Murray Evans

Robust abandoned object detection integrating wide area visual surveillance and social context

This paper presents a video surveillance framework that robustly and efficiently detects abandoned objects in surveillance scenes. The framework is based on a novel threat assessment algorithm which combines the concept of ownership with automatic understanding of social relations in order to infer abandonment of objects. Implementation is achieved through development of a logic-based inference engine based on Prolog. Threat detection performance is conducted by testing against a range of datasets describing realistic situations and demonstrates a reduction in the number of false alarms generated. The proposed system represents the approach employed in the EU SUBITO project (Surveillance of Unattended Baggage and the Identification and Tracking of the Owner).

Video Activity Extraction and Reporting with Incremental Unsupervised Learning

The present work presents a new method for activity extractionand reporting from video based on the aggregationof fuzzy relations. Trajectory clustering is first employedmainly to discover the points of entry and exit of mobiles appearingin the scene. In a second step, proximity relationsbetween resulting clusters of detected mobiles and contextualelements from the scene are modeled employing fuzzyrelations. These can then be aggregated employing typicalsoft-computing algebra. A clustering algorithm based onthe transitive closure calculation of the fuzzy relations allowsbuilding the structure of the scene and characterisesthe ongoing different activities of the scene. Discovered activityzones can be reported as activity maps with differentgranularities thanks to the analysis of the transitive closurematrix. Taking advantage of the soft relation properties, activityzones and related activities can be labeled in a morehuman-like language. We present results obtained on realvideos corresponding to apron monitoring in the Toulouseairport in France.

Activity recognition and localization on a truck parking lot

In this paper we present a set of activity recognition and localization algorithms that together assemble a large amount of information about activities on a parking lot. The aim is to detect and recognize events that may pose a threat to truck drivers and trucks. The algorithms perform zone-based activity learning, individual action recognition and group detection. Visual sensor data, from one camera, have been recorded for 23 realistic scenarios of different complexities. The scene is complicated and causes uncertain and false position estimates. We also present a situational assessment ontology which serves the algorithms with relevant knowledge about the observed scene (e.g. information about objects, vulnerabilities and historical data). The algorithms are tested with real tracking data and the evaluations show promising results. The accuracies are 90 % for zone-based activity learning, 71 % for individual action recognition and 66 % for group detection (i.e. merging of people).

Multicamera object detection and tracking with object size estimation

A number of multi-camera solutions exist for tracking objects of interest in surveillance scenes. Generally, the approach follows the idea of either early fusion (where all cameras are used to make a decision about detection and tracking) or late fusion (where objects are detected and tracked in individual cameras independently, and then the results combined). This paper describes an early fusion approach derived from the common approach of projecting foreground mask into a common coordinate system. The described approach extends prior work to suppress false detections and automatically estimate the size of the object under tracking, thus enabling it to work in environments containing a mix of people and vehicles.

Surveillance Camera Calibration from Observations of a Pedestrian

Calibrated cameras are an extremely useful resource forcomputer vision scenarios. Typically, cameras are calibratedthrough calibration targets, measurements of the observedscene, or self-calibrated through features matchedbetween cameras with overlapping fields of view. This paperconsiders an approach to camera calibration based onobservations of a pedestrian and compares the resultingcalibration to a commonly used approach requiring thatmeasurements be made of the scene.

Group stochastic search for object detection and tracking

A technique is presented for locating and tracking objects in cluttered environments. Agents are randomly distributed across the image, and subsequently grouped around targets. Each agent uses a weightless neural network and a histogram intersection technique to score its location. The system has been used to locate and track a head in 320/spl times/240 resolution video at up to 15 fps.

Unsupervised activity extraction on long-term video recordings employing soft computing relations

In this work we present a novel approach for activity extraction and knowledge discovery from video employing fuzzy relations. Spatial and temporal properties from detected mobile objects are modeled with fuzzy relations. These can then be aggregated employing typical soft-computing algebra. A clustering algorithm based on the transitive closure calculation of the fuzzy relations allows finding spatio-temporal patterns of activity. We present results obtained on videos corresponding to different sequences of apron monitoring in the Toulouse airport in France.

Global-to-Local Histogram Match Culling for Epipolar Geometry Estimation

Estimation of the Epipolar Geometry and Fundamental Matrix for a pair of stereo images often begins with a stage of feature (corner) detection and correlation based feature matching. This generally results in a set of matches where features are matched multiple times and frequently incorrectly. This paper introduces a simple and fast histogram based technique for refining the set of matches prior to a final stage of robust Fundamental Matrix estimation that compares favourably to previously published techniques such as SVD and Relaxation.