Robust automatic face clustering in news video

Clustering identities in a video is a useful task to aid in video search, annotation and retrieval, and cast identification. However, reliably clustering faces across multiple videos is challenging task due to variations in the appearance of the faces, as videos are captured in an uncontrolled environment. A person's appearance may vary due to session variations including: lighting and background changes, occlusions, changes in expression and make up. In this paper we propose the novel Local Total Variability Modelling (Local TVM) approach to cluster faces across a news video corpus; and incorporate this into a novel two stage video clustering system. We first cluster faces within a single video using colour, spatial and temporal cues; after which we use face track modelling and hierarchical agglomerative clustering to cluster faces across the entire corpus. We compare different face recognition approaches within this framework. Experiments on a news video database show that the Local TVM technique is able effectively model the session variation observed in the data, resulting in improved clustering performance, with much greater computational efficiency than other methods.

Class-specific sparse codes for representing activities

In this paper we investigate the effectiveness of class specific sparse codes in the context of discriminative action classification. The bag-of-words representation is widely used in activity recognition to encode features, and although it yields state-of-the art performance with several feature descriptors it still suffers from large quantization errors and reduces the overall performance. Recently proposed sparse representation methods have been shown to effectively represent features as a linear combination of an over complete dictionary by minimizing the reconstruction error. In contrast to most of the sparse representation methods which focus on Sparse-Reconstruction based Classification (SRC), this paper focuses on a discriminative classification using a SVM by constructing class-specific sparse codes for motion and appearance separately. Experimental results demonstrates that separate motion and appearance specific sparse coefficients provide the most effective and discriminative representation for each class compared to a single class-specific sparse coefficients.

Towards web-based semantic enrichment of 3D insects

Natural history collections are an invaluable resource housing a wealth of knowledge with a long tradition of contributing to a wide range of fields such as taxonomy, quarantine, conservation and climate change. It is recognized however [Smith and Blagoderov 2012] that such physical collections are often heavily underutilized as a result of the practical issues of accessibility. The digitization of these collections is a step towards removing these access issues, but other hurdles must be addressed before we truly unlock the potential of this knowledge.

Visual detection of occluded crop: For automated harvesting

This paper presents a novel crop detection system applied to the challenging task of field sweet pepper (capsicum) detection. The field-grown sweet pepper crop presents several challenges for robotic systems such as the high degree of occlusion and the fact that the crop can have a similar colour to the background (green on green). To overcome these issues, we propose a two-stage system that performs per-pixel segmentation followed by region detection. The output of the segmentation is used to search for highly probable regions and declares these to be sweet pepper. We propose the novel use of the local binary pattern (LBP) to perform crop segmentation. This feature improves the accuracy of crop segmentation from an AUC of 0.10, for previously proposed features, to 0.56. Using the LBP feature as the basis for our two-stage algorithm, we are able to detect 69.2% of field grown sweet peppers in three sites. This is an impressive result given that the average detection accuracy of people viewing the same colour imagery is 66.8%.

Automatic wildfire detection and simulation using optical information from unmanned aerial systems

In many parts of the world, uncontrolled fires in sparsely populated areas are a major concern as they can quickly grow into large and destructive conflagrations in short time spans. Detecting these fires has traditionally been a job for trained humans on the ground, or in the air. In many cases, these manned solutions are simply not able to survey the amount of area necessary to maintain sufficient vigilance and coverage. This paper investigates the use of unmanned aerial systems (UAS) for automated wildfire detection. The proposed system uses low-cost, consumer-grade electronics and sensors combined with various airframes to create a system suitable for automatic detection of wildfires. The system employs automatic image processing techniques to analyze captured images and autonomously detect fire-related features such as fire lines, burnt regions, and flammable material. This image recognition algorithm is designed to cope with environmental occlusions such as shadows, smoke and obstructions. Once the fire is identified and classified, it is used to initialize a spatial/temporal fire simulation. This simulation is based on occupancy maps whose fidelity can be varied to include stochastic elements, various types of vegetation, weather conditions, and unique terrain. The simulations can be used to predict the effects of optimized firefighting methods to prevent the future propagation of the fires and greatly reduce time to detection of wildfires, thereby greatly minimizing the ensuing damage. This paper also documents experimental flight tests using a SenseFly Swinglet UAS conducted in Brisbane, Australia as well as modifications for custom UAS.

