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.

A pilot study on affective classification of facial images for emerging news topics

The proliferation of news reports published in online websites and news information sharing among social media users necessitates effective techniques for analysing the image, text and video data related to news topics. This paper presents the first study to classify affective facial images on emerging news topics. The proposed system dynamically monitors and selects the current hot (of great interest) news topics with strong affective interestingness using textual keywords in news articles and social media discussions. Images from the selected hot topics are extracted and classified into three categorized emotions, positive, neutral and negative, based on facial expressions of subjects in the images. Performance evaluations on two facial image datasets collected from real-world resources demonstrate the applicability and effectiveness of the proposed system in affective classification of facial images in news reports. Facial expression shows high consistency with the affective textual content in news reports for positive emotion, while only low correlation has been observed for neutral and negative. The system can be directly used for applications, such as assisting editors in choosing photos with a proper affective semantic for a certain topic during news report preparation.

Robotic explosive charging in mining and construction applications

Describes the development and testing of a robotic system for charging blast holes in underground mining. The automation system supports four main tactical functions: detection of blast holes; teleoperated arm pose control; automatic arm pose control; and human-in-the-loop visual servoing. We present the system architecture, and analyse the major components, Hole detection is crucial for automating the process, and we discuss theoretical and practical aspects in detail. The sensors used are laser range finders and cameras installed in the end effector. For automatic insertion, we consider image processing techniques to support visual servoing the tool to the hole. We also discuss issues surrounding the control of heavy-duty mining manipulators, in particular, friction, stiction, and actuator saturation.

Identifying weak linear features with the "coalescing shortest path image transform"

The detection of line-like features in images finds many applications in microanalysis. Actin fibers, microtubules, neurites, pilis, DNA, and other biological structures all come up as tenuous curved lines in microscopy images. A reliable tracing method that preserves the integrity and details of these structures is particularly important for quantitative analyses. We have developed a new image transform called the "Coalescing Shortest Path Image Transform" with very encouraging properties. Our scheme efficiently combines information from an extensive collection of shortest paths in the image to delineate even very weak linear features. © Copyright Microscopy Society of America 2011.

Capturing natural-colour 3D models of insects for species discovery and diagnostics

Collections of biological specimens are fundamental to scientific understanding and characterization of natural diversity - past, present and future. This paper presents a system for liberating useful information from physical collections by bringing specimens into the digital domain so they can be more readily shared, analyzed, annotated and compared. It focuses on insects and is strongly motivated by the desire to accelerate and augment current practices in insect taxonomy which predominantly use text, 2D diagrams and images to describe and characterize species. While these traditional kinds of descriptions are informative and useful, they cannot cover insect specimens "from all angles" and precious specimens are still exchanged between researchers and collections for this reason. Furthermore, insects can be complex in structure and pose many challenges to computer vision systems. We present a new prototype for a practical, cost-effective system of off-the-shelf components to acquire natural-colour 3D models of insects from around 3 mm to 30 mm in length. ("Natural-colour" is used to contrast with "false-colour", i.e., colour generated from, or applied to, gray-scale data post-acquisition.) Colour images are captured from different angles and focal depths using a digital single lens reflex (DSLR) camera rig and two-axis turntable. These 2D images are processed into 3D reconstructions using software based on a visual hull algorithm. The resulting models are compact (around 10 megabytes), afford excellent optical resolution, and can be readily embedded into documents and web pages, as well as viewed on mobile devices. The system is portable, safe, relatively affordable, and complements the sort of volumetric data that can be acquired by computed tomography. This system provides a new way to augment the description and documentation of insect species holotypes, reducing the need to handle or ship specimens. It opens up new opportunities to collect data for research, education, art, entertainment, biodiversity assessment and biosecurity control. © 2014 Nguyen et al.

Multi-modal deformable medical image registration

Non-rigid image registration is an essential tool required for overcoming the inherent local anatomical variations that exist between images acquired from different individuals or atlases. Furthermore, certain applications require this type of registration to operate across images acquired from different imaging modalities. One popular local approach for estimating this registration is a block matching procedure utilising the mutual information criterion. However, previous block matching procedures generate a sparse deformation field containing displacement estimates at uniformly spaced locations. This neglects to make use of the evidence that block matching results are dependent on the amount of local information content. This paper presents a solution to this drawback by proposing the use of a Reversible Jump Markov Chain Monte Carlo statistical procedure to optimally select grid points of interest. Three different methods are then compared to propagate the estimated sparse deformation field to the entire image including a thin-plate spline warp, Gaussian convolution, and a hybrid fluid technique. Results show that non-rigid registration can be improved by using the proposed algorithm to optimally select grid points of interest.

