Robust visual tracking using structurally random projection and weighted least squares

Sparse representation based visual tracking approaches have attracted increasing interests in the community in recent years. The main idea is to linearly represent each target candidate using a set of target and trivial templates while imposing a sparsity constraint onto the representation coefficients. After we obtain the coefficients using L1-norm minimization methods, the candidate with the lowest error, when it is reconstructed using only the target templates and the associated coefficients, is considered as the tracking result. In spite of promising system performance widely reported, it is unclear if the performance of these trackers can be maximised. In addition, computational complexity caused by the dimensionality of the feature space limits these algorithms in real-time applications. In this paper, we propose a real-time visual tracking method based on structurally random projection and weighted least squares techniques. In particular, to enhance the discriminative capability of the tracker, we introduce background templates to the linear representation framework. To handle appearance variations over time, we relax the sparsity constraint using a weighed least squares (WLS) method to obtain the representation coefficients. To further reduce the computational complexity, structurally random projection is used to reduce the dimensionality of the feature space while preserving the pairwise distances between the data points in the feature space. Experimental results show that the proposed approach outperforms several state-of-the-art tracking methods.

Genetic Background and Light-Dependent Progression of Photoreceptor Cell Degeneration in Prominin-1 Knockout Mice

PURPOSE: Mutations in the Prominin-1 (Prom1) gene are known to cause retinitis pigmentosa and Stargardt disease, both of which are associated with progressive photoreceptor cell death. There are no effective therapies for either disorder. The aim of this study was to investigate the mechanism of the retinal degeneration in Prom1-deficient mouse models.

METHODS: We constructed Prom1 knockout mice with two distinct genetic backgrounds of C57BL/6 and C57BL/6xCBA/NSlc, and investigated the photoreceptor degeneration by means of histology and functional tests.. In addition, we examined the effect of light on the Prom1(-/-) retina by rearing the mice in the normal light/dark cycle and completely dark conditions. Finally, we investigated if the retinoic-acid derivative Fenretinide slowed the pace of retinal degeneration in these mouse models.

RESULTS: The Prom1(-/-)-knockout mice with both backgrounds developed photoreceptor degeneration after eye opening, but the CB57/BL6-background mice developed photoreceptor cell degeneration much faster than the C57BL/6xCBA/NSlc mice, demonstrating genetic background dependency.. Interestingly, our histologic and functional examination showed that the photoreceptor cell degeneration of Prom1-knockout mice was light-dependent, and was almost completely inhibited when the mutant mice were kept in the dark. The Prom1-knockout retina showed strong downregulation of expression of the visual cycle components, Rdh12 and Abca4. Furthermore, administration of Fenretinide, which lowers the level of the toxic lipofuscin, slowed the degeneration of photoreceptor cells.

CONCLUSIONS: These findings improve our understanding of the mechanism of cell death in Prominin-1-related disease and provide evidence that fenretinide may be worth studying in human disease.

Deep Salience: Visual Salience Modeling via Deep Belief Propagation

Visual salience is an intriguing phenomenon observed in biological neural systems. Numerous attempts have been made to model visual salience mathematically using various feature contrasts, either locally or globally. However, these algorithmic models tend to ignore the problem’s biological solutions, in which visual salience appears to arise during the propagation of visual stimuli along the visual cortex. In this paper, inspired by the conjecture that salience arises from deep propagation along the visual cortex, we present a Deep Salience model where a multi-layer model based on successive Markov random fields (sMRF) is proposed to analyze the input image successively through its deep belief propagation. As a result, the foreground object can be automatically separated from the background in a fully unsupervised way. Experimental evaluation on the benchmark dataset validated that our Deep Salience model can consistently outperform eleven state-of-the-art salience models, yielding the higher rates in the precision-recall tests and attaining the best F-measure and mean-square error in the experiments.

A role for local mechanisms in perceived duration of brief visual events

Background: Spatially localized duration compression of a briefly presented moving stimulus following adaptation in the same location is taken as evidence for modality-specific neural timing mechanisms.

Aims: The present study used random dot motion stimuli to investigate where these mechanisms may be located.

Method: Experiment 1 measured duration compression of the test stimulus as a function of adaptor speed and revealed that duration compression is speed tuned. These data were then used to make predictions of duration compression responses for various models which were tested in experiment 2. Here a mixed-speed adaptor stimulus was used with duration compression being measured as a function of the adaptor’s ‘speed notch’ (the removal of a central band from the speed range).

Results: The results were consistent with a local-mean model.

Conclusions: Local-motion mechanisms are involved in duration perception of brief events.

Investigation into DCT Feature Selection for Visual Lip-Based Biometric Authentication

This paper investigated using lip movements as a behavioural biometric for person authentication. The system was trained, evaluated and tested using the XM2VTS dataset, following the Lausanne Protocol configuration II. Features were selected from the DCT coefficients of the greyscale lip image. This paper investigated the number of DCT coefficients selected, the selection process, and static and dynamic feature combinations. Using a Gaussian Mixture Model - Universal Background Model framework an Equal Error Rate of 2.20% was achieved during evaluation and on an unseen test set a False Acceptance Rate of 1.7% and False Rejection Rate of 3.0% was achieved. This compares favourably with face authentication results on the same dataset whilst not being susceptible to spoofing attacks.

