We introduce a robust, real-time, high-resolution human video matting method that achieves new state-of-the-art performance. Our method is much lighter than previous approaches and can process 4K at 76 FPS and HD at 104 FPS on an Nvidia GTX 1080Ti GPU. Unlike most existing methods that perform video matting frame-by-frame as independent images, our method uses a recurrent architecture to exploit temporal information in videos and achieves significant improvements in temporal coherence and matting quality. Furthermore, we propose a novel training strategy that enforces our network on both matting and segmentation objectives. This significantly improves our model’s robustness. Our method does not require any auxiliary inputs such as a trimap or a pre-captured background image, so it can be widely applied to existing human matting applications. Our code is available at https://peterl1n.github.io/RobustVideoMatting/

Videos of complex events are difficult to represent solely as bags of low level features. Increasingly, supervised concepts or attributes are being employed as the intermediate representation of such videos. We propose a probabilistic framework that models the conditional relationships between the concepts and events and devise an approximate yet tractable solution to infer the posterior distribution to perform event classification. Using noisy outputs of pre-trained concept detectors, we learn semantic and visual dependencies between event and concept pairs. The co-occurrence between concept pairs is also learned as a marginal over training samples. The proposed method then employs the learned prior, as well as the probabilities of occurrence of specific concepts in a test video to infer the probability of each event using weighted average one-dependence estimation. The evaluation shows that our method improves event classification compared to recent literature on the TRECVID data set.

This paper attempts to address the problem of recognizing human actions while training and testing on distinct datasets, when test videos are neither labeled nor available during training. In this scenario, learning of a joint vocabulary, or domain transfer techniques are not applicable. We first explore reasons for poor classifier performance when tested on novel datasets, and quantify the effect of scene backgrounds on action representations and recognition. Using only the background features and partitioning of gist feature space, we show that the background scenes in recent datasets are quite discriminative and can be used classify an action with reasonable accuracy. We then propose a new process to obtain a measure of confidence in each pixel of the video being a foreground region, using motion, appearance, and saliency together in a 3D MRF based framework. We also propose multiple ways to exploit the foreground confidence: to improve bag-of-words vocabulary, histogram representation of a video, and a novel histogram decomposition based representation and kernel. We used these foreground confidences to recognize actions trained on one data set and test on a different data set. We have performed extensive experiments on several datasets that improve cross dataset recognition accuracy as compared to baseline methods.

We propose to leverage multiple sources of information to compute an estimate of the number of individuals present in an extremely dense crowd visible in a single image. Due to problems including perspective, occlusion, clutter, and few pixels per person, counting by human detection in such images is almost impossible. Instead, our approach relies on multiple sources such as low confidence head detections, repetition of texture elements (using SIFT), and frequency-domain analysis to estimate counts, along with confidence associated with observing individuals, in an image region. Secondly, we employ a global consistency constraint on counts using Markov Random Field. This caters for disparity in counts in local neighborhoods and across scales. We tested our approach on a new dataset of fifty crowd images containing 64K annotated humans, with the head counts ranging from 94 to 4543. This is in stark contrast to datasets used for existing methods which contain not more than tens of individuals. We experimentally demonstrate the efficacy and reliability of the proposed approach by quantifying the counting performance.

This paper proposes a novel representation of articulated human actions and gestures and facial expressions. The main goals of the proposed approach are: 1) to enable recognition using very few examples, i.e., one or k-shot learning, and 2) meaningful organization of unlabeled datasets by unsupervised clustering. Our proposed representation is obtained by automatically discovering high-level subactions or motion primitives, by hierarchical clustering of observed optical flow in four-dimensional, spatial, and motion flow space. The completely unsupervised proposed method, in contrast to state-of-the-art representations like bag of video words, provides a meaningful representation conducive to visual interpretation and textual labeling. Each primitive action depicts an atomic subaction, like directional motion of limb or torso, and is represented by a mixture of four-dimensional Gaussian distributions. For one--shot and k-shot learning, the sequence of primitive labels discovered in a test video are labeled using KL divergence, and can then be represented as a string and matched against similar strings of training videos. The same sequence can also be collapsed into a histogram of primitives or be used to learn a Hidden Markov model to represent classes. We have performed extensive experiments on recognition by one and k-shot learning as well as unsupervised action clustering on six human actions and gesture datasets, a composite dataset, and a database of facial expressions. These experiments confirm the validity and discriminative nature of the proposed representation.

