Development of multi-rotor localised surveillance using multi-spectral sensors for plant biosecurity

This report describes a proof of concept for multi-rotor localised surveillance using a multi-spectral sensor for plant biosecurity applications. A literature review was conducted on previous applications using airborne multispectral imaging for plant biosecurity purposes. A ready built platform was purchased and modified in order to fit and provide suitable clearance for a Tetracam Mini-MCA multispectral camera. The appropriate risk management documents were developed allowing the platform and the multi-spectral camera to be tested extensively. However, due to technical difficulties with the platform the Mini- MCA was not mounted to the platform. Once a suitable platform is developed, future extensions can be conducted into the suitability of the Mini-MCA for airborne surveillance of Australian crops.

Determining operational measures from multi-camera surveillance systems using soft biometrics

CCTV and surveillance networks are increasingly being used for operational as well as security tasks. One emerging area of technology that lends itself to operational analytics is soft biometrics. Soft biometrics can be used to describe a person and detect them throughout a sparse multi-camera network. This enables them to be used to perform tasks such as determining the time taken to get from point to point, and the paths taken through an environment by detecting and matching people across disjoint views. However, in a busy environment where there are 100's if not 1000's of people such as an airport, attempting to monitor everyone is highly unrealistic. In this paper we propose an average soft biometric, that can be used to identity people who look distinct, and are thus suitable for monitoring through a large, sparse camera network. We demonstrate how an average soft biometric can be used to identify unique people to calculate operational measures such as the time taken to travel from point to point.

A database for person re-identification in multi-camera surveillance networks

Person re-identification involves recognising individuals in different locations across a network of cameras and is a challenging task due to a large number of varying factors such as pose (both subject and camera) and ambient lighting conditions. Existing databases do not adequately capture these variations, making evaluations of proposed techniques difficult. In this paper, we present a new challenging multi-camera surveillance database designed for the task of person re-identification. This database consists of 150 unscripted sequences of subjects travelling in a building environment though up to eight camera views, appearing from various angles and in varying illumination conditions. A flexible XML-based evaluation protocol is provided to allow a highly configurable evaluation setup, enabling a variety of scenarios relating to pose and lighting conditions to be evaluated. A baseline person re-identification system consisting of colour, height and texture models is demonstrated on this database.

'Going live' : establishing the creative attributes of the live multi-camera television professional

In my capacity as a television professional and teacher specialising in multi-camera live television production for over 40 years, I was drawn to the conclusion that opaque or inadequately formed understandings of how creativity applies to the field of live television, have impeded the development of pedagogies suitable to the teaching of live television in universities. In the pursuit of this hypothesis, the thesis shows that television degrees were born out of film studies degrees, where intellectual creativity was aligned to single camera production, and the 'creative roles' of producers, directors and scriptwriters. At the same time, multi-camera live television production was subsumed under the 'mass communication' banner, leading to an understanding that roles other than producer and director are simply technical, and bereft of creative intent or acumen. The thesis goes on to show that this attitude to other television production personnel, for example, the vision mixer, videotape operator and camera operator, relegates their roles to that of 'button pusher'. This has resulted in university teaching models with inappropriate resources and unsuitable teaching practices. As a result, the industry is struggling to find people with the skills to fill the demands of the multi-camera live television sector. In specific terms the central hypothesis is pursued through the following sequenced approach. Firstly, the thesis sets out to outline the problems, and traces the origins of the misconceptions that hold with the notion that intellectual creativity does not exist in live multi-camera television. Secondly, this more adequately conceptualised rendition, of the origins particular to the misconceptions of live television and creativity, is then anchored to the field of examination by presentation of the foundations of the roles involved in making live television programs, using multicamera production techniques. Thirdly, this more nuanced rendition of the field sets the stage for a thorough analysis of education and training in the industry, and teaching models at Australian universities. The findings clearly establish that the pedagogical models are aimed at single camera production, a position that deemphasises the creative aspects of multi-camera live television production. Informed by an examination of theories of learning, qualitative interviews, professional reflective practice and observations, the roles of four multi-camera live production crewmembers (camera operator, vision mixer, EVS/videotape operator and director's assistant), demonstrate the existence of intellectual creativity during live production. Finally, supported by the theories of learning, and the development and explication of a successful teaching model, a new approach to teaching students how to work in live television is proposed and substantiated.