Deploying speaker verification techniques to vision-based RPA detect and avoid

Detect and Avoid (DAA) technology is widely acknowledged as a critical enabler for unsegregated Remote Piloted Aircraft (RPA) operations, particularly Beyond Visual Line of Sight (BVLOS). Image-based DAA, in the visible spectrum, is a promising technological option for addressing the challenges DAA presents. Two impediments to progress for this approach are the scarcity of available video footage to train and test algorithms, in conjunction with testing regimes and specifications which facilitate repeatable, statistically valid, performance assessment. This paper includes three key contributions undertaken to address these impediments. In the first instance, we detail our progress towards the creation of a large hybrid collision and near-collision encounter database. Second, we explore the suitability of techniques employed by the biometric research community (Speaker Verification and Language Identification), for DAA performance optimisation and assessment. These techniques include Detection Error Trade-off (DET) curves, Equal Error Rates (EER), and the Detection Cost Function (DCF). Finally, the hybrid database and the speech-based techniques are combined and employed in the assessment of a contemporary, image based DAA system. This system includes stabilisation, morphological filtering and a Hidden Markov Model (HMM) temporal filter.

Genetic programming metamodel for rotating beams

This paper investigates the use of Genetic Programming (GP) to create an approximate model for the non-linear relationship between flexural stiffness, length, mass per unit length and rotation speed associated with rotating beams and their natural frequencies. GP, a relatively new form of artificial intelligence, is derived from the Darwinian concept of evolution and genetics and it creates computer programs to solve problems by manipulating their tree structures. GP predicts the size and structural complexity of the empirical model by minimizing the mean square error at the specified points of input-output relationship dataset. This dataset is generated using a finite element model. The validity of the GP-generated model is tested by comparing the natural frequencies at training and at additional input data points. It is found that by using a non-dimensional stiffness, it is possible to get simple and accurate function approximation for the natural frequency. This function approximation model is then used to study the relationships between natural frequency and various influencing parameters for uniform and tapered beams. The relations obtained with GP model agree well with FEM results and can be used for preliminary design and structural optimization studies.

Solution of MDPS using simulation-based value iteration

This article proposes a three-timescale simulation based algorithm for solution of infinite horizon Markov Decision Processes (MDPs). We assume a finite state space and discounted cost criterion and adopt the value iteration approach. An approximation of the Dynamic Programming operator T is applied to the value function iterates. This 'approximate' operator is implemented using three timescales, the slowest of which updates the value function iterates. On the middle timescale we perform a gradient search over the feasible action set of each state using Simultaneous Perturbation Stochastic Approximation (SPSA) gradient estimates, thus finding the minimizing action in T. On the fastest timescale, the 'critic' estimates, over which the gradient search is performed, are obtained. A sketch of convergence explaining the dynamics of the algorithm using associated ODEs is also presented. Numerical experiments on rate based flow control on a bottleneck node using a continuous-time queueing model are performed using the proposed algorithm. The results obtained are verified against classical value iteration where the feasible set is suitably discretized. Over such a discretized setting, a variant of the algorithm of [12] is compared and the proposed algorithm is found to converge faster.

Investigating novelty-outcome relationships in engineering design

Design creativity involves developing novel and useful solutions to design problems The research in this article is an attempt to understand how novelty of a design resulting from a design process is related to the kind of outcomes. described here as constructs, involved in the design process A model of causality, the SAPPhIRE model, is used as the basis of the analysis The analysis is based on previous research that shows that designing involves development and exploration of the seven basic constructs of the SAPPhIRE model that constitute the causal connection between the various levels of abstraction at which a design can be described The constructs am state change, action, parts. phenomenon. input. organs. and effect The following two questions are asked. Is there a relationship between novelty and the constructs? If them is a relationship, what is the degree of this relationship? A hypothesis is developed to answer the questions an increase in the number and variety of ideas explored while designing should enhance the variety of concept space. leading to an increase in the novelty of the concept space Eight existing observational studies of designing sessions are used to empirically validate the hypothesis Each designing session involves an individual designer. experienced or novice. solving a design problem by producing concepts and following a think-aloud protocol. The results indicate dependence of novelty of concept space on variety of concept space and dependence of variety of concept space on variety of idea space. thereby validating the hypothesis The Jesuits also reveal a strong correlation between novelty and the constructs, correlation value decreases as the abstraction level of the constructs reduces. signifying the importance of using constructs at higher abstraction levels for enhancing novelty