Cataract surgical outcomes, visual function and quality of life in four rural districts in Vietnam.

BACKGROUND: To evaluate cataract surgical outcomes in four rural districts of Ha Tinh Province, Vietnam. DESIGN: Cross-sectional study. PARTICIPANTS: Post-cataract surgery patients sampled randomly from facilities in four rural districts of Ha Tinh Province >3 months after surgery. MAIN OUTCOME MEASURES: Postoperative visual acuity (VA), visual function and quality of life. RESULTS: Among 412 patients, the mean age was 74.5 ± 9.4 years, 67% (276) were female, and 377 (91.5%) received intraocular lenses (IOL). Nearly two-thirds of patients had no postoperative visits after discharge. Postoperatively, more than 40% of eyes had presenting VA <6/18, while 20% remained <6/60. The mean self-reported visual function and quality of life for all patients were 68.7 ± 23.8 and 73.8 ± 21.6, respectively. Most patients (89.5%) were satisfied with surgery and the majority (94.4%) would recommend surgery to others. One-third of patients paid ≥$US50 for surgery. In multiple regression modelling, older age (P < 0.01), intraoperative complications (P < 0.01) and failure to receive an IOL (P < 0.01) were associated with postoperative VA <6/60. CONCLUSION: Satisfaction with surgery was high, and many patients were willing to pay for their operations. Poor visual outcomes were common; however, and better surgical training is needed to reduce complications and their impact on visual outcomes. More intensive postoperative follow-up may also be beneficial. © 2011 The Authors. Clinical and Experimental Ophthalmology © 2011 Royal Australian and New Zealand College of Ophthalmologists.

Early assessment of visual acuity after cataract surgery in rural Indonesia.

BACKGROUND: The accuracy and impact on service uptake of early examination after cataract surgery is not known. DESIGN:   Prospective cohort study. PARTICIPANTS: Cataract patients in rural Indonesia. METHODS: Visual acuity was measured preoperatively, 1day, 1-3, 4-6 and >12weeks after surgery, and 6-8months postoperatively at an outreach examination. Acceptance of second-eye surgery and spectacles was evaluated. MAIN OUTCOME MEASURE: Presenting visual acuity in the operated eye. RESULTS: Among 241 subjects (extracapsular surgery 84%), examinations at 1day, 1-3, 4-6 and >12weeks and 6-8months were completed for 100% (241), 90.9% (219), 67.6% (163), 22.0% (53) and 80.0% (193), respectively. Among subjects at the final examination (mean age 65.8±10.6years, 51.8% male), 73.6% had bilateral preoperative presenting visual acuity≤6/60. By 4-6weeks, the proportion with good (≥6/18) or poor (≤6/60) visual acuity did not differ significantly from the final examination. Among 49 persons accepting free second-eye surgery, 69.4% (34) and 16.3% (8) returned to clinic at 4-6 and >12weeks, respectively. Among 131 patients (67.9%) paying US$7 for glasses, 94 (71.8%) and 30 (22.9%) attended 4- to 6- and >12-week examinations, respectively. CONCLUSION: Even with large-incision surgery, early assessment of postoperative vision is representative of final vision, and may help deliver postoperative services to more of those needing them. © 2011 The Authors. Clinical and Experimental Ophthalmology © 2011 Royal Australian and New Zealand College of Ophthalmologists.

Local object gist: meaningful shapes and spatial layout at a very early stage of visual processing

In his introduction, Pinna (2010) quoted one of Wertheimer’s observations: “I stand at the window and see a house, trees, sky. Theoretically I might say there were 327 brightnesses and nuances of color. Do I have ‘327’? No. I have sky, house, and trees.” This seems quite remarkable, for Max Wertheimer, together with Kurt Koffka and Wolfgang Koehler, was a pioneer of Gestalt Theory: perceptual organisation was tackled considering grouping rules of line and edge elements in relation to figure-ground segregation, i.e., a meaningful object (the figure) as perceived against a complex background (the ground). At the lowest level – line and edge elements – Wertheimer (1923) himself formulated grouping principles on the basis of proximity, good continuation, convexity, symmetry and, often forgotten, past experience of the observer. Rubin (1921) formulated rules for figure-ground segregation using surroundedness, size and orientation, but also convexity and symmetry. Almost a century of research into Gestalt later, Pinna and Reeves (2006) introduced the notion of figurality, meant to represent the integrated set of properties of visual objects, from the principles of grouping and figure-ground to the colour and volume of objects with shading. Pinna, in 2010, went one important step further and studied perceptual meaning, i.e., the interpretation of complex figures on the basis of past experience of the observer. Re-establishing a link to Wertheimer’s rule about past experience, he formulated five propositions, three definitions and seven properties on the basis of observations made on graphically manipulated patterns. For example, he introduced the illusion of meaning by comics-like elements suggesting wind, therefore inducing a learned interpretation. His last figure shows a regular array of squares but with irregular positions on the right side. This pile of (ir)regular squares can be interpreted as the result of an earthquake which destroyed part of an apartment block. This is much more intuitive, direct and economic than describing the complexity of the array of squares.

