
Temporal video segmentation is a field of multimedia research enabling us to temporally split video data into semantically coherent scenes. In order to develop methods challenging temporal video segmentation, detecting scene boundaries is one of the more widely used approaches. As a result, representation of temporal information becomes important. We propose a new temporal video segment representation to formalize video scenes as a sequence of temporal motion change information. The idea here is that some sort of change in the optical flow character determines motion change and cuts between consecutive scenes. The problem is eventually reduced to an optical flow-based cut detection problem from which the average motion vector concept is put forward. This concept is used for proposing a pixel-based representation enriched with a novel motion-based approach. Temporal video segment points are classified as cuts and noncuts according to the proposed video segment representation. Consequently, the proposed method and representation is applied to benchmark data sets and the results are compared to other state-of-the art methods.
TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES

Suggestions

A Graph-Based Approach for Video Scene Detection
Sakarya, Ufuk; Telatar, Zjya (2008-04-22)
In this paper, a graph-based method for video scene detection is proposed. The method is based on a weighted undirected graph. Each shot is a vertex on the graph. Edge weights among the vertices are evaluated by using spatial and temporal similarities of shots. By using the complete information of the graph, a set of the vertices mostly similar to each other and dissimilar to the others is detected. Temporal continuity constraint is achieved on this set. This set is the first detected video scene. The verti...
A modular scheme for 2D/3D conversion of TV broadcast
Knorr, Sebastian; Imre, Evren; Oezkalayci, Burak; Alatan, Abdullah Aydın; Sikora, Thomas (2006-06-16)
The 3D reconstruction from 2D broadcast video is a challenging problem with many potential applications, such as 3DTV, free-viewpoint video or augmented reality. In this paper, a modular system capable of efficiently reconstructing 3D scenes from broadcast video is proposed. The system consists of four constitutive modules: tracking and segmentation, self-calibration, sparse reconstruction and, finally, dense reconstruction. This paper also introduces some novel approaches for moving object segmentation and...
Summarizing video: Content, features, and HMM topologies
Yasaroglu, Y; Alatan, Abdullah Aydın (2003-01-01)
An algorithm is proposed for automatic summarization of multimedia content by segmenting digital video into semantic scenes using HMMs. Various multi-modal low-level features are extracted to determine state transitions in HMMs for summarization. Advantage of using different model topologies and observation sets in order to segment different content types is emphasized and verified by simulations. Performance of the proposed algorithm is also compared with a deterministic scene segmentation method. A better...
Recursive Prediction for Joint Spatial and Temporal Prediction in Video Coding
Kamışlı, Fatih (2014-06-01)
Video compression systems use prediction to reduce redundancies present in video sequences along the temporal and spatial dimensions. Standard video coding systems use either temporal or spatial prediction on a per block basis. If temporal prediction is used, spatial information is ignored. If spatial prediction is used, temporal information is ignored. This may be a computationally efficient approach, but it does not effectively combine temporal and spatial information. In this letter, we provide a framewo...
An embedding technique to determine tau tau backgrounds in proton-proton collision data
Sirunyan, A. M.; et. al. (IOP Publishing, 2019-06-01)
An embedding technique is presented to estimate standard model ττ backgrounds from data with minimal simulation input. In the data, the muons are removed from reconstructed μμ events and replaced with simulated tau leptons with the same kinematic properties. In this way, a set of hybrid events is obtained that does not rely on simulation except for the decay of the tau leptons. The challenges in describing the underlying event or the production of associated jets in the simulation are avoided. The technique...
Citation Formats
S. Akpınar and F. N. Alpaslan, “A novel optical flow-based representation for temporal video segmentation,” TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, pp. 3983–3993, 2017, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/33193.