Janusz Konrad

Changedetection.net: A new change detection benchmark dataset

Change detection is one of the most commonly encountered low-level tasks in computer vision and video processing. A plethora of algorithms have been developed to date, yet no widely accepted, realistic, large-scale video dataset exists for benchmarking different methods. Presented here is a unique change detection benchmark dataset consisting of nearly 90,000 frames in 31 video sequences representing 6 categories selected to cover a wide range of challenges in 2 modalities (color and thermal IR). A distinguishing characteristic of this dataset is that each frame is meticulously annotated for ground-truth foreground, background, and shadow area boundaries - an effort that goes much beyond a simple binary label denoting the presence of change. This enables objective and precise quantitative comparison and ranking of change detection algorithms. This paper presents and discusses various aspects of the new dataset, quantitative performance metrics used, and comparative results for over a dozen previous and new change detection algorithms. The dataset, evaluation tools, and algorithm rankings are available to the public on a website1 and will be updated with feedback from academia and industry in the future.

Efficient, robust, and fast global motion estimation for video coding

In this paper, we propose an efficient, robust, and fast method for the estimation of global motion from image sequences. The method is generic in that it can accommodate various global motion models, from a simple translation to an eight-parameter perspective model. The algorithm is hierarchical and consists of three stages. In the first stage, a low-pass image pyramid is built. Then, an initial translation is estimated with full-pixel precision at the top of the pyramid using a modified n-step search matching. In the third stage, a gradient descent is executed at each level of the pyramid starting from the initial translation at the coarsest level. Due to the coarse initial estimation and the hierarchical implementation, the method is very fast. To increase robustness to outliers, we replace the usual formulation based on a quadratic error criterion with a truncated quadratic function. We have applied the algorithm to various test sequences within an MPEG-4 coding system. From the experimental results we conclude that global motion estimation provides significant performance gains for video material with camera zoom and/or pan. The gains result from a reduced prediction error and a more compact representation of motion. We also conclude that the robust error criterion can introduce additional performance gains without increasing computational complexity.

Estimating motion in image sequences

We have reviewed the estimation of 2D motion from time-varying images, paying particular attention to the underlying models, estimation criteria, and optimization strategies. Several parametric and nonparametric models for the representation of motion vector fields and motion trajectory fields have been discussed. For a given region of support, these models determine the dimensionality of the estimation problem as well as the amount of data that has to be interpreted or transmitted thereafter. Also, the interdependence of motion and image data has been addressed. We have shown that even ideal constraints may not provide a well-defined estimation criterion. Therefore, the data term of an estimation criterion is usually supplemented with a smoothness term that can be expressed explicitly or implicitly via a constraining motion model. We have paid particular attention to the statistical criteria based on Markov random fields. Because the optimization of an estimation criterion typically involves a large number of unknowns, we have presented several fast search strategies.

Bayesian estimation of motion vector fields

A stochastic approach to the estimation of 2D motion vector fields from time-varying images is presented. The formulation involves the specification of a deterministic structural model along with stochastic observation and motion field models. Two motion models are proposed: a globally smooth model based on vector Markov random fields and a piecewise smooth model derived from coupled vector-binary Markov random fields. Two estimation criteria are studied. In the maximum a posteriori probability (MAP) estimation, the a posteriori probability of motion given data is maximized, whereas in the minimum expected cost (MEC) estimation, the expectation of a certain cost function is minimized. Both algorithms generate sample fields by means of stochastic relaxation implemented via the Gibbs sampler. Two versions are developed: one for a discrete state space and the other for a continuous state space. The MAP estimation is incorporated into a hierarchical environment to deal efficiently with large displacements. >

CDnet 2014: An Expanded Change Detection Benchmark Dataset

Change detection is one of the most important lowlevel tasks in video analytics. In 2012, we introduced the changedetection.net (CDnet) benchmark, a video dataset devoted to the evalaution of change and motion detection approaches. Here, we present the latest release of the CDnet dataset, which includes 22 additional videos (70; 000 pixel-wise annotated frames) spanning 5 new categories that incorporate challenges encountered in many surveillance settings. We describe these categories in detail and provide an overview of the results of more than a dozen methods submitted to the IEEE Change DetectionWorkshop 2014. We highlight strengths and weaknesses of these methods and identify remaining issues in change detection.

