Haroon Idrees

Detection and tracking of large number of targets in wide area surveillance

In this paper, we tackle the problem of object detection and tracking in a new and challenging domain of wide area surveillance. This problem poses several challenges: large camera motion, strong parallax, large number of moving objects, small number of pixels on target, single channel data and low framerate of video. We propose a method that overcomes these challenges and evaluate it on CLIF dataset. We use median background modeling which requires few frames to obtain a workable model. We remove false detections due to parallax and registration errors using gradient information of the background image. In order to keep complexity of the tracking problem manageable, we divide the scene into grid cells, solve the tracking problem optimally within each cell using bipartite graph matching and then link tracks across cells. Besides tractability, grid cells allow us to define a set of local scene constraints such as road orientation and object context. We use these constraints as part of cost function to solve the tracking problem which allows us to track fast-moving objects in low framerate videos. In addition to that, we manually generated groundtruth for four sequences and performed quantitative evaluation of the proposed algorithm.

Multi-source Multi-scale Counting in Extremely Dense Crowd Images

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.

NMF-KNN: Image Annotation Using Weighted Multi-view Non-negative Matrix Factorization

The real world image databases such as Flickr are characterized by continuous addition of new images. The recent approaches for image annotation, i.e. the problem of assigning tags to images, have two major drawbacks. First, either models are learned using the entire training data, or to handle the issue of dataset imbalance, tag-specific discriminative models are trained. Such models become obsolete and require relearning when new images and tags are added to database. Second, the task of feature-fusion is typically dealt using ad-hoc approaches. In this paper, we present a weighted extension of Multi-view Non-negative Matrix Factorization (NMF) to address the aforementioned drawbacks. The key idea is to learn query-specific generative model on the features of nearest-neighbors and tags using the proposed NMF-KNN approach which imposes consensus constraint on the coefficient matrices across different features. This results in coefficient vectors across features to be consistent and, thus, naturally solves the problem of feature fusion, while the weight matrices introduced in the proposed formulation alleviate the issue of dataset imbalance. Furthermore, our approach, being query-specific, is unaffected by addition of images and tags in a database. We tested our method on two datasets used for evaluation of image annotation and obtained competitive results.

The THUMOS challenge on action recognition for videos “in the wild”☆

Abstract Automatically recognizing and localizing wide ranges of human actions are crucial for video understanding. Towards this goal, the THUMOS challenge was introduced in 2013 to serve as a benchmark for action recognition. Until then, video action recognition, including THUMOS challenge, had focused primarily on the classification of pre-segmented (i.e., trimmed) videos, which is an artificial task. In THUMOS 2014, we elevated action recognition to a more practical level by introducing temporally untrimmed videos. These also include ‘background videos’ which share similar scenes and backgrounds as action videos, but are devoid of the specific actions. The three editions of the challenge organized in 2013–2015 have made THUMOS a common benchmark for action classification and detection and the annual challenge is widely attended by teams from around the world. In this paper we describe the THUMOS benchmark in detail and give an overview of data collection and annotation procedures. We present the evaluation protocols used to quantify results in the two THUMOS tasks of action classification and temporal action detection. We also present results of submissions to the THUMOS 2015 challenge and review the participating approaches. Additionally, we include a comprehensive empirical study evaluating the differences in action recognition between trimmed and untrimmed videos, and how well methods trained on trimmed videos generalize to untrimmed videos. We conclude by proposing several directions and improvements for future THUMOS challenges.

Detecting Humans in Dense Crowds Using Locally-Consistent Scale Prior and Global Occlusion Reasoning

Human detection in dense crowds is an important problem, as it is a prerequisite to many other visual tasks, such as tracking, counting, action recognition or anomaly detection in behaviors exhibited by individuals in a dense crowd. This problem is challenging due to the large number of individuals, small apparent size, severe occlusions and perspective distortion. However, crowded scenes also offer contextual constraints that can be used to tackle these challenges. In this paper, we explore context for human detection in dense crowds in the form of a locally-consistent scale prior which captures the similarity in scale in local neighborhoods and its smooth variation over the image. Using the scale and confidence of detections obtained from an underlying human detector, we infer scale and confidence priors using Markov Random Field. In an iterative mechanism, the confidences of detection hypotheses are modified to reflect consistency with the inferred priors, and the priors are updated based on the new detections. The final set of detections obtained are then reasoned for occlusion using Binary Integer Programming where overlaps and relations between parts of individuals are encoded as linear constraints. Both human detection and occlusion reasoning in proposed approach are solved with local neighbor-dependent constraints, thereby respecting the inter-dependence between individuals characteristic to dense crowd analysis. In addition, we propose a mechanism to detect different combinations of body parts without requiring annotations for individual combinations. We performed experiments on a new and extremely challenging dataset of dense crowd images showing marked improvement over the underlying human detector.