In this paper, we propose a novel method that exploits correlation between audio-visual dynamics of a video to segment and localize objects that are the dominant source of audio. Our approach consists of a two-step spatiotemporal segmentation mechanism that relies on velocity and acceleration of moving objects as visual features. Each frame of the video is segmented into regions based on motion and appearance cues using the QuickShift algorithm, which are then clustered over time using K-means, so as to obtain a spatiotemporal video segmentation. The video is represented by motion features computed over individual segments. The Mel-Frequency Cepstral Coefficients (MFCC) of the audio signal, and their first order derivatives are exploited to represent audio. The proposed framework assumes there is a non-trivial correlation between these audio features and the velocity and acceleration of the moving and sounding objects. The canonical correlation analysis (CCA) is utilized to identify the moving objects which are most correlated to the audio signal. In addition to moving-sounding object identification, the same framework is also exploited to solve the problem of audio-video synchronization, and is used to aid interactive segmentation. We evaluate the performance of our proposed method on challenging videos. Our experiments demonstrate significant increase in performance over the state-of-the-art both qualitatively and quantitatively, and validate the feasibility and superiority of our approach.

This paper proposes a novel method for recognition and classification of events represented by Mixture distributions of location and flow. The main idea is to classify observed events into semantically meaningful groups even when motion is observed from distinct viewpoints. Events in the proposed framework are modeled as motion patterns, which are represented by mixtures of multivariate Gaussians, and are obtained by hierarchical clustering of optical flow in the four dimensional space (x, y, u, v). Such motion patterns observed from varying viewpoints, and in distinct locations or datasets, can be compared using different families of divergences between statistical distributions, given that a transformation between the views is known. One of the major contributions of this paper is to compare and match two motion pattern mixture distributions by estimating the similarity transformation between them, that minimizes their Kullback-Leibler (KL) divergence. The KL divergence between Gaussian mixtures is approximated by Monte Carlo sampling, and the minimization is accomplished by employing an iterative nonlinear least squares estimation method, which bears close resemblance to the Iterative Closest Point (ICP) algorithm. We present a robust framework for matching of high-dimensional, sampled point sets representing statistical distributions, by defining similarity measures between them, for global energy minimization. The proposed approach is tested for classification of events observed across several datasets, captured from both static and moving cameras, involving real world pedestrian as well as vehicular motion. Encouraging results are obtained which demonstrate the feasibility and validity of the proposed approach.

We present a novel method for the discovery and statistical representation of motion patterns in a scene observed by a static camera. Related methods involving learning of patterns of activity rely on trajectories obtained from object detection and tracking systems, which are unreliable in complex scenes of crowded motion. We propose a mixture model representation of salient patterns of optical flow, and present an algorithm for learning these patterns from dense optical flow in a hierarchical, unsupervised fashion. Using low level cues of noisy optical flow, K-means is employed to initialize a Gaussian mixture model for temporally segmented clips of video. The components of this mixture are then filtered and instances of motion patterns are computed using a simple motion model, by linking components across space and time. Motion patterns are then initialized and membership of instances in different motion patterns is established by using KL divergence between mixture distributions of pattern instances. Finally, a pixel level representation of motion patterns is proposed by deriving conditional expectation of optical flow. Results of extensive experiments are presented for multiple surveillance sequences containing numerous patterns involving both pedestrian and vehicular traffic.

We propose a novel method to model and learn the scene activity, observed by a static camera. The proposed model is very general and can be applied for solution of a variety of problems. The motion patterns of objects in the scene are modeled in the form of a multivariate nonparametric probability density function of spatiotemporal variables (object locations and transition times between them). Kernel Density Estimation is used to learn this model in a completely unsupervised fashion. Learning is accomplished by observing the trajectories of objects by a static camera over extended periods of time. It encodes the probabilistic nature of the behavior of moving objects in the scene and is useful for activity analysis applications, such as persistent tracking and anomalous motion detection. In addition, the model also captures salient scene features, such as the areas of occlusion and most likely paths. Once the model is learned, we use a unified Markov Chain Monte Carlo (MCMC)-based framework for generating the most likely paths in the scene, improving foreground detection, persistent labeling of objects during tracking, and deciding whether a given trajectory represents an anomaly to the observed motion patterns. Experiments with real-world videos are reported which validate the proposed approach.