Probabilistic video stabilization using Kalman filtering and mosaicking

The removal of unwanted, parasitic vibrations in a video sequence induced by camera motion is an essential part of video acquisition in industrial, military and consumer applications. In this paper, we present a new image processing method to remove such vibrations and reconstruct a video sequence void of sudden camera movements. Our approach to separating unwanted vibrations from intentional camera motion is based on a probabilistic estimation framework. We treat estimated parameters of interframe camera motion as noisy observations of the intentional camera motion parameters. We construct a physics-based state-space model of these interframe motion parameters and use recursive Kalman filtering to perform stabilized camera position estimation. A six-parameter affine model is used to describe the interframe transformation, allowing quite accurate description of typical scene changes due to camera motion. The model parameters are estimated using a p-norm-based multi-resolution approach. This approach is robust to model mismatch and to object motion within the scene (which are treated as outliers). We use mosaicking in order to reconstruct undefined areas that result from motion compensation applied to each video frame. Registration between distant frames is performed efficiently by cascading interframe affine transformation parameters. We compare our methods performance with that of a commercial product on real-life video sequences, and show a significant improvement in stabilization quality for our method.

Action Recognition Using Sparse Representation on Covariance Manifolds of Optical Flow

A novel approach to action recognition in video based onthe analysis of optical flow is presented. Properties of opticalflow useful for action recognition are captured usingonly the empirical covariance matrix of a bag of featuressuch as flow velocity, gradient, and divergence. The featurecovariance matrix is a low-dimensional representationof video dynamics that belongs to a Riemannian manifold.The Riemannian manifold of covariance matrices is transformedinto the vector space of symmetric matrices underthe matrix logarithm mapping. The log-covariance matrixof a test action segment is approximated by a sparse linearcombination of the log-covariance matrices of training actionsegments using a linear program and the coefficients ofthe sparse linear representation are used to recognize actions.This approach based on the unique blend of a logcovariance-descriptor and a sparse linear representation istested on the Weizmann and KTH datasets. The proposedapproach attains leave-one-out cross validation scores of94.4% correct classification rate for the Weizmann datasetand 98.5% for the KTH dataset. Furthermore, the methodis computationally efficient and easy to implement.

Foreground-Adaptive Background Subtraction

Background subtraction is a powerful mechanism for detecting change in a sequence of images that finds many applications. The most successful background subtraction methods apply probabilistic models to background intensities evolving in time; nonparametric and mixture-of-Gaussians models are but two examples. The main difficulty in designing a robust background subtraction algorithm is the selection of a detection threshold. In this paper, we adapt this threshold to varying video statistics by means of two statistical models. In addition to a nonparametric background model, we introduce a foreground model based on small spatial neighborhood to improve discrimination sensitivity. We also apply a Markov model to change labels to improve spatial coherence of the detections. The proposed methodology is applicable to other background models as well.

3-D Displays and Signal Processing

In this article, main electronic 3-D display technologies from a signal processing perspective are overviewed. And the underlying physics, benefits, deficiencies of various displays are described. The general role of signal processing and provide specific examples of signal processing helping address certain display deficiencies are discussed. Challenges awaiting signal processing in quest of the ultimate 3-D experience is highlighted.

A gesture-driven computer interface using Kinect

Automatic recognition of human actions from video has been studied for many years. Although still very difficult in uncontrolled scenarios, it has been successful in more restricted settings (e.g., fixed viewpoint, no occlusions) with recognition rates approaching 100%. However, the best-performing methods are complex and computationally-demanding and thus not well-suited for real-time deployments. This paper proposes to leverage the Kinect camera for close-range gesture recognition using two methods. Both methods use feature vectors that are derived from the skeleton model provided by the Kinect SDK in real-time. Although both methods perform nearest-neighbor classification, one method does this in the space of features using the Euclidean distance metric, while the other method does this in the space of feature covariances using a log-Euclidean metric. Both methods recognize 8 hand gestures in real time achieving correct-classification rates of over 99% on a dataset of 20 subjects but the method based on Euclidean distance requires feature-vector collections to be of the same size, is sensitive to temporal misalignment, and has higher computation and storage requirements.