Scene invariant multi camera crowd counting

Automated crowd counting has become an active field of computer vision research in recent years. Existing approaches are scene-specific, as they are designed to operate in the single camera viewpoint that was used to train the system. Real world camera networks often span multiple viewpoints within a facility, including many regions of overlap. This paper proposes a novel scene invariant crowd counting algorithm that is designed to operate across multiple cameras. The approach uses camera calibration to normalise features between viewpoints and to compensate for regions of overlap. This compensation is performed by constructing an 'overlap map' which provides a measure of how much an object at one location is visible within other viewpoints. An investigation into the suitability of various feature types and regression models for scene invariant crowd counting is also conducted. The features investigated include object size, shape, edges and keypoints. The regression models evaluated include neural networks, K-nearest neighbours, linear and Gaussian process regresion. Our experiments demonstrate that accurate crowd counting was achieved across seven benchmark datasets, with optimal performance observed when all features were used and when Gaussian process regression was used. The combination of scene invariance and multi camera crowd counting is evaluated by training the system on footage obtained from the QUT camera network and testing it on three cameras from the PETS 2009 database. Highly accurate crowd counting was observed with a mean relative error of less than 10%. Our approach enables a pre-trained system to be deployed on a new environment without any additional training, bringing the field one step closer toward a 'plug and play' system.

Optimal camera planning under versatile user constraints in multi-camera image processing systems

The selection of optimal camera configurations (camera locations, orientations, etc.) for multi-camera networks remains an unsolved problem. Previous approaches largely focus on proposing various objective functions to achieve different tasks. Most of them, however, do not generalize well to large scale networks. To tackle this, we propose a statistical framework of the problem as well as propose a trans-dimensional simulated annealing algorithm to effectively deal with it. We compare our approach with a state-of-the-art method based on binary integer programming (BIP) and show that our approach offers similar performance on small scale problems. However, we also demonstrate the capability of our approach in dealing with large scale problems and show that our approach produces better results than two alternative heuristics designed to deal with the scalability issue of BIP. Last, we show the versatility of our approach using a number of specific scenarios.

Camera calibration in wireless multimedia sensor networks

Wireless Multi-media Sensor Networks (WMSNs) have become increasingly popular in recent years, driven in part by the increasing commoditization of small, low-cost CMOS sensors. As such, the challenge of automatically calibrating these types of cameras nodes has become an important research problem, especially for the case when a large quantity of these type of devices are deployed. This paper presents a method for automatically calibrating a wireless camera node with the ability to rotate around one axis. The method involves capturing images as the camera is rotated and computing the homographies between the images. The camera parameters, including focal length, principal point and the angle and axis of rotation can then recovered from two or more homographies. The homography computation algorithm is designed to deal with the limited resources of the wireless sensor and to minimize energy con- sumption. In this paper, a modified RANdom SAmple Consensus (RANSAC) algorithm is proposed to effectively increase the efficiency and reliability of the calibration procedure.

A multi-resolution image alignment technique based on direct methods for pose estimation of aerial vehicles

In this paper, we seek to expand the use of direct methods in real-time applications by proposing a vision-based strategy for pose estimation of aerial vehicles. The vast majority of approaches make use of features to estimate motion. Conversely, the strategy we propose is based on a MR (Multi- Resolution) implementation of an image registration technique (Inverse Compositional Image Alignment ICIA) using direct methods. An on-board camera in a downwards-looking configuration, and the assumption of planar scenes, are the bases of the algorithm. The motion between frames (rotation and translation) is recovered by decomposing the frame-to-frame homography obtained by the ICIA algorithm applied to a patch that covers around the 80% of the image. When the visual estimation is required (e.g. GPS drop-out), this motion is integrated with the previous known estimation of the vehicles’ state, obtained from the on-board sensors (GPS/IMU), and the subsequent estimations are based only on the vision-based motion estimations. The proposed strategy is tested with real flight data in representative stages of a flight: cruise, landing, and take-off, being two of those stages considered critical: take-off and landing. The performance of the pose estimation strategy is analyzed by comparing it with the GPS/IMU estimations. Results show correlation between the visual estimation obtained with the MR-ICIA and the GPS/IMU data, that demonstrate that the visual estimation can be used to provide a good approximation of the vehicle’s state when it is required (e.g. GPS drop-outs). In terms of performance, the proposed strategy is able to maintain an estimation of the vehicle’s state for more than one minute, at real-time frame rates based, only on visual information.

On the statistical determination of optimal camera configurations in large scale surveillance networks

The selection of optimal camera configurations (camera locations, orientations etc.) for multi-camera networks remains an unsolved problem. Previous approaches largely focus on proposing various objective functions to achieve different tasks. Most of them, however, do not generalize well to large scale networks. To tackle this, we introduce a statistical formulation of the optimal selection of camera configurations as well as propose a Trans-Dimensional Simulated Annealing (TDSA) algorithm to effectively solve the problem. We compare our approach with a state-of-the-art method based on Binary Integer Programming (BIP) and show that our approach offers similar performance on small scale problems. However, we also demonstrate the capability of our approach in dealing with large scale problems and show that our approach produces better results than 2 alternative heuristics designed to deal with the scalability issue of BIP.

