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
Patent
09 Nov 1995
TL;DR: In this paper, a motion detection camera system which may be used as a security camera includes an active pixel imaging system operable in a video and differential mode connected to a mode activation circuit that controls the imaging system mode.
Abstract: A motion detection camera system which may be used as a security camera includes an active pixel imaging system operable in a video and differential mode connected to a mode activation circuit that controls the imaging system mode. In the video mode, the imaging system generates an output signal containing information of a viewed area on a frame by frame manner. In the differential mode, the imaging system generates a differential output signal containing information consisting of the differences in the viewed area between adjacent detected frames. Normally, the imaging system camera is operated in the differential mode. If no motion occurs in the viewed area, the corresponding differential output signal representing the interframe differences will have a constant signal level. Upon detecting that the differential output signal deviates by greater than a threshold level indicating motion in the viewed area, the mode activation circuit causes the imaging system to operate in its video mode. The corresponding generated video output signal of the imaging system is then provided to monitoring equipment, such as a video cassette recorder for recording of the motion in the viewed area.

73 citations

Patent
24 Jul 2007
TL;DR: In this paper, the interpolation control module adjusts the frame interpolation operation in response to the analysis of the information associated with one or more frames, in order to select a different type of interpolation, select a video frame prediction mode, or select different threshold values for frame interpolations.
Abstract: In general, this disclosure is directed to decoding techniques for interpolating video frames. In particular, the techniques of this disclosure may be used to dynamically adjust a frame interpolation operation based on analysis of information associated with one or more video frames. In response to the analysis of the information associated with one or more frames, the interpolation control module adjusts the frame interpolation operation in number of different manners. For example, the interpolation control module may dynamically enable or disable motion compensated frame interpolation, select a different type of interpolation, select a video frame prediction mode to be used in the motion compensated frame interpolation, or select different threshold values for frame interpolation.

71 citations

Patent
Caspar Horne1
26 Oct 1994
TL;DR: In this paper, a method and apparatus for use in digital video compression provides improved block-based motion compensation using the global motion of a video frame A video frame comprising a plurality of blocks may be compressed for transmission using block motion vectors Motion vectors are generated by block matching a block to be coded with a block within a reference frame and determining the displacement there between.
Abstract: A novel method and apparatus for use in digital video compression provides improved block-based motion compensation using the global motion of a video frame A video frame comprising a plurality of blocks may be compressed for transmission using block motion vectors Motion vectors are generated by block matching a block to be coded with a block within a reference frame and determining the displacement therebetween To effect block matching, motion compensation techniques define a search window within one or more reference frames within which a displaced block will be found According to the present invention, the location of the search window within a reference frame is defined using the global motion of the frame

71 citations

Journal ArticleDOI
TL;DR: This work proposes a novel and efficient video eye fixation detection model that outperforms all 11 state-of-the-art methods across a number of publicly available datasets by combining the memory Information on the time axis with the motion information on the space axis while storing the saliency information of the current frame.
Abstract: Data-driven saliency detection has attracted strong interest as a result of applying convolutional neural networks to the detection of eye fixations. Although a number of image-based salient object and fixation detection models have been proposed, video fixation detection still requires more exploration. Different from image analysis, motion and temporal information is a crucial factor affecting human attention when viewing video sequences. Although existing models based on local contrast and low-level features have been extensively researched, they failed to simultaneously consider interframe motion and temporal information across neighboring video frames, leading to unsatisfactory performance when handling complex scenes. To this end, we propose a novel and efficient video eye fixation detection model to improve the saliency detection performance. By simulating the memory mechanism and visual attention mechanism of human beings when watching a video, we propose a step-gained fully convolutional network by combining the memory information on the time axis with the motion information on the space axis while storing the saliency information of the current frame. The model is obtained through hierarchical training, which ensures the accuracy of the detection. Extensive experiments in comparison with 11 state-of-the-art methods are carried out, and the results show that our proposed model outperforms all 11 methods across a number of publicly available datasets.

71 citations

Patent
07 Nov 2003
TL;DR: In this paper, the boundary of the target region of a previous frame is projected onto the current frame so that a search area in the current search area can be established, for every pixel in the search area, a search window is established in the previous frame so as to find a matched pixel within the search window.
Abstract: A method and device for tracking a region-of-interest in a sequence of image frames, wherein the boundary of the target region of a previous frame is projected onto the current frame so that a search area in the current frame can be established. For every pixel in the search area in the current frame, a search window is established in the previous frame so as to find a matched pixel within the search window. If the matched pixel is within the ROI of the previous frame, then the corresponding pixel in the current frame is preliminarily considered as a pixel within the ROI of the current frame. This backward matching is carried out using a low pass subband in the wavelet domain. The preliminary ROI in the current frame is then refined using edge detection in a high frequency subband.

71 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