Espaço e perspectivas na representação visual

Relatório da prática de ensino supervisionada, Mestrado em Ensino de Artes Visuais, Universidade de Lisboa, 2011

Secret Sharing Schemes Using Visual Cryptography

Secret sharing schemes allow a secret to be shared among a group of participants so that only qualified subsets of participants can recover the secret. A visual cryptography scheme (VCS) is a special kind of secret sharing scheme in which the secret to share consists of an image and the shares consist of xeroxed transparencies which are stacked to recover the shared image. In this thesis we have given the theoretical background of Secret Sharing Schemes and the historical development of the subject. We have included a few examples to improve the readability of the thesis. We have tried to maintain the rigor of the treatment of the subject. The limitations and disadvantages of the various forms secret sharing schemes are brought out. Several new schemes for both dealing and combining are included in the thesis. We have introduced a new number system, called, POB number system. Representation using POB number system has been presented. Algorithms for finding the POB number and POB value are given.We have also proved that the representation using POB number system is unique and is more efficient. Being a new system, there is much scope for further development in this area.

A system to evaluate the accuracy of a visual mosaicking methodology

When underwater vehicles navigate close to the ocean floor, computer vision techniques can be applied to obtain motion estimates. A complete system to create visual mosaics of the seabed is described in this paper. Unfortunately, the accuracy of the constructed mosaic is difficult to evaluate. The use of a laboratory setup to obtain an accurate error measurement is proposed. The system consists on a robot arm carrying a downward looking camera. A pattern formed by a white background and a matrix of black dots uniformly distributed along the surveyed scene is used to find the exact image registration parameters. When the robot executes a trajectory (simulating the motion of a submersible), an image sequence is acquired by the camera. The estimated motion computed from the encoders of the robot is refined by detecting, to subpixel accuracy, the black dots of the image sequence, and computing the 2D projective transform which relates two consecutive images. The pattern is then substituted by a poster of the sea floor and the trajectory is executed again, acquiring the image sequence used to test the accuracy of the mosaicking system

Changing text and background colours in Adobe Acrobat

A 4-minute video that shows how students with dyslexia or visual stress can change the text and background colours in Adobe Acrobat Reader to suit their needs.

Optokinetic stimulation induces illusory movement of both out-of-the-body and on-the-body hand-held visual objects

The coding of body part location may depend upon both visual and proprioceptive information, and allows targets to be localized with respect to the body. The present study investigates the interaction between visual and proprioceptive localization systems under conditions of multisensory conflict induced by optokinetic stimulation (OKS). Healthy subjects were asked to estimate the apparent motion speed of a visual target (LED) that could be located either in the extrapersonal space (visual encoding only, V), or at the same distance, but stuck on the subject's right index finger-tip (visual and proprioceptive encoding, V-P). Additionally, the multisensory condition was performed with the index finger kept in position both passively (V-P passive) and actively (V-P active). Results showed that the visual stimulus was always perceived to move, irrespective of its out- or on-the-body location. Moreover, this apparent motion speed varied consistently with the speed of the moving OKS background in all conditions. Surprisingly, no differences were found between V-P active and V-P passive conditions in the speed of apparent motion. The persistence of the visual illusion during the active posture maintenance reveals a novel condition in which vision totally dominates over proprioceptive information, suggesting that the hand-held visual stimulus was perceived as a purely visual, external object despite its contact with the hand.

Robust real-time tracking for visual surveillance

This paper describes a real-time multi-camera surveillance system that can be applied to a range of application domains. This integrated system is designed to observe crowded scenes and has mechanisms to improve tracking of objects that are in close proximity. The four component modules described in this paper are (i) motion detection using a layered background model, (ii) object tracking based on local appearance, (iii) hierarchical object recognition, and (iv) fused multisensor object tracking using multiple features and geometric constraints. This integrated approach to complex scene tracking is validated against a number of representative real-world scenarios to show that robust, real-time analysis can be performed. Copyright (C) 2007 Hindawi Publishing Corporation. All rights reserved.

Visual motion interferes with lexical decision on motion words

Embodied theories of cognition propose that neural substrates used in experiencing the referent of a word, for example perceiving upward motion, should be engaged in weaker form when that word, for example ‘rise’, is comprehended. Motivated by the finding that the perception of irrelevant background motion at near-threshold, but not supra-threshold, levels interferes with task execution, we assessed whether interference from near-threshold background motion was modulated by its congruence with the meaning of words (semantic content) when participants completed a lexical decision task (deciding if a string of letters is a real word or not). Reaction times for motion words, such as ‘rise’ or ‘fall’, were slower when the direction of visual motion and the ‘motion’ of the word were incongruent — but only when the visual motion was at nearthreshold levels. When motion was supra-threshold, the distribution of error rates, not reaction times, implicated low-level motion processing in the semantic processing of motion words. As the perception of near-threshold signals is not likely to be influenced by strategies, our results support a close contact between semantic information and perceptual systems.