A Structured Model of Video Reproduces Primary Visual Cortical Organisation

The visual system must learn to infer the presence of objects and features in the world from the images it encounters, and as such it must, either implicitly or explicitly, model the way these elements interact to create the image. Do the response properties of cells in the mammalian visual system reflect this constraint? To address this question, we constructed a probabilistic model in which the identity and attributes of simple visual elements were represented explicitly and learnt the parameters of this model from unparsed, natural video sequences. After learning, the behaviour and grouping of variables in the probabilistic model corresponded closely to functional and anatomical properties of simple and complex cells in the primary visual cortex (V1). In particular, feature identity variables were activated in a way that resembled the activity of complex cells, while feature attribute variables responded much like simple cells. Furthermore, the grouping of the attributes within the model closely parallelled the reported anatomical grouping of simple cells in cat V1. Thus, this generative model makes explicit an interpretation of complex and simple cells as elements in the segmentation of a visual scene into basic independent features, along with a parametrisation of their moment-by-moment appearances. We speculate that such a segmentation may form the initial stage of a hierarchical system that progressively separates the identity and appearance of more articulated visual elements, culminating in view-invariant object recognition.

Video segmentation with superpixels

Due to its importance, video segmentation has regained interest recently. However, there is no common agreement about the necessary ingredients for best performance. This work contributes a thorough analysis of various within- and between-frame affinities suitable for video segmentation. Our results show that a frame-based superpixel segmentation combined with a few motion and appearance-based affinities are sufficient to obtain good video segmentation performance. A second contribution of the paper is the extension of [1] to include motion-cues, which makes the algorithm globally aware of motion, thus improving its performance for video sequences. Finally, we contribute an extension of an established image segmentation benchmark [1] to videos, allowing coarse-to-fine video segmentations and multiple human annotations. Our results are tested on BMDS [2], and compared to existing methods. © 2013 Springer-Verlag.

Warping trajectories for video synchronization

Temporal synchronization of multiple video recordings of the same dynamic event is a critical task in many computer vision applications e.g. novel view synthesis and 3D reconstruction. Typically this information is implied, since recordings are made using the same timebase, or time-stamp information is embedded in the video streams. Recordings using consumer grade equipment do not contain this information; hence, there is a need to temporally synchronize signals using the visual information itself. Previous work in this area has either assumed good quality data with relatively simple dynamic content or the availability of precise camera geometry. In this paper, we propose a technique which exploits feature trajectories across views in a novel way, and specifically targets the kind of complex content found in consumer generated sports recordings, without assuming precise knowledge of fundamental matrices or homographies. Our method automatically selects the moving feature points in the two unsynchronized videos whose 2D trajectories can be best related, thereby helping to infer the synchronization index. We evaluate performance using a number of real recordings and show that synchronization can be achieved to within 1 sec, which is better than previous approaches. Copyright 2013 ACM.

MoT - Mixture of trees probabilistic graphical model for video segmentation

We present a novel mixture of trees (MoT) graphical model for video segmentation. Each component in this mixture represents a tree structured temporal linkage between super-pixels from the first to the last frame of a video sequence. Our time-series model explicitly captures the uncertainty in temporal linkage between adjacent frames which improves segmentation accuracy. We provide a variational inference scheme for this model to estimate super-pixel labels and their confidences in nearly realtime. The efficacy of our approach is demonstrated via quantitative comparisons on the challenging SegTrack joint segmentation and tracking dataset [23].

A new half-flash architecture for high speed video ADC

In this paper a new half-flash architecture for high speed video ADC is presented. Based on a high speed single-way analog switch circuit, this architecture effectively reduces the number of elements. At the same lime no sacrifice of speed is needed compared with the normal half-flash structure.

Non-goal scene analysis for soccer video

The broadcast soccer video is usually recorded by one main camera, which is constantly gazing somewhere of playfield where a highlight event is happening. So the camera parameters and their variety have close relationship with semantic information of soccer video, and much interest has been caught in camera calibration for soccer video. The previous calibration methods either deal with goal scene, or have strict calibration conditions and high complexity. So, it does not properly handle the non-goal scene such as midfield or center-forward scene. In this paper, based on a new soccer field model, a field symbol extraction algorithm is proposed to extract the calibration information. Then a two-stage calibration approach is developed which can calibrate camera not only for goal scene but also for non-goal scene. The preliminary experimental results demonstrate its robustness and accuracy. (c) 2010 Elsevier B.V. All rights reserved.

A Video Quality Assessment Metric Based on Human Visual System

It is important for practical application to design an effective and efficient metric for video quality. The most reliable way is by subjective evaluation. Thus, to design an objective metric by simulating human visual system (HVS) is quite reasonable and available. In this paper, the video quality assessment metric based on visual perception is proposed. Three-dimensional wavelet is utilized to decompose video and then extract features to mimic the multichannel structure of HVS. Spatio-temporal contrast sensitivity function (S-T CSF) is employed to weight coefficient obtained by three-dimensional wavelet to simulate nonlinearity feature of the human eyes. Perceptual threshold is exploited to obtain visual sensitive coefficients after S-T CSF filtered. Visual sensitive coefficients are normalized representation and then visual sensitive errors are calculated between reference and distorted video. Finally, temporal perceptual mechanism is applied to count values of video quality for reducing computational cost. Experimental results prove the proposed method outperforms the most existing methods and is comparable to LHS and PVQM.

Biologically Inspired Features for Scene Classification in Video Surveillance

Inspired by human visual cognition mechanism, this paper first presents a scene classification method based on an improved standard model feature. Compared with state-of-the-art efforts in scene classification, the newly proposed method is more robust, more selective, and of lower complexity. These advantages are demonstrated by two sets of experiments on both our own database and standard public ones. Furthermore, occlusion and disorder problems in scene classification in video surveillance are also first studied in this paper.