Adaptive online gradient descent

We study the rates of growth of the regret in online convex optimization. First, we show that a simple extension of the algorithm of Hazan et al eliminates the need for a priori knowledge of the lower bound on the second derivatives of the observed functions. We then provide an algorithm, Adaptive Online Gradient Descent, which interpolates between the results of Zinkevich for linear functions and of Hazan et al for strongly convex functions, achieving intermediate rates between [square root T] and [log T]. Furthermore, we show strong optimality of the algorithm. Finally, we provide an extension of our results to general norms.

Automatic surveillance in transportation hubs: No Longer just about catching the bad guy

As critical infrastructure such as transportation hubs continue to grow in complexity, greater importance is placed on monitoring these facilities to ensure their secure and efficient operation. In order to achieve these goals, technology continues to evolve in response to the needs of various infrastructure. To date, however, the focus of technology for surveillance has been primarily concerned with security, and little attention has been placed on assisting operations and monitoring performance in real-time. Consequently, solutions have emerged to provide real-time measurements of queues and crowding in spaces, but have been installed as system add-ons (rather than making better use of existing infrastructure), resulting in expensive infrastructure outlay for the owner/operator, and an overload of surveillance systems which in itself creates further complexity. Given many critical infrastructure already have camera networks installed, it is much more desirable to better utilise these networks to address operational monitoring as well as security needs. Recently, a growing number of approaches have been proposed to monitor operational aspects such as pedestrian throughput, crowd size and dwell times. In this paper, we explore how these techniques relate to and complement the more commonly seen security analytics, and demonstrate the value that can be added by operational analytics by demonstrating their performance on airport surveillance data. We explore how multiple analytics and systems can be combined to better leverage the large amount of data that is available, and we discuss the applicability and resulting benefits of the proposed framework for the ongoing operation of airports and airport networks.

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.

A non-linear analogue-to-digital converter for linearization of transducer input-output relationships

Analogue and digital techniques for linearization of non-linear input-output relationship of transducers are briefly reviewed. The condition required for linearizing a non-linear function y = f(x) using a non-linear analogue-to-digital converter, is explained. A simple technique to construct a non-linear digital-to-analogue converter, based on ' segments of equal digital interval ' is described. The technique was used to build an N-DAC which can be employed in a successive approximation or counter-ramp type ADC to linearize the non-linear transfer function of a thermistor-resistor combination. The possibility of achieving an order of magnitude higher accuracy in the measurement of temperature is shown.

Unsupervised Domain Adaptation by Domain Invariant Projection

Domain-invariant representations are key to addressing the domain shift problem where the training and test exam- ples follow different distributions. Existing techniques that have attempted to match the distributions of the source and target domains typically compare these distributions in the original feature space. This space, however, may not be di- rectly suitable for such a comparison, since some of the fea- tures may have been distorted by the domain shift, or may be domain specific. In this paper, we introduce a Domain Invariant Projection approach: An unsupervised domain adaptation method that overcomes this issue by extracting the information that is invariant across the source and tar- get domains. More specifically, we learn a projection of the data to a low-dimensional latent space where the distance between the empirical distributions of the source and target examples is minimized. We demonstrate the effectiveness of our approach on the task of visual object recognition and show that it outperforms state-of-the-art methods on a stan- dard domain adaptation benchmark dataset

Kuva tikkeinä kankaalla : Kokemuksia PE-design 6.0 -kirjontakuvion suunnitteluohjelman kahden automaattisen tekniikan käytettävyydestä

The aim of the thesis was to compare the correspondence of the outcome a computer assisted program appearance compared to the original image. The aspect of the study was directed to embroidery with household machines. The study was made from the usability point of view with Brother's PE-design 6.0 embroidery design programs two automatic techniques; multicoloured fragment design and multicoloured stitch surface design. The study's subject is very current because of the fast development of machine embroidery. The theory is based on history of household sewing machines, embroidery sewing machines, stitch types in household sewing machines, embroidery design programs as well as PE-design 6.0 embroidery design program's six automatic techniques. Additionally designing of embroidery designs were included: original image, digitizing, punching, applicable sewing threads as well as the connection between embroidery designs and materials used on embroidery. Correspondences of sewn appearances were examined with sewing experimental methods. 18 research samples of five original image were sewn with both techniques. Experiments were divided into four testing stages in design program. Every testing stage was followed by experimental sewing with Brother Super Galaxie 3100D embroidery machine. Experiments were reported into process files and forms made for the techniques. Research samples were analysed on images syntactic bases with sensory perception assessment. Original images and correspondence of the embroidery appearances were analysed with a form made of it. The form was divided into colour and shape assessment in five stage-similarity-scale. Based on this correspondence analysis it can be said that with both automatic techniques the best correspondence of colour and shape was achieved by changing the standard settings and using the makers own thread chart and edited original image. According to the testing made it is impossible to inform where the image editing possibilities of the images are sufficient or does the optimum correspondence need a separate program. When aiming at correspondence between appearances of two images the computer is unable to trace by itself the appearance of the original image. Processing a computer program assisted embroidery image human perception and personal decision making are unavoidable.

