Aggregating Local Descriptors for Epigraphs Recognition

In this paper, we consider the task of recognizing epigraphs in images such as photos taken using mobile devices. Given a set of 17,155 photos related to 14,560 epigraphs, we used a k-NearestNeighbor approach in order to perform the recognition. The contribution of this work is in evaluating state-of-the-art visual object recognition techniques in this specific context. The experimental results conducted show that Vector of Locally Aggregated Descriptors obtained aggregating SIFT descriptors is the best choice for this task.

Mid-level concept learning with visual contextual ontologies and probabilistic inference for image annotation

To date, automatic recognition of semantic information such as salient objects and mid-level concepts from images is a challenging task. Since real-world objects tend to exist in a context within their environment, the computer vision researchers have increasingly incorporated contextual information for improving object recognition. In this paper, we present a method to build a visual contextual ontology from salient objects descriptions for image annotation. The ontologies include not only partOf/kindOf relations, but also spatial and co-occurrence relations. A two-step image annotation algorithm is also proposed based on ontology relations and probabilistic inference. Different from most of the existing work, we specially exploit how to combine representation of ontology, contextual knowledge and probabilistic inference. The experiments show that image annotation results are improved in the LabelMe dataset.

A global vision system for a robot soccer team

This paper describes the real time global vision system for the robot soccer team the RoboRoos. It has a highly optimised pipeline that includes thresholding, segmenting, colour normalising, object recognition and perspective and lens correction. It has a fast ‘paint’ colour calibration system that can calibrate in any face of the YUV or HSI cube. It also autonomously selects both an appropriate camera gain and colour gains robot regions across the field to achieve colour uniformity. Camera geometry calibration is performed automatically from selection of keypoints on the field. The system achieves a position accuracy of better than 15mm over a 4m × 5.5m field, and orientation accuracy to within 1°. It processes 614 × 480 pixels at 60Hz on a 2.0GHz Pentium 4 microprocessor.

Unsupervised alignment of thousands of images

The task addressed in this thesis is the automatic alignment of an ensemble of misaligned images in an unsupervised manner. This application is especially useful in computer vision applications where annotations of the shape of an object of interest present in a collection of images is required. Performing this task manually is a slow, tedious, expensive and error prone process which hinders the progress of research laboratories and businesses. Most recently, the unsupervised removal of geometric variation present in a collection of images has been referred to as congealing based on the seminal work of Learned-Miller [21]. The only assumption made in congealing is that the parametric nature of the misalignment is known a priori (e.g. translation, similarity, a�ne, etc) and that the object of interest is guaranteed to be present in each image. The capability to congeal an ensemble of misaligned images stemming from the same object class has numerous applications in object recognition, detection and tracking. This thesis concerns itself with the construction of a congealing algorithm titled, least-squares congealing, which is inspired by the well known image to image alignment algorithm developed by Lucas and Kanade [24]. The algorithm is shown to have superior performance characteristics when compared to previously established methods: canonical congealing by Learned-Miller [21] and stochastic congealing by Z�ollei [39].

Ontology-based image annotation

With regard to the long-standing problem of the semantic gap between low-level image features and high-level human knowledge, the image retrieval community has recently shifted its emphasis from low-level features analysis to high-level image semantics extrac- tion. User studies reveal that users tend to seek information using high-level semantics. Therefore, image semantics extraction is of great importance to content-based image retrieval because it allows the users to freely express what images they want. Semantic content annotation is the basis for semantic content retrieval. The aim of image anno- tation is to automatically obtain keywords that can be used to represent the content of images. The major research challenges in image semantic annotation are: what is the basic unit of semantic representation? how can the semantic unit be linked to high-level image knowledge? how can the contextual information be stored and utilized for image annotation? In this thesis, the Semantic Web technology (i.e. ontology) is introduced to the image semantic annotation problem. Semantic Web, the next generation web, aims at mak- ing the content of whatever type of media not only understandable to humans but also to machines. Due to the large amounts of multimedia data prevalent on the Web, re- searchers and industries are beginning to pay more attention to the Multimedia Semantic Web. The Semantic Web technology provides a new opportunity for multimedia-based applications, but the research in this area is still in its infancy. Whether ontology can be used to improve image annotation and how to best use ontology in semantic repre- sentation and extraction is still a worth-while investigation. This thesis deals with the problem of image semantic annotation using ontology and machine learning techniques in four phases as below. 1) Salient object extraction. A salient object servers as the basic unit in image semantic extraction as it captures the common visual property of the objects. Image segmen- tation is often used as the �rst step for detecting salient objects, but most segmenta- tion algorithms often fail to generate meaningful regions due to over-segmentation and under-segmentation. We develop a new salient object detection algorithm by combining multiple homogeneity criteria in a region merging framework. 2) Ontology construction. Since real-world objects tend to exist in a context within their environment, contextual information has been increasingly used for improving object recognition. In the ontology construction phase, visual-contextual ontologies are built from a large set of fully segmented and annotated images. The ontologies are composed of several types of concepts (i.e. mid-level and high-level concepts), and domain contextual knowledge. The visual-contextual ontologies stand as a user-friendly interface between low-level features and high-level concepts. 3) Image objects annotation. In this phase, each object is labelled with a mid-level concept in ontologies. First, a set of candidate labels are obtained by training Support Vectors Machines with features extracted from salient objects. After that, contextual knowledge contained in ontologies is used to obtain the �nal labels by removing the ambiguity concepts. 4) Scene semantic annotation. The scene semantic extraction phase is to get the scene type by using both mid-level concepts and domain contextual knowledge in ontologies. Domain contextual knowledge is used to create scene con�guration that describes which objects co-exist with which scene type more frequently. The scene con�guration is represented in a probabilistic graph model, and probabilistic inference is employed to calculate the scene type given an annotated image. To evaluate the proposed methods, a series of experiments have been conducted in a large set of fully annotated outdoor scene images. These include a subset of the Corel database, a subset of the LabelMe dataset, the evaluation dataset of localized semantics in images, the spatial context evaluation dataset, and the segmented and annotated IAPR TC-12 benchmark.

