Jagannadan Varadarajan

Topic models for scene analysis and abnormality detection

Automatic analysis and understanding of common activities and detection of deviant behaviors is a challenging task in computer vision. This is particularly true in surveillance data, where busy traffic scenes are rich with multifarious activities many of them occurring simultaneously. In this paper, we address these issues with an unsupervised learning approach relying on probabilistic Latent Semantic Analysis (pLSA) applied to a rich set visual features including motion and size activities for discovering relevant activity patterns occurring in such scenes. We then show how the discovered patterns can directly be used to segment the scene into regions with clear semantic activity content. Furthermore, we introduce novel abnormality detection measures within the scope of the adopted modeling approach, and investigate in detail their performance with respect to various issues. Experiments on 45 minutes of video captured from a busy traffic scene and involving abnormal events are conducted.

Extracting and locating temporal motifs in video scenes using a hierarchical non parametric Bayesian model

In this paper, we present an unsupervised method for mining activities in videos. From unlabeled video sequences of a scene, our method can automatically recover what are the recurrent temporal activity patterns (or motifs) and when they occur. Using non parametric Bayesian methods, we are able to automatically find both the underlying number of motifs and the number of motif occurrences in each document. The models robustness is first validated on synthetic data. It is then applied on a large set of video data from state-of-the-art papers. We show that it can effectively recover temporal activities with high semantics for humans and strong temporal information. The model is also used for prediction where it is shown to be as efficient as other approaches. Although illustrated on video sequences, this model can be directly applied to various kinds of time series where multiple activities occur simultaneously.

Probabilistic Latent Sequential Motifs: Discovering temporal activity patterns in video scenes

This paper introduces a novel probabilistic activity modeling approach that mines recurrent sequential patterns from documents given as word-time occurrences. In this model, documents are represented as a mixture of sequential activity motifs (or topics) and their starting occurrences. The novelties are threefold. First, unlike previous approaches where topics only modeled the co-occurrence of words at a given time instant, our topics model the co-occurrence and temporal order in which the words occur within a temporal window. Second, our model accounts for the important case where activities occur concurrently in the document. And third, our method explicitly models with latent variables the starting time of the activities within the documents, enabling to implicitly align the occurrences of the same pattern during the joint inference of the temporal topics and their starting times. The model and its robustness to the presence of noise have been validated on synthetic data. Its effectiveness is also illustrated in video activity analysis from low-level motion features, where the discovered topics capture frequent patterns that implicitly represent typical trajectories of scene objects.

Temporal Analysis of Motif Mixtures Using Dirichlet Processes

In this paper, we present a new model for unsupervised discovery of recurrent temporal patterns (or motifs) in time series (or documents). The model is designed to handle the difficult case of multivariate time series obtained from a mixture of activities, that is, our observations are caused by the superposition of multiple phenomena occurring concurrently and with no synchronization. The model uses nonparametric Bayesian methods to describe both the motifs and their occurrences in documents. We derive an inference scheme to automatically and simultaneously recover the recurrent motifs (both their characteristics and number) and their occurrence instants in each document. The model is widely applicable and is illustrated on datasets coming from multiple modalities, mainly videos from static cameras and audio localization data. The rich semantic interpretation that the model offers can be leveraged in tasks such as event counting or for scene analysis. The approach is also used as a mean of doing soft camera calibration in a camera network. A thorough study of the model parameters is provided and a cross-platform implementation of the inference algorithm will be made publicly available.

Bridging the past, present and future: Modeling scene activities from event relationships and global rules

This paper addresses the discovery of activities and learns the underlying processes that govern their occurrences over time in complex surveillance scenes. To this end, we propose a novel topic model that accounts for the two main factors that affect these occurrences: (1) the existence of global scene states that regulate which of the activities can spontaneously occur; (2) local rules that link past activity occurrences to current ones with temporal lags. These complementary factors are mixed in the probabilistic generative process, thanks to the use of a binary random variable that selects for each activity occurrence which one of the above two factors is applicable. All model parameters are efficiently inferred using a collapsed Gibbs sampling inference scheme. Experiments on various datasets from the literature show that the model is able to capture temporal processes at multiple scales: the scene-level first order Markovian process, and causal relationships amongst activities that can be used to predict which activity can happen after another one, and after what delay, thus providing a rich interpretation of the scenes dynamical content.

Multi-camera open space human activity discovery for anomaly detection

We address the discovery of typical activities in video stream contents and its exploitation for estimating the abnormality levels of these streams. Such estimates can be used to select the most interesting cameras to show to a human operator. Our contributions come from the following facets: i) the method is fully unsupervised and learns the activities from long term data; ii) the method is scalable and can efficiently handle the information provided by multiple un-calibrated cameras, jointly learning activities shared by them if it happens to be the case (e.g. when they have overlapping fields of view); iii) unlike previous methods which were mainly applied to structured urban traffic scenes, we show that ours performs well on videos from a metro environment where human activities are only loosely constrained.

