Vikas Reddy

Improved anomaly detection in crowded scenes via cell-based analysis of foreground speed, size and texture

A robust and efficient anomaly detection technique is proposed, capable of dealing with crowded scenes where traditional tracking based approaches tend to fail. Initial foreground segmentation of the input frames confines the analysis to foreground objects and effectively ignores irrelevant background dynamics. Input frames are split into non-overlapping cells, followed by extracting features based on motion, size and texture from each cell. Each feature type is independently analysed for the presence of an anomaly. Unlike most methods, a refined estimate of object motion is achieved by computing the optical flow of only the foreground pixels. The motion and size features are modelled by an approximated version of kernel density estimation, which is computationally efficient even for large training datasets. Texture features are modelled by an adaptively grown code-book, with the number of entries in the codebook selected in an online fashion. Experiments on the recently published UCSD Anomaly Detection dataset show that the proposed method obtains considerably better results than three recent approaches: MPPCA, social force, and mixture of dynamic textures (MDT). The proposed method is also several orders of magnitude faster than MDT, the next best performing method.

Improved Foreground Detection via Block-Based Classifier Cascade With Probabilistic Decision Integration

Background subtraction is a fundamental low-level processing task in numerous computer vision applications. The vast majority of algorithms process images on a pixel-by-pixel basis, where an independent decision is made for each pixel. A general limitation of such processing is that rich contextual information is not taken into account. We propose a block-based method capable of dealing with noise, illumination variations, and dynamic backgrounds, while still obtaining smooth contours of foreground objects. Specifically, image sequences are analyzed on an overlapping block-by-block basis. A low-dimensional texture descriptor obtained from each block is passed through an adaptive classifier cascade, where each stage handles a distinct problem. A probabilistic foreground mask generation approach then exploits block overlaps to integrate interim block-level decisions into final pixel-level foreground segmentation. Unlike many pixel-based methods, ad-hoc postprocessing of foreground masks is not required. Experiments on the difficult Wallflower and I2R datasets show that the proposed approach obtains on average better results (both qualitatively and quantitatively) than several prominent methods. We furthermore propose the use of tracking performance as an unbiased approach for assessing the practical usefulness of foreground segmentation methods, and show that the proposed approach leads to considerable improvements in tracking accuracy on the CAVIAR dataset.

Adaptive Patch-Based Background Modelling for Improved Foreground Object Segmentation and Tracking

A robust foreground object segmentation technique is proposed, capable of dealing with image sequences containing noise, illumination variations and dynamic backgrounds. The method employs contextual spatial information by analysing each image on an overlapping patch-by-patch basis and obtaining a low-dimensional texture descriptor for each patch. Each descriptor is passed through an adaptive multi-stage classifier, comprised of a likelihood evaluation, an illumination robust measure, and a temporal correlation check. A probabilistic foreground mask generation approach integrates the classification decisions by exploiting the overlapping of patches, ensuring smooth contours of the foreground objects as well as effectively minimising the number of errors. The parameter settings are robust against wide variety of sequences and post-processing of foreground masks is not required. Experiments on the difficult Wallflower and I2R datasets show that the proposed method obtains considerably better results (both qualitatively and quantitatively) than methods based on Gaussian mixture models, feature histograms, and normalised vector distances. Further experiments on the CAVIAR dataset (using several tracking algorithms) indicate that the proposed method leads to considerable improvements in object tracking accuracy.

An efficient background estimation algorithm for embedded smart cameras

Segmentation of foreground objects of interest from an image sequence is an important task in most smart cameras. Background subtraction is a popular and efficient technique used for segmentation. The method assumes that a background model of the scene under analysis is known. However, in many practical circumstances it is unavailable and needs to be estimated from cluttered image sequences. With embedded systems as the target platform, in this paper we propose a sequential technique for background estimation in such conditions, with low computational and memory requirements. The first stage is somewhat similar to that of the recently proposed agglomerative clustering background estimation method, where image sequences are analysed on a block by block basis. For each block location a representative set is maintained which contains distinct blocks obtained along its temporal line. The novelties lie in iteratively filling in background areas by selecting the most appropriate candidate blocks according to the combined frequency responses of extended versions of the candidate block and its neighbourhood. It is assumed that the most appropriate block results in the smoothest response, indirectly enforcing the spatial continuity of structures within a scene. Experiments on real-life surveillance videos demonstrate the advantages of the proposed method.