Toward automated power line corridor monitoring using advanced aircraft control and multisource feature fusion

The conventional manual power line corridor inspection processes that are used by most energy utilities are labor-intensive, time consuming and expensive. Remote sensing technologies represent an attractive and cost-effective alternative approach to these monitoring activities. This paper presents a comprehensive investigation into automated remote sensing based power line corridor monitoring, focusing on recent innovations in the area of increased automation of fixed-wing platforms for aerial data collection, and automated data processing for object recognition using a feature fusion process. Airborne automation is achieved by using a novel approach that provides improved lateral control for tracking corridors and automatic real-time dynamic turning for flying between corridor segments, we call this approach PTAGS. Improved object recognition is achieved by fusing information from multi-sensor (LiDAR and imagery) data and multiple visual feature descriptors (color and texture). The results from our experiments and field survey illustrate the effectiveness of the proposed aircraft control and feature fusion approaches.

V1-inspired features induce a weighted margin in SVMs

Image representations derived from simplified models of the primary visual cortex (V1), such as HOG and SIFT, elicit good performance in a myriad of visual classification tasks including object recognition/detection, pedestrian detection and facial expression classification. A central question in the vision, learning and neuroscience communities regards why these architectures perform so well. In this paper, we offer a unique perspective to this question by subsuming the role of V1-inspired features directly within a linear support vector machine (SVM). We demonstrate that a specific class of such features in conjunction with a linear SVM can be reinterpreted as inducing a weighted margin on the Kronecker basis expansion of an image. This new viewpoint on the role of V1-inspired features allows us to answer fundamental questions on the uniqueness and redundancies of these features, and offer substantial improvements in terms of computational and storage efficiency.

Modelling users' contextual querying behaviour for web image searching

The rapid growth of visual information on Web has led to immense interest in multimedia information retrieval (MIR). While advancement in MIR systems has achieved some success in specific domains, particularly the content-based approaches, general Web users still struggle to find the images they want. Despite the success in content-based object recognition or concept extraction, the major problem in current Web image searching remains in the querying process. Since most online users only express their needs in semantic terms or objects, systems that utilize visual features (e.g., color or texture) to search images create a semantic gap which hinders general users from fully expressing their needs. In addition, query-by-example (QBE) retrieval imposes extra obstacles for exploratory search because users may not always have the representative image at hand or in mind when starting a search (i.e. the page zero problem). As a result, the majority of current online image search engines (e.g., Google, Yahoo, and Flickr) still primarily use textual queries to search. The problem with query-based retrieval systems is that they only capture users’ information need in terms of formal queries;; the implicit and abstract parts of users’ information needs are inevitably overlooked. Hence, users often struggle to formulate queries that best represent their needs, and some compromises have to be made. Studies of Web search logs suggest that multimedia searches are more difficult than textual Web searches, and Web image searching is the most difficult compared to video or audio searches. Hence, online users need to put in more effort when searching multimedia contents, especially for image searches. Most interactions in Web image searching occur during query reformulation. While log analysis provides intriguing views on how the majority of users search, their search needs or motivations are ultimately neglected. User studies on image searching have attempted to understand users’ search contexts in terms of users’ background (e.g., knowledge, profession, motivation for search and task types) and the search outcomes (e.g., use of retrieved images, search performance). However, these studies typically focused on particular domains with a selective group of professional users. General users’ Web image searching contexts and behaviors are little understood although they represent the majority of online image searching activities nowadays. We argue that only by understanding Web image users’ contexts can the current Web search engines further improve their usefulness and provide more efficient searches. In order to understand users’ search contexts, a user study was conducted based on university students’ Web image searching in News, Travel, and commercial Product domains. The three search domains were deliberately chosen to reflect image users’ interests in people, time, event, location, and objects. We investigated participants’ Web image searching behavior, with the focus on query reformulation and search strategies. Participants’ search contexts such as their search background, motivation for search, and search outcomes were gathered by questionnaires. The searching activity was recorded with participants’ think aloud data for analyzing significant search patterns. The relationships between participants’ search contexts and corresponding search strategies were discovered by Grounded Theory approach. Our key findings include the following aspects: - Effects of users' interactive intents on query reformulation patterns and search strategies - Effects of task domain on task specificity and task difficulty, as well as on some specific searching behaviors - Effects of searching experience on result expansion strategies A contextual image searching model was constructed based on these findings. The model helped us understand Web image searching from user perspective, and introduced a context-aware searching paradigm for current retrieval systems. A query recommendation tool was also developed to demonstrate how users’ query reformulation contexts can potentially contribute to more efficient searching.