A course for teaching design research methodology

Design research informs and supports practice by developing knowledge to improve the chances of producing successful products.Training in design research has been poorly supported. Design research uses human and natural/technical sciences, embracing all facets of design; its methods and tools are adapted from both these traditions. However, design researchers are rarely trained in methods from both the traditions. Research in traditional sciences focuses primarily on understanding phenomena related to human, natural, or technical systems. Design research focuses on supporting improvement of such systems, using understanding as a necessary but not sufficient step, and it must embrace methods for both understanding reality and developing support for its improvement. A one-semester, postgraduate-level, credited course that has been offered since 2002, entitled Methodology for Design Research, is described that teaches a methodology for carrying out research into design. Its steps are to clarify research success; to understand relevant phenomena of design and how these influence success; to use this to envision design improvement and develop proposals for supporting improvement; to evaluate support for its influence on success; and, if unacceptable, to modify, support, or improve the understanding of success and its links to the phenomena of design. This paper highlights some major issues about the status of design research and describes how design research methodology addresses these. The teaching material, model of delivery, and evaluation of the course on methodology for design research are discussed.

A methodology for supporting ``transfer'' in biomimetic design

Biomimetics involves transfer from one or more biological examples to a technical system. This study addresses four questions. What are the essential steps in a biomimetic process? What is transferred? How can the transferred knowledge be structured in a way useful for biologists and engineers? Which guidelines can be given to support transfer in biomimetic design processes? In order to identify the essential steps involved in carrying out biomimetics, several procedures found in the literature were summarized, and four essential steps that are common across these procedures were identified. For identification of mechanisms for transfer, 20 biomimetic examples were collected and modeled according to a model. of causality called the SAPPhIRE model. These examples were then analyzed for identifying the underlying similarity between each biological and corresponding analogue technical system. Based on the SAPPhIRE model, four levels of abstraction at which transfer takes place were identified. Taking into account similarity, the biomimetic examples were assigned to the appropriate levels of abstraction of transfer. Based on the essential steps and the levels of transfer, guidelines for supporting transfer in biomimetic design were proposed and evaluated using design experiments. The 20 biological and analogue technical systems that were analyzed were similar in the physical effects used and at the most abstract levels of description of their functionality, but they were the least similar at the lowest levels of abstraction: the parts involved. Transfer most often was carried out at the physical effect level of abstraction. Compared to a generic set of guidelines based on the literature, the proposed guidelines improved design performance by about 60%. Further, the SAPPhIRE model turned out to be a useful representation for modeling complex biological systems and their functionality. Databases of biological systems, which are structured using the SAPPhIRE model, have the potential to aid biomimetic concept generation.

Control of Agent Swarms using Generalized Centroidal Cyclic Pursuit Laws

One of the major tasks in swarm intelligence is to design decentralized but homogenoeus strategies to enable controlling the behaviour of swarms of agents. It has been shown in the literature that the point of convergence and motion of a swarm of autonomous mobile agents can be controlled by using cyclic pursuit laws. In cyclic pursuit, there exists a predefined cyclic connection between agents and each agent pursues the next agent in the cycle. In this paper we generalize this idea to a case where an agent pursues a point which is the weighted average of the positions of the remaining agents. This point correspond to a particular pursuit sequence. Using this concept of centroidal cyclic pursuit, the behavior of the agents is analyzed such that, by suitably selecting the agents' gain, the rendezvous point of the agents can be controlled, directed linear motion of the agents can be achieved, and the trajectories of the agents can be changed by switching between the pursuit sequences keeping some of the behaviors of the agents invariant. Simulation experiments are given to support the analytical proofs.

Performance of the generalized delta rule in structural damage detection

The paper examines the suitability of the generalized data rule in training artificial neural networks (ANN) for damage identification in structures. Several multilayer perceptron architectures are investigated for a typical bridge truss structure with simulated damage stares generated randomly. The training samples have been generated in terms of measurable structural parameters (displacements and strains) at suitable selected locations in the structure. Issues related to the performance of the network with reference to hidden layers and hidden. neurons are examined. Some heuristics are proposed for the design of neural networks for damage identification in structures. These are further supported by an investigation conducted on five other bridge truss configurations.