Robust Foreground Object Segmentation via Adaptive Region-Based Background Modelling

We propose a region-based foreground object segmentation method capable of dealing with image sequences containing noise, illumination variations and dynamic backgrounds (as often present in outdoor environments). The method utilises contextual spatial information through analysing each frame on an overlapping block by-block basis and obtaining a low-dimensional texture descriptor for each block. Each descriptor is passed through an adaptive multi-stage classifier, comprised of a likelihood evaluation, an illumination invariant measure, and a temporal correlation check. The overlapping of blocks not only ensures smooth contours of the foreground objects but also effectively minimises the number of false positives in the generated foreground masks. The parameter settings are robust against wide variety of sequences and post-processing of foreground masks is not required. Experiments on the challenging I2R dataset show that the proposed method obtains considerably better results (both qualitatively and quantitatively) than methods based on Gaussian mixture models (GMMs), feature histograms, and normalised vector distances. On average, the proposed method achieves 36% more accurate foreground masks than the GMM based method.

An efficient and robust sequential algorithm for background estimation in video surveillance

Many computer vision algorithms such as object tracking and event detection assume that a background model of the scene under analysis is known. However, in many practical circumstances it is unavailable and must be estimated from cluttered image sequences. We propose a sequential technique for background estimation in such conditions, with low computational and memory requirements. The first stage is somewhat similar to that of the recently proposed agglomerative clustering background estimation method, where image sequences are analysed on a patch by patch basis. For each patch location a representative set is maintained which contains distinct patches obtained along its temporal line. The novelties lie in iteratively filling in background areas by selecting the most appropriate candidate patches according to the combined frequency responses of extended versions of the candidate patch and its neigh-bourhood. It is assumed that the most appropriate patch results in the smoothest response, indirectly enforcing the spatial continuity of structures within a scene. Experiments on real-life surveillance videos demonstrate the efficacy of the proposed method.

MRF-based background initialisation for improved foreground detection in cluttered surveillance videos

Robust foreground object segmentation via background modelling is a difficult problem in cluttered environments, where obtaining a clear view of the background to model is almost impossible. In this paper, we propose a method capable of robustly estimating the background and detecting regions of interest in such environments. In particular, we propose to extend the background initialisation component of a recent patch-based foreground detection algorithm with an elaborate technique based on Markov Random Fields, where the optimal labelling solution is computed using iterated conditional modes. Rather than relying purely on local temporal statistics, the proposed technique takes into account the spatial continuity of the entire background. Experiments with several tracking algorithms on the CAVIAR dataset indicate that the proposed method leads to considerable improvements in object tracking accuracy, when compared to methods based on Gaussian mixture models and feature histograms.

Real-time video event detection in crowded scenes using MPEG derived features

Investigate multiple instance learning and motion features for event detection.A novel trajectory feature descriptor from the MPEG domain is proposed.A novel multiple instance learning approach using sparse approximation is proposed.Real time performance is achieved. This paper presents an investigation into event detection in crowded scenes, where the event of interest co-occurs with other activities and only binary labels at the clip level are available. The proposed approach incorporates a fast feature descriptor from the MPEG domain, and a novel multiple instance learning (MIL) algorithm using sparse approximation and random sensing. MPEG motion vectors are used to build particle trajectories that represent the motion of objects in uniform video clips, and the MPEG DCT coefficients are used to compute a foreground map to remove background particles. Trajectories are transformed into the Fourier domain, and the Fourier representations are quantized into visual words using the K-Means algorithm. The proposed MIL algorithm models the scene as a linear combination of independent events, where each event is a distribution of visual words. Experimental results show that the proposed approaches achieve promising results for event detection compared to the state-of-the-art.

An intuitive multi-touch surface and gesture based interaction for video surveillance systems

This paper discusses the idea and demonstrates an early prototype of a novel method of interacting with security surveillance footage using natural user interfaces in place of traditional mouse and keyboard interaction. Current surveillance monitoring stations and systems provide the user with a vast array of video feeds from multiple locations on a video wall, relying on the user’s ability to distinguish locations of the live feeds from experience or list based key-value pair of location and camera IDs. During an incident, this current method of interaction may cause the user to spend increased amounts time obtaining situational and location awareness, which is counter-productive. The system proposed in this paper demonstrates how a multi-touch screen and natural interaction can enable the surveillance monitoring station users to quickly identify the location of a security camera and efficiently respond to an incident.

Analysis of passenger group behaviour and its impact on passenger flow using an agent-based model

Group interaction within crowds is a common phenomenon and has great influence on pedestrian behaviour. This paper investigates the impact of passenger group dynamics using an agent-based simulation method for the outbound passenger process at airports. Unlike most passenger-flow models that treat passengers as individual agents, the proposed model additionally incorporates their group dynamics as well. The simulation compares passenger behaviour at airport processes and discretionary services under different group formations. Results from experiments (both qualitative and quantitative) show that incorporating group attributes, in particular, the interactions with fellow travellers and wavers can have significant influence on passengers activity preference as well as the performance and utilisation of services in airport terminals. The model also provides a convenient way to investigate the effectiveness of airport space design and service allocations, which can contribute to positive passenger experiences. The model was created using AnyLogic software and its parameters were initialised using recent research data published in the literature.