Did you see that? Dissociating advanced visual information and ball flight constrains perception and action processes during one-handed catching

The integration of separate, yet complimentary, cortical pathways appears to play a role in visual perception and action when intercepting objects. The ventral system is responsible for object recognition and identification, while the dorsal system facilitates continuous regulation of action. This dual-system model implies that empirically manipulating different visual information sources during performance of an interceptive action might lead to the emergence of distinct gaze and movement pattern profiles. To test this idea, we recorded hand kinematics and eye movements of participants as they attempted to catch balls projected from a novel apparatus that synchronised or de-synchronised accompanying video images of a throwing action and ball trajectory. Results revealed that ball catching performance was less successful when patterns of hand movements and gaze behaviours were constrained by the absence of advanced perceptual information from the thrower's actions. Under these task constraints, participants began tracking the ball later, followed less of its trajectory, and adapted their actions by initiating movements later and moving the hand faster. There were no performance differences when the throwing action image and ball speed were synchronised or de-synchronised since hand movements were closely linked to information from ball trajectory. Results are interpreted relative to the two-visual system hypothesis, demonstrating that accurate interception requires integration of advanced visual information from kinematics of the throwing action and from ball flight trajectory.

Tools for Mobile Multimedia Programming and Development

Mobile devices are rapidly developing into the primary technology for users to work, socialize, and play in a variety of settings and contexts. Their pervasiveness has provided researchers with the means to investigate innovative solutions to ever more complex user demands. Tools for Mobile Multimedia Programming and Development investigates the use of mobile platforms for research projects, focusing on the development, testing, and evaluation of prototypes rather than final products, which enables researchers to better understand the needs of users through image processing, object recognition, sensor integration, and user interactions. This book benefits researchers and professionals in multiple disciplines who utilize such techniques in the creation of prototypes for mobile devices and applications. This book is part of the Advances in Wireless Technologies and Telecommunication series collection.

Developing grounded representations for robots through the principles of sensorimotor coordination

Robots currently recognise and use objects through algorithms that are hand-coded or specifically trained. Such robots can operate in known, structured environments but cannot learn to recognise or use novel objects as they appear. This thesis demonstrates that a robot can develop meaningful object representations by learning the fundamental relationship between action and change in sensory state; the robot learns sensorimotor coordination. Methods based on Markov Decision Processes are experimentally validated on a mobile robot capable of gripping objects, and it is found that object recognition and manipulation can be learnt as an emergent property of sensorimotor coordination.

Reflexive and automatic violence: A function of aberrant perceptual inhibition

It’s commonly assumed that psychiatric violence is motivated by delusions, but here the concept of a reversed impetus is explored, to understand whether delusions are formed as ad-hoc or post-hoc rationalizations of behaviour or in advance of the actus reus. The reflexive violence model proposes that perceptual stimuli has motivational power and this may trigger unwanted actions and hallucinations. The model is based on the theory of ecological perception, where opportunities enabled by an object are cues to act. As an apple triggers a desire to eat, a gun triggers a desire to shoot. These affordances (as they are called) are part of the perceptual apparatus, they allow the direct recognition of objects – and in emergencies they enable the fastest possible reactions. Even under normal circumstances, the presence of a weapon will trigger inhibited violent impulses. The presence of a victim will also, but under normal circumstances, these affordances don’t become violent because negative action impulses are totally inhibited, whereas in psychotic illness, negative action impulses are treated as emergencies and bypass frontal inhibitory circuits. What would have been object recognition becomes a blind automatic action. A range of mental illnesses can cause inhibition to be bypassed. At its most innocuous, this causes both simple hallucinations (where the motivational power of an object is misattributed). But ecological perception may have the power to trigger serious violence also –a kind that’s devoid of motives or planning and is often shrouded in amnesia or post-rational delusions.

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

Domain Adaptation on the Statistical Manifold

In this paper, we tackle the problem of unsupervised domain adaptation for classification. In the unsupervised scenario where no labeled samples from the target domain are provided, a popular approach consists in transforming the data such that the source and target distributions be- come similar. To compare the two distributions, existing approaches make use of the Maximum Mean Discrepancy (MMD). However, this does not exploit the fact that prob- ability distributions lie on a Riemannian manifold. Here, we propose to make better use of the structure of this man- ifold and rely on the distance on the manifold to compare the source and target distributions. In this framework, we introduce a sample selection method and a subspace-based method for unsupervised domain adaptation, and show that both these manifold-based techniques outperform the cor- responding approaches based on the MMD. Furthermore, we show that our subspace-based approach yields state-of- the-art results on a standard object recognition benchmark.