Automating marine mammal detection in aerial images captured during wildlife surveys: A deep learning approach

Aerial surveys conducted using manned or unmanned aircraft with customized camera payloads can generate a large number of images. Manual review of these images to extract data is prohibitive in terms of time and financial resources, thus providing strong incentive to automate this process using computer vision systems. There are potential applications for these automated systems in areas such as surveillance and monitoring, precision agriculture, law enforcement, asset inspection, and wildlife assessment. In this paper, we present an efficient machine learning system for automating the detection of marine species in aerial imagery. The effectiveness of our approach can be credited to the combination of a well-suited region proposal method and the use of Deep Convolutional Neural Networks (DCNNs). In comparison to previous algorithms designed for the same purpose, we have been able to dramatically improve recall to more than 80% and improve precision to 27% by using DCNNs as the core approach.

From vision to actions: Towards adaptive and autonomous humanoid robots

Although robotics research has seen advances over the last decades robots are still not in widespread use outside industrial applications. Yet a range of proposed scenarios have robots working together, helping and coexisting with humans in daily life. In all these a clear need to deal with a more unstructured, changing environment arises. I herein present a system that aims to overcome the limitations of highly complex robotic systems, in terms of autonomy and adaptation. The main focus of research is to investigate the use of visual feedback for improving reaching and grasping capabilities of complex robots. To facilitate this a combined integration of computer vision and machine learning techniques is employed. From a robot vision point of view the combination of domain knowledge from both imaging processing and machine learning techniques, can expand the capabilities of robots. I present a novel framework called Cartesian Genetic Programming for Image Processing (CGP-IP). CGP-IP can be trained to detect objects in the incoming camera streams and successfully demonstrated on many different problem domains. The approach requires only a few training images (it was tested with 5 to 10 images per experiment) is fast, scalable and robust yet requires very small training sets. Additionally, it can generate human readable programs that can be further customized and tuned. While CGP-IP is a supervised-learning technique, I show an integration on the iCub, that allows for the autonomous learning of object detection and identification. Finally this dissertation includes two proof-of-concepts that integrate the motion and action sides. First, reactive reaching and grasping is shown. It allows the robot to avoid obstacles detected in the visual stream, while reaching for the intended target object. Furthermore the integration enables us to use the robot in non-static environments, i.e. the reaching is adapted on-the- fly from the visual feedback received, e.g. when an obstacle is moved into the trajectory. The second integration highlights the capabilities of these frameworks, by improving the visual detection by performing object manipulation actions.

Enhancing human action recognition with region proposals

Deep convolutional network models have dominated recent work in human action recognition as well as image classification. However, these methods are often unduly influenced by the image background, learning and exploiting the presence of cues in typical computer vision datasets. For unbiased robotics applications, the degree of variation and novelty in action backgrounds is far greater than in computer vision datasets. To address this challenge, we propose an “action region proposal” method that, informed by optical flow, extracts image regions likely to contain actions for input into the network both during training and testing. In a range of experiments, we demonstrate that manually segmenting the background is not enough; but through active action region proposals during training and testing, state-of-the-art or better performance can be achieved on individual spatial and temporal video components. Finally, we show by focusing attention through action region proposals, we can further improve upon the existing state-of-the-art in spatio-temporally fused action recognition performance.

Formal description, compression and transformation of digital pictures

This paper describes the application of vector spaces over Galois fields, for obtaining a formal description of a picture in the form of a very compact, non-redundant, unique syntactic code. Two different methods of encoding are described. Both these methods consist in identifying the given picture as a matrix (called picture matrix) over a finite field. In the first method, the eigenvalues and eigenvectors of this matrix are obtained. The eigenvector expansion theorem is then used to reconstruct the original matrix. If several of the eigenvalues happen to be zero this scheme results in a considerable compression. In the second method, the picture matrix is reduced to a primitive diagonal form (Hermite canonical form) by elementary row and column transformations. These sequences of elementary transformations constitute a unique and unambiguous syntactic code-called Hermite code—for reconstructing the picture from the primitive diagonal matrix. A good compression of the picture results, if the rank of the matrix is considerably lower than its order. An important aspect of this code is that it preserves the neighbourhood relations in the picture and the primitive remains invariant under translation, rotation, reflection, enlargement and replication. It is also possible to derive the codes for these transformed pictures from the Hermite code of the original picture by simple algebraic manipulation. This code will find extensive applications in picture compression, storage, retrieval, transmission and in designing pattern recognition and artificial intelligence systems.

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.