Automating Crop Damage Assessments with Unmanned Aerial Systems and Machine Learning

Agricultural pests are responsible for millions of dollars in crop losses and management costs every year. In order to implement optimal site-specific treatments and reduce control costs, new methods to accurately monitor and assess pest damage need to be investigated. In this paper we explore the combination of unmanned aerial vehicles (UAV), remote sensing and machine learning techniques as a promising methodology to address this challenge. The deployment of UAVs as a sensor platform is a rapidly growing field of study for biosecurity and precision agriculture applications. In this experiment, a data collection campaign is performed over a sorghum crop severely damaged by white grubs (Coleoptera: Scarabaeidae). The larvae of these scarab beetles feed on the roots of plants, which in turn impairs root exploration of the soil profile. In the field, crop health status could be classified according to three levels: bare soil where plants were decimated, transition zones of reduced plant density and healthy canopy areas. In this study, we describe the UAV platform deployed to collect high-resolution RGB imagery as well as the image processing pipeline implemented to create an orthoimage. An unsupervised machine learning approach is formulated in order to create a meaningful partition of the image into each of the crop levels. The aim of this approach is to simplify the image analysis step by minimizing user input requirements and avoiding the manual data labelling necessary in supervised learning approaches. The implemented algorithm is based on the K-means clustering algorithm. In order to control high-frequency components present in the feature space, a neighbourhood-oriented parameter is introduced by applying Gaussian convolution kernels prior to K-means clustering. The results show the algorithm delivers consistent decision boundaries that classify the field into three clusters, one for each crop health level as shown in Figure 1. The methodology presented in this paper represents a venue for further esearch towards automated crop damage assessments and biosecurity surveillance.

Näkövammaisten tietokoneavusteinen tiedon hankinta

The study examines various uses of computer technology in acquisition of information for visually impaired people. For this study 29 visually impaired persons took part in a survey about their experiences concerning acquisition of infomation and use of computers, especially with a screen magnification program, a speech synthesizer and a braille display. According to the responses, the evolution of computer technology offers an important possibility for visually impaired people to cope with everyday activities and interacting with the environment. Nevertheless, the functionality of assistive technology needs further development to become more usable and versatile. Since the challenges of independent observation of environment were emphasized in the survey, the study led into developing a portable text vision system called Tekstinäkö. Contrary to typical stand-alone applications, Tekstinäkö system was constructed by combining devices and programs that are readily available on consumer market. As the system operates, pictures are taken by a digital camera and instantly transmitted to a text recognition program in a laptop computer that talks out loud the text using a speech synthesizer. Visually impaired test users described that even unsure interpretations of the texts in the environment given by Tekstinäkö system are at least a welcome addition to complete perception of the environment. It became clear that even with a modest development work it is possible to bring new, useful and valuable methods to everyday life of disabled people. Unconventional production process of the system appeared to be efficient as well. Achieved results and the proposed working model offer one suggestion for giving enough attention to easily overlooked needs of the people with special abilities. ACM Computing Classification System (1998): K.4.2 Social Issues: Assistive technologies for persons with disabilities I.4.9 Image processing and computer vision: Applications Keywords: Visually impaired, computer-assisted, information, acquisition, assistive technology, computer, screen magnification program, speech synthesizer, braille display, survey, testing, text recognition, camera, text, perception, picture, environment, trasportation, guidance, independence, vision, disabled, blind, speech, synthesizer, braille, software engineering, programming, program, system, freeware, shareware, open source, Tekstinäkö, text vision, TopOCR, Autohotkey, computer engineering, computer science

Beyond Gauss: Image-set matching on the Riemannian manifold of PDFs

State-of-the-art image-set matching techniques typically implicitly model each image-set with a Gaussian distribution. Here, we propose to go beyond these representations and model image-sets as probability distribution functions (PDFs) using kernel density estimators. To compare and match image-sets, we exploit Csiszar´ f-divergences, which bear strong connections to the geodesic distance defined on the space of PDFs, i.e., the statistical manifold. Furthermore, we introduce valid positive definite kernels on the statistical manifold, which let us make use of more powerful classification schemes to match image-sets. Finally, we introduce a supervised dimensionality reduction technique that learns a latent space where f-divergences reflect the class labels of the data. Our experiments on diverse problems, such as video-based face recognition and dynamic texture classification, evidence the benefits of our approach over the state-of-the-art image-set matching methods.