Re-framing infrastructure investment decision-making processes : a preliminary scoping study for urban flood risk management in Jakarta, Indonesia

Jakarta, Indonesia’s chronic housing shortage poses multiple challenges for contemporary policy-makers. While it may be in the city’s interest to increase the availability of housing, there is limited land to do so. Market pressures, in tandem with government’s desire for housing availability, demand consideration of even marginal lands, such as those within floodplains, for development. Increasingly, planning for a flood resilient Jakarta is complicated by a number of factors, including: the city is highly urbanized and land use data is limited; flood management is technically complex, creating potential barriers to engagement for both decision-makers and the public; inherent uncertainty exists throughout modelling efforts, central to management; and risk and liability for infrastructure investments is unclear. These obstacles require localized watershed-level participatory planning to address risks of flooding where possible and reduce the likelihood that informal settlements occur in areas of extreme risk. This paper presents a preliminary scoping study for determination of an effective participatory planning method to encourage more resilient development. First, the scoping study provides background relevant to the challenges faced in planning for contemporary Jakarta. Second, the study examines the current use of decision-support tools, such as Geographic Information Systems (GIS), in planning for Jakarta. Existing capacity in the use of GIS allows for consideration of the use of an emerging method of community consultation - Multi-Criteria Decision-Making (MCDM) support systems infused with geospatial information - to aid in engagement with the public and improve decision-making outcomes. While these methods have been used in Australia to promote stakeholder engagement in urban intensification, the planned research will be an early introduction of the method to Indonesia. As a consequence of this intervention, it is expected that planning activities will result in a more resilient city, capable of engaging with disaster risk management in a more effective manner.

Sensor Data Integrity : Multi-Sensor Perception for Unmanned Ground Vehicles

This document describes large, accurately calibrated and time-synchronised datasets, gathered in controlled environmental conditions, using an unmanned ground vehicle equipped with a wide variety of sensors. These sensors include: multiple laser scanners, a millimetre wave radar scanner, a colour camera and an infra-red camera. Full details of the sensors are given, as well as the calibration parameters needed to locate them with respect to each other and to the platform. This report also specifies the format and content of the data, and the conditions in which the data have been gathered. The data collection was made in two different situations of the vehicle: static and dynamic. The static tests consisted of sensing a fixed ’reference’ terrain, containing simple known objects, from a motionless vehicle. For the dynamic tests, data were acquired from a moving vehicle in various environments, mainly rural, including an open area, a semi-urban zone and a natural area with different types of vegetation. For both categories, data have been gathered in controlled environmental conditions, which included the presence of dust, smoke and rain. Most of the environments involved were static, except for a few specific datasets which involve the presence of a walking pedestrian. Finally, this document presents illustrations of the effects of adverse environmental conditions on sensor data, as a first step towards reliability and integrity in autonomous perceptual systems.

The Marulan data sets: multi-sensor perception in a natural environment with challenging conditions

In this paper we present large, accurately calibrated and time-synchronized data sets, gathered outdoors in controlled and variable environmental conditions, using an unmanned ground vehicle (UGV), equipped with a wide variety of sensors. These include four 2D laser scanners, a radar scanner, a color camera and an infrared camera. It provides a full description of the system used for data collection and the types of environments and conditions in which these data sets have been gathered, which include the presence of airborne dust, smoke and rain.

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.

Online self-supervised multi-instance segmentation of dynamic objects

This paper presents a method for the continuous segmentation of dynamic objects using only a vehicle mounted monocular camera without any prior knowledge of the object’s appearance. Prior work in online static/dynamic segmentation is extended to identify multiple instances of dynamic objects by introducing an unsupervised motion clustering step. These clusters are then used to update a multi-class classifier within a self-supervised framework. In contrast to many tracking-by-detection based methods, our system is able to detect dynamic objects without any prior knowledge of their visual appearance shape or location. Furthermore, the classifier is used to propagate labels of the same object in previous frames, which facilitates the continuous tracking of individual objects based on motion. The proposed system is evaluated using recall and false alarm metrics in addition to a new multi-instance labelled dataset to evaluate the performance of segmenting multiple instances of objects.

Multi-shot person re-identification via relational stein divergence

Person re-identification is particularly challenging due to significant appearance changes across separate camera views. In order to re-identify people, a representative human signature should effectively handle differences in illumination, pose and camera parameters. While general appearance-based methods are modelled in Euclidean spaces, it has been argued that some applications in image and video analysis are better modelled via non-Euclidean manifold geometry. To this end, recent approaches represent images as covariance matrices, and interpret such matrices as points on Riemannian manifolds. As direct classification on such manifolds can be difficult, in this paper we propose to represent each manifold point as a vector of similarities to class representers, via a recently introduced form of Bregman matrix divergence known as the Stein divergence. This is followed by using a discriminative mapping of similarity vectors for final classification. The use of similarity vectors is in contrast to the traditional approach of embedding manifolds into tangent spaces, which can suffer from representing the manifold structure inaccurately. Comparative evaluations on benchmark ETHZ and iLIDS datasets for the person re-identification task show that the proposed approach obtains better performance than recent techniques such as Histogram Plus Epitome, Partial Least Squares, and Symmetry-Driven Accumulation of Local Features.