Robust Visual Tracking Using Oblique Random Forests

Random forest has emerged as a powerful classification technique with promising results in various vision tasks including image classification, pose estimation and object detection. However, current techniques have shown little improvements in visual tracking as they mostly rely on piece wise orthogonal hyperplanes to create decision nodes and lack a robust incremental learning mechanism that is much needed for online tracking. In this paper, we propose a discriminative tracker based on a novel incremental oblique random forest. Unlike conventional orthogonal decision trees that use a single feature and heuristic measures to obtain a split at each node, we propose to use a more powerful proximal SVM to obtain oblique hyperplanes to capture the geometric structure of the data better. The resulting decision surface is not restricted to be axis aligned and hence has the ability to represent and classify the input data better. Furthermore, in order to generalize to online tracking scenarios, we derive incremental update steps that enable the hyperplanes in each node to be updated recursively, efficiently and in a closed-form fashion. We demonstrate the effectiveness of our method using two large scale benchmark datasets (OTB-51 and OTB-100) and show that our method gives competitive results on several challenging cases by relying on simple HOG features as well as in combination with more sophisticated deep neural network based models. The implementations of the proposed random forest are available at https://github.com/ZhangLeUestc/ Incremental-Oblique-Random-Forest.

A Topic Model Approach to Represent and Classify American Football Plays

Automated understanding of group activities is an important area of research with applications in many domains such as surveillance, retail, health care, and sports. Despite active research in automated activity analysis, the sports domain is extremely under-served. One particularly difficult but significant sports application is the automated labeling of plays in American Football (‘football’), a sport in which multiple players interact on a playing field during structured time segments called plays. Football plays vary according to the initial formation and trajectories of players making the task of play classification quite challenging. We define a play as a unique combination of offense players’ trajectories as shown in Fig. 1(e). This dynamic group activity (play) is labeled by play type (run or pass) and direction (left, middle, or right). A run play is simply an attempt to advance the ball via running with the ball in left/middle/right directions, while a pass play is defined as an attempt to advance the ball by throwing it to the left/middle/right third of the field. In this paper, we address the combined problem of automatic representation and classification of football plays as summarized in Fig. 1. Such analysis will allow broadcasters to analyze large collections of videos, index and retrieve them more efficiently. Furthermore, this will also help coaches to infer patterns and tendencies of opponents more efficiently, resulting in better strategy planning in a game. For instance, Team A’s coach can input Team B’s videos and quickly understand commonly chosen play types and underlying strategies of Team B. Problem definition. Given a play (short video clip) consisting trajectories of six important offense players: quarterback (QB), running back (RB), wide receiver left (WR-L), wide receiver right (WR-R), tight end left (TE-L) and tight end right (TE-R), we consider two problems: 1)

Joint Estimation of Human Pose and Conversational Groups from Social Scenes

Despite many attempts in the last few years, automatic analysis of social scenes captured by wide-angle camera networks remains a very challenging task due to the low resolution of targets, background clutter and frequent and persistent occlusions. In this paper, we present a novel framework for jointly estimating (i) head, body orientations of targets and (ii) conversational groups called F-formations from social scenes. In contrast to prior works that have (a) exploited the limited range of head and body orientations to jointly learn both, or (b) employed the mutual head (but not body) pose of interactors for deducing F-formations, we propose a weakly-supervised learning algorithm for joint inference. Our algorithm employs body pose as the primary cue for F-formation estimation, and an alternating optimization strategy is proposed to iteratively refine F-formation and pose estimates. We demonstrate the increased efficacy of joint inference over the state-of-the-art via extensive experiments on three social datasets.

Active Online Anomaly Detection Using Dirichlet Process Mixture Model and Gaussian Process Classification

We present a novel anomaly detection (AD) system for streaming videos. Different from prior methods that rely on unsupervised learning of clip representations, that are usually coarse in nature, and batch-mode learning, we propose the combination of two non-parametric models for our task: i) Dirichlet process mixture models (DPMM) based modeling of object motion and directions in each cell, and ii) Gaussian process based active learning paradigm involving labeling by a domain expert. Whereas conventional clip representation methods adopt quantizing only motion directions leading to a lossy, coarse representation that are inadequate, our clip representation approach results in fine grained clusters at each cell that model the scene activities (both direction and speed) more effectively. For active anomaly detection, we adapt a Gaussian Process framework to process incoming samples (video snippets) sequentially, seek labels for confusing or informative samples and and update the AD model online. Furthermore, the proposed video representation along with a novel query criterion to select informative samples for labeling that incorporates both exploration and exploitation criteria is proposed, and is found to outperform competing criteria on two challenging traffic scene datasets.