Prasad Gabbur

Human Face Detection and Tracking using Skin Color Modeling and Connected Component Operators

Face Recognition (FR) systems are increasingly gaining more importance. Face detection and tracking in a complex scene forms the first step in building a practical FR system. In this paper, a method to detect and track human faces in color image sequences is described. Skin color classification and morphological segmentation is used to detect face(s) in the first frame. These detected faces are tracked over subsequent frames by using the position of the faces in the first frame as the marker and detecting for skin in the localized region. Specific advantages of this approach are that skin color analysis method is simple and powerful, and the system can be used to detect/track multiple faces.

Relative Attributes for Large-Scale Abandoned Object Detection

Effective reduction of false alarms in large-scale video surveillance is rather challenging, especially for applications where abnormal events of interest rarely occur, such as abandoned object detection. We develop an approach to prioritize alerts by ranking them, and demonstrate its great effectiveness in reducing false positives while keeping good detection accuracy. Our approach benefits from a novel representation of abandoned object alerts by relative attributes, namely static ness, foreground ness and abandonment. The relative strengths of these attributes are quantified using a ranking function[19] learnt on suitably designed low-level spatial and temporal features. These attributes of varying strengths are not only powerful in distinguishing abandoned objects from false alarms such as people and light artifacts, but also computationally efficient for large-scale deployment. With these features, we apply a linear ranking algorithm to sort alerts according to their relevance to the end-user. We test the effectiveness of our approach on both public data sets and large ones collected from the real world.

Detecting human activities in retail surveillance using hierarchical finite state machine

Cashiers in retail stores usually exhibit certain repetitive and periodic activities when processing items. Detecting such activities plays a key role in most retail fraud detection systems. In this paper, we propose a highly efficient, effective and robust vision technique to detect checkout-related primitive activities, based on a hierarchical finite state machine (FSM). Our deterministic approach uses visual features and prior spatial constraints on the hand motion to capture particular motion patterns performed in primitive activities. We also apply our approach to the problem of retail fraud detection. Experimental results on a large set of video data captured from retail stores show that our approach, while much simpler and faster, achieves significantly better results than state-of-the-art machine learning-based techniques both in detecting checkout-related activities and in detecting checkout-related fraudulent incidents.

Hand tracking by binary quadratic programming and its application to retail activity recognition

Substantial ambiguities arise in hand tracking due to issues such as small hand size, deformable hand shapes and similar hand appearances. These issues have greatly limited the capability of current multi-target tracking techniques in hand tracking. As an example, state-of-the-art approaches for people tracking handle indentity switching by exploiting the appearance cues using advanced object detectors. For hand tracking, such approaches will fail due to similar, or even identical hand appearances. The main contribution of our work is a global optimization framework based on binary quadratic programming (BQP) that seamlessly integrates appearance, motion and complex interactions between hands. Our approach effectively handles key challenges such as occlusion, detection failure, identity switching, and robustly tracks both hands in two challenging real-life scenarios: retail surveillance and sign languages. In addition, we demonstrate that an automatic method based on hand trajectory analysis outperforms state-of-the-art on checkout-related activity recognition in grocery stores.

Retail video analytics: an overview and survey

Today retail video analytics has gone beyond the traditional domain of security and loss prevention by providing retailers insightful business intelligence such as store traffic statistics and queue data. Such information allows for enhanced customer experience, optimized store performance, reduced operational costs, and ultimately higher profitability. This paper gives an overview of various camera-based applications in retail as well as the state-ofthe- art computer vision techniques behind them. It also presents some of the promising technical directions for exploration in retail video analytics.

A pattern discovery approach to retail fraud detection

A major source of revenue shrink in retail stores is the intentional or unintentional failure of proper checking out of items by the cashier. More recently, a few automated surveillance systems have been developed to monitor cashier lanes and detect non-compliant activities such as fake item checkouts or scans done with the intention of deriving monetary benefit. These systems use data from surveillance video cameras and transaction logs (TLog) recorded at the Point-of-Sale (POS). In this paper, we present a pattern discovery based approach to detect fraudulent events at the POS. Our approach is based on mining time-ordered text streams, representing retail transactions, formed from a combination of visually detected checkout related activities called primitives and barcodes from TLog data. Patterns representing single item checkouts, i.e. anchored around a single barcode, are discovered from these text streams using an efficient pattern discovery technique called Teiresias. The discovered patterns are used to build models for true and fake item scans by retaining or discarding the anchoring barcodes in those patterns respectively. A pattern matching and classification scheme is designed to robustly detect non-compliant cashier activities in the presence of noise in either the TLog or the video data. Different weighting schemes for quantifying the relative importance of the discovered patterns are explored: Frequency, Support Vector Machine (SVM) and Frequency+SVM. Using a large scale dataset recorded from retail stores, our approach discovers semantically meaningful cashier scan patterns. Our experiments also suggest that different weighting schemes result in varied false and true positive performances on the task of fake scan detection.

A fast connected components labeling algorithm and its application to real-time pupil detection

We describe a fast connected components labeling algorithm using a region coloring approach. It computes region attributes such as size, moments, and bounding boxes in a single pass through the image. Working in the context of real-time pupil detection for an eye tracking system, we compare the time performance of our algorithm with a contour tracing-based labeling approach and a region coloring method developed for a hardware eye detection system. We find that region attribute extraction performance exceeds that of these comparison methods. Further, labeling each pixel, which requires a second pass through the image, has comparable performance.

Evaluation strategies for image understanding and retrieval

We address evaluation of image understanding and retrieval large scale image data in the context of three evaluation projects. The first project is a comprehensive strategy for evaluating image retrieval algorithms and provides an open reference data set for doing so. The second project develops word prediction as a semantically relevant evaluation strategy, and applies it to the evaluation of of image processing methods for semantic image analysis. The third project evaluates words for suitability of their visual properties for use in an image annotation framework.

Cross Modal Disambiguation

We consider strategies for reducing ambiguity in multi-modal data, particularly in the domain of images and text. Large data sets containing images with associated text (and vice versa) are readily available, and recent work has exploited such data to learn models for linking visual elements to semantics. This requires addressing a correspondence ambiguity because it is generally not known which parts of the images connect with which language elements. In this paper we first discuss using language processing to reduce correspondence ambiguity in loosely labeled image data. We then consider a similar problem of using visual correlates to reduce ambiguity in text with associated images. Only rudimentary image understanding is needed for this task because the image only needs to help differentiate between a limited set of choices, namely the senses of a particular word.

Soft margin keyframe comparison: Enhancing precision of fraud detection in retail surveillance

We propose a novel approach for enhancing precision in a leading video analytics system that detects cashier fraud in grocery stores for loss prevention. While intelligent video analytics has recently become a promising means of loss prevention for retailers, most of the real-world systems suffer from a large number of false alarms, resulting in a significant waste of human labor during manual verification. Our proposed approach starts with the candidate fraudulent events detected by a state-of-the-art system. Such fraudulent events are a set of visually recognized checkout-related activities of the cashier without barcode associations. Instead of conducting costly video analysis, we extract a few keyframes to represent the essence of each candidate fraudulent event, and compare those keyframes to identify whether or not the event is a valid check-out process that involves consistent appearance changes on the lead-in belt, the scan area and the take-away belt. Our approach also performs a margin-based soft classification so that the user could trade off between saving human labor and preserving high recall. Experiments on days of surveillance videos collected from real grocery stores show that our algorithm can save about 50% of human labor while preserving over 90% of true alarms with small computational overhead.