Scalable fault tolerant agent grooming environment-SAGE

Multi-agent systems (MAS) advocate an agent-based approach to software engineering based on decomposing problems in terms of decentralized, autonomous agents that can engage in flexible, high-level interactions. This chapter introduces scalable fault tolerant agent grooming environment (SAGE), a second-generation Foundation for Intelligent Physical Agents (FIPA)-compliant multi-agent system developed at NIIT-Comtec, which provides an environment for creating distributed, intelligent, and autonomous entities that are encapsulated as agents. The chapter focuses on the highlight of SAGE, which is its decentralized fault-tolerant architecture that can be used to develop applications in a number of areas such as e-health, e-government, and e-science. In addition, SAGE architecture provides tools for runtime agent management, directory facilitation, monitoring, and editing messages exchange between agents. SAGE also provides a built-in mechanism to program agent behavior and their capabilities with the help of its autonomous agent architecture, which is the other major highlight of this chapter. The authors believe that the market for agent-based applications is growing rapidly, and SAGE can play a crucial role for future intelligent applications development. © 2007, IGI Global.

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%.

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.

Nash equilibrium based semantic cache in mobile sensor grid database systems

Mobile applications are being increasingly deployed on a massive scale in various mobile sensor grid database systems. With limited resources from the mobile devices, how to process the huge number of queries from mobile users with distributed sensor grid databases becomes a critical problem for such mobile systems. While the fundamental semantic cache technique has been investigated for query optimization in sensor grid database systems, the problem is still difficult due to the fact that more realistic multi-dimensional constraints have not been considered in existing methods. To solve the problem, a new semantic cache scheme is presented in this paper for location-dependent data queries in distributed sensor grid database systems. It considers multi-dimensional constraints or factors in a unified cost model architecture, determines the parameters of the cost model in the scheme by using the concept of Nash equilibrium from game theory, and makes semantic cache decisions from the established cost model. The scenarios of three factors of semantic, time and locations are investigated as special cases, which improve existing methods. Experiments are conducted to demonstrate the semantic cache scheme presented in this paper for distributed sensor grid database systems.

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.

A survey of indian logic from the point of view of computer science

Indian logic has a long history. It somewhat covers the domains of two of the six schools (darsanas) of Indian philosophy, namely, Nyaya and Vaisesika. The generally accepted definition of Indian logic over the ages is the science which ascertains valid knowledge either by means of six senses or by means of the five members of the syllogism. In other words, perception and inference constitute the subject matter of logic. The science of logic evolved in India through three ages: the ancient, the medieval and the modern, spanning almost thirty centuries. Advances in Computer Science, in particular, in Artificial Intelligence have got researchers in these areas interested in the basic problems of language, logic and cognition in the past three decades. In the 1980s, Artificial Intelligence has evolved into knowledge-based and intelligent system design, and the knowledge base and inference engine have become standard subsystems of an intelligent system. One of the important issues in the design of such systems is knowledge acquisition from humans who are experts in a branch of learning (such as medicine or law) and transferring that knowledge to a computing system. The second important issue in such systems is the validation of the knowledge base of the system i.e. ensuring that the knowledge is complete and consistent. It is in this context that comparative study of Indian logic with recent theories of logic, language and knowledge engineering will help the computer scientist understand the deeper implications of the terms and concepts he is currently using and attempting to develop.

A GIS (geographical information system)-based spatial data mining approach for optimal location and capacity planning of distributed biomass power generation facilities: A case study of Tumkur district, India

This paper primarily intends to develop a GIS (geographical information system)-based data mining approach for optimally selecting the locations and determining installed capacities for setting up distributed biomass power generation systems in the context of decentralized energy planning for rural regions. The optimal locations within a cluster of villages are obtained by matching the installed capacity needed with the demand for power, minimizing the cost of transportation of biomass from dispersed sources to power generation system, and cost of distribution of electricity from the power generation system to demand centers or villages. The methodology was validated by using it for developing an optimal plan for implementing distributed biomass-based power systems for meeting the rural electricity needs of Tumkur district in India consisting of 2700 villages. The approach uses a k-medoid clustering algorithm to divide the total region into clusters of villages and locate biomass power generation systems at the medoids. The optimal value of k is determined iteratively by running the algorithm for the entire search space for different values of k along with demand-supply matching constraints. The optimal value of the k is chosen such that it minimizes the total cost of system installation, costs of transportation of biomass, and transmission and distribution. A smaller region, consisting of 293 villages was selected to study the sensitivity of the results to varying demand and supply parameters. The results of clustering are represented on a GIS map for the region.