scispace - formally typeset
Search or ask a question
Topic

Inter frame

About: Inter frame is a research topic. Over the lifetime, 4154 publications have been published within this topic receiving 63549 citations.


Papers
More filters
Journal ArticleDOI
TL;DR: A novel method for virtual focus and object depth estimation from defocused video captured by a moving camera that can be utilized to correct out-of-focus video sequences and can potentially replace the expensive apparatus required for auto-focus adjustments currently employed in many camera devices.
Abstract: In this paper, we present a novel method for virtual focus and object depth estimation from defocused video captured by a moving camera. We use the term virtual focus to refer to a new approach for producing in-focus image sequences by processing blurred videos captured by out-of-focus cameras. Our method relies on the concept of Depth-from-Defocus (DFD) for virtual focus estimation. However, the proposed approach overcomes limitations of DFD by reformulating the problem in a moving-camera scenario. We introduce the interframe image motion model, from which the relationship between the camera motion and blur characteristics can be formed. This relationship subsequently leads to a new method for blur estimation. We finally rely on the blur estimation to develop the proposed technique for object depth estimation and focused video reconstruction. The proposed approach can be utilized to correct out-of-focus video sequences and can potentially replace the expensive apparatus required for auto-focus adjustments currently employed in many camera devices. The performance of the proposed algorithm is demonstrated through error analysis and computer simulated experiments.

27 citations

Proceedings ArticleDOI
12 Nov 2007
TL;DR: Experimental results verify that the proposed algorithm can greatly increase the speed of prediction with negligible loss of coding efficiency.
Abstract: The multi-view video coding improves the coding efficiency by utilizing motion-compensated prediction (MCP) and disparity-compensated prediction (DCP). However, the complexity of the inter frame prediction is very high, especially when the rate-distortion optimization is used. This paper presents a fast inter frame prediction algorithm to reduce the complexity. Firstly the prediction type is decided according to reference frames. Then some unuseful search regions in view direction are removed. Finally a fast inter mode decision strategy is proposed based on the relationship between MCP and DCP. Experimental results verify that the proposed algorithm can greatly increase the speed of prediction with negligible loss of coding efficiency.

27 citations

Patent
Zhun Zhong1
11 Apr 2001
TL;DR: In this article, a motion compensation predictor is adapted to determine a likely local nature of a reference frame data area in the video data stream and then apply proper interpolation to the reference-frame data area according to the determined likelihood of local nature.
Abstract: The present invention can complement and benefit virtually any method utilizing motion compensation to decode an inputted digital video data stream by determining a likely local nature of reference frame data area in the video data stream and then applying proper interpolation to the reference frame data area according to the determined likely local nature of the reference frame data area. The present invention can also complement and benefit virtually any decoding system utilizing motion compensation to decode an inputted digital video data stream by providing a motion compensation predictor that is adapted to determine a likely local nature of a reference frame data area in the video data stream and then apply proper interpolation to the reference frame data area according to the determined likely local nature of the reference frame data area.

27 citations

Proceedings ArticleDOI
01 Nov 1998
TL;DR: A frame rate control scheme is proposed which can dynamically adjust the number of skipped frames according to the accumulated magnitude of motion vectors, and the decoded sequence can present much smoother motion.
Abstract: This paper investigates the dynamic frame-skipping strategy in video transcoding. To speed up the operation, a video transcoder usually reuses the decoded motion vectors to reencode the video sequences at a lower bit-rate. When frame-skipping is allowed in a transcoder, those motion vectors can not be reused because the motion vectors of the current frame is no longer estimated from the immediate past frame. To reduce the computational complexity of motion vectors re-estimation, a bilinear interpolation approach is developed to overcome this problem. Based on these interpolated motion vectors, the search range can be much reduced. Furthermore, we propose a frame rate control scheme which can dynamically adjust the number of skipped frames according to the accumulated magnitude of motion vectors. As a result, the decoded sequence can present much smoother motion.

27 citations

Proceedings Article
01 Dec 2012
TL;DR: A CU splitting early termination scheme for inter frame coding that achieves up to 34.83% total encoding time reduction with less than 0.25% BD-rate increase on average is proposed.
Abstract: The emerging high-efficiency video coding (HEVC) standard employs a new coding structure characterized by coding unit (CU), prediction unit (PU) and transform unit (TU) It improves the coding efficiency significantly, but also introduces great computation complexity on the decision of optimal CU, PU and TU sizes To reduce the encoding complexity, we propose a CU splitting early termination scheme for inter frame coding In the proposed scheme, the characteristics of prediction residuals are utilized to early terminate the CU splitting Specifically, the Mean Square Error (MSE) between the prediction block and the origin block for each CU level is obtained and then compared with an adaptive threshold The recursive CU splitting process is early terminated according to the threshold Experimental results demonstrate that, the proposed algorithm achieves up to 3483% total encoding time reduction with less than 025% BD-rate increase on average

26 citations


Network Information
Related Topics (5)
Feature (computer vision)
128.2K papers, 1.7M citations
86% related
Feature extraction
111.8K papers, 2.1M citations
86% related
Image segmentation
79.6K papers, 1.8M citations
86% related
Convolutional neural network
74.7K papers, 2M citations
83% related
Image processing
229.9K papers, 3.5M citations
82% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
202324
202272
202162
202084
2019110
201897