Tracking in dense crowds using prominence and neighborhood motion concurrence

Methods designed for tracking in dense crowds typically employ prior knowledge to make this difficult problem tractable. In this paper, we show that it is possible to handle this problem, without any priors, by utilizing the visual and contextual information already available in such scenes. We propose a novel tracking method tailored to dense crowds which provides an alternative and complementary approach to methods that require modeling of crowd flow and, simultaneously, is less likely to fail in the case of dynamic crowd flows and anomalies by minimally relying on previous frames. Our method begins with the automatic identification of prominent individuals from the crowd that are easy to track. Then, we use Neighborhood Motion Concurrence to model the behavior of individuals in a dense crowd, this predicts the position of an individual based on the motion of its neighbors. When the individual moves with the crowd flow, we use Neighborhood Motion Concurrence to predict motion while leveraging five-frame instantaneous flow in case of dynamically changing flow and anomalies. All these aspects are then embedded in a framework which imposes hierarchy on the order in which positions of individuals are updated. Experiments on a number of sequences show that the proposed solution can track individuals in dense crowds without requiring any pre-processing, making it a suitable online tracking algorithm for dense crowds.

Moving Object Detection and Tracking in Forward Looking Infra-Red Aerial Imagery

This chapter discusses the challenges of automating surveillance and reconnaissance tasks for infra-red visual data obtained from aerial platforms. These problems have gained significant importance over the years, especially with the advent of lightweight and reliable imaging devices. Detection and tracking of objects of interest has traditionally been an area of interest in the computer vision literature. These tasks are rendered especially challenging in aerial sequences of infra red modality. The chapter gives an overview of these problems, and the associated limitations of some of the conventional techniques typically employed for these applications. We begin with a study of various image registration techniques that are required to eliminate motion induced by the motion of the aerial sensor. Next, we present a technique for detecting moving objects from the ego-motion compensated input sequence. Finally, we describe a methodology for tracking already detected objects using their motion history. We substantiate our claims with results on a wide range of aerial video sequences.

Automatic Detection and Tracking of Pedestrians in Videos with Various Crowd Densities

Manual analysis of pedestrians and crowds is often impractical for massive datasets of surveillance videos. Automatic tracking of humans is one of the essential abilities for computerized analysis of such videos. In this keynote paper, we present two state of the art methods for automatic pedestrian tracking in videos with low and high crowd density. For videos with low density, first we detect each person using a part-based human detector. Then, we employ a global data association method based on Generalized Graphs for tracking each individual in the whole video. In videos with high crowd-density, we track individuals using a scene structured force model and crowd flow modeling. Additionally, we present an alternative approach which utilizes contextual information without the need to learn the structure of the scene. Performed evaluations show the presented methods outperform the currently available algorithms on several benchmarks.

Human Re-identification in Crowd Videos Using Personal, Social and Environmental Constraints

This paper addresses the problem of human re-identification in videos of dense crowds. Re-identification in crowded scenes is a challenging problem due to large number of people and frequent occlusions, coupled with changes in their appearance due to different properties and exposure of cameras. To solve this problem, we model multiple Personal, Social and Environmental (PSE) constraints on human motion across cameras in crowded scenes. The personal constraints include appearance and preferred speed of each individual, while the social influences are modeled by grouping and collision avoidance. Finally, the environmental constraints model the transition probabilities between gates (entrances/exits). We incorporate these constraints into an energy minimization for solving human re-identification. Assigning 1–1 correspondence while modeling PSE constraints is NP-hard. We optimize using a greedy local neighborhood search algorithm to restrict the search space of hypotheses. We evaluated the proposed approach on several thousand frames of PRID and Grand Central datasets, and obtained significantly better results compared to existing methods.

Improving Semantic Concept Detection through the Dictionary of Visually-Distinct Elements

A video captures a sequence and interactions of concepts that can be static, for instance, objects or scenes, or dynamic, such as actions. For large datasets containing hundreds of thousands of images or videos, it is impractical to manually annotate all the concepts, or all the instances of a single concept. However, a dictionary with visually-distinct elements can be created automatically from unlabeled videos which can capture and express the entire dataset. The downside to this machine-discovered dictionary is meaninglessness, i.e., its elements are devoid of semantics and interpretation. In this paper, we present an approach that leverages the strengths of semantic concepts and the machine-discovered DOVE by learning a relationship between them. Since instances of a semantic concept share visual similarity, the proposed approach uses soft-consensus regularization to learn the mapping that enforces instances from each semantic concept to have similar representations. The testing is performed by projecting the query onto the DOVE as well as new representations of semantic concepts from training, with non-negativity and unit summation constraints for probabilistic interpretation. We tested our formulation on TRECVID MED and SIN tasks, and obtained encouraging results.