Since the Lucas-Kanade algorithm was proposed in 1981 image alignment has become one of the most widely used techniques in computer vision. Applications range from optical flow and tracking to layered motion, mosaic construction, and face coding. Numerous algorithms have been proposed and a wide variety of extensions have been made to the original formulation. We present an overview of image alignment, describing most of the algorithms and their extensions in a consistent framework. We concentrate on the inverse compositional algorithm, an efficient algorithm that we recently proposed. We examine which of the extensions to Lucas-Kanade can be used with the inverse compositional algorithm without any significant loss of efficiency, and which cannot. In this paper, Part 1 in a series of papers, we cover the quantity approximated, the warp update rule, and the gradient descent approximation. In future papers, we will cover the choice of the error function, how to allow linear appearance variation, and how to impose priors on the parameters.

The quantitative evaluation of optical flow algorithms by Barron et al. (1994) led to significant advances in performance. The challenges for optical flow algorithms today go beyond the datasets and evaluation methods proposed in that paper. Instead, they center on problems associated with complex natural scenes, including nonrigid motion, real sensor noise, and motion discontinuities. We propose a new set of benchmarks and evaluation methods for the next generation of optical flow algorithms. To that end, we contribute four types of data to test different aspects of optical flow algorithms: (1) sequences with nonrigid motion where the ground-truth flow is determined by tracking hidden fluorescent texture, (2) realistic synthetic sequences, (3) high frame-rate video used to study interpolation error, and (4) modified stereo sequences of static scenes. In addition to the average angular error used by Barron et al., we compute the absolute flow endpoint error, measures for frame interpolation error, improved statistics, and results at motion discontinuities and in textureless regions. In October 2007, we published the performance of several well-known methods on a preliminary version of our data to establish the current state of the art. We also made the data freely available on the web at

Active Appearance Models (AAMs) and the closely related concepts of Morphable Models and Active Blobs are generative models of a certain visual phenomenon. Although linear in both shape and appearance, overall, AAMs are nonlinear parametric models in terms of the pixel intensities. Fitting an AAM to an image consists of minimizing the error between the input image and the closest model instance; i.e. solving a nonlinear optimization problem. We propose an efficient fitting algorithm for AAMs based on the inverse compositional image alignment algorithm. We show how the appearance variation can be "projected out" using this algorithm and how the algorithm can be extended to include a "shape normalizing" warp, typically a 2D similarity transformation. We evaluate our algorithm to determine which of its novel aspects improve AAM fitting performance.

No abstract

No abstract

Conventional video cameras have limited elds of view which make them restrictive for certain applications in computational vision. A catadioptric sensor uses a combination of lenses and mirrors placed in a carefully arranged con guration to capture a much wider eld of view. When designing a catadioptric sensor, the shape of the mirrors should ideally be selected to ensure that the complete catadioptric system has a single e ective viewpoint. In this paper, we derive the complete class of single-lens single-mirror catadioptric sensors which have a single viewpoint and an expression for the spatial resolution of a catadioptric sensor in terms of the resolution of the camera used to construct it. We also include a preliminary analysis of the defocus blur caused by the use of a curved mirror.

A close relationship exists between the advancement of face recognition algorithms and the availability of face databases varying factors that affect facial appearance in a controlled manner. The CMU PIE database has been very influential in advancing research in face recognition across pose and illumination. Despite its success the PIE database has several shortcomings: a limited number of subjects, single recording session and only few expressions captured. To address these issues we collected the CMU Multi-PIE database. It contains 337 subjects, imaged under 15 view points and 19 illumination conditions in up to four recording sessions. In this paper we introduce the database and describe the recording procedure. We furthermore present results from baseline experiments using PCA and LDA classifiers to highlight similarities and differences between PIE and Multi-PIE.

SummaryBackgroundFemoroacetabular impingement syndrome is an important cause of hip pain in young adults. It can be treated by arthroscopic hip surgery, including reshaping the hip, or with physiotherapist-led conservative care. We aimed to compare the clinical effectiveness of hip arthroscopy with best conservative care.MethodsUK FASHIoN is a pragmatic, multicentre, assessor-blinded randomised controlled trial, done at 23 National Health Service hospitals in the UK. We enrolled patients with femoroacetabular impingement syndrome who presented at these hospitals. Eligible patients were at least 16 years old, had hip pain with radiographic features of cam or pincer morphology but no osteoarthritis, and were believed to be likely to benefit from hip arthroscopy. Patients with bilateral femoroacetabular impingement syndrome were eligible; only the most symptomatic hip was randomly assigned to treatment and followed-up. Participants were randomly allocated (1:1) to receive hip arthroscopy or personalised hip therapy (an individualised, supervised, and progressive physiotherapist-led programme of conservative care). Randomisation was stratified by impingement type and recruiting centre and was done by research staff at each hospital, using a central telephone randomisation service. Patients and treating clinicians were not masked to treatment allocation, but researchers who collected the outcome assessments and analysed the results were masked. The primary outcome was hip-related quality of life, as measured by the patient-reported International Hip Outcome Tool (iHOT-33) 12 months after randomisation, and analysed in all eligible participants who were allocated to treatment (the intention-to-treat population). This trial is registered as an International Standard Randomised Controlled Trial, number ISRCTN64081839, and is closed to recruitment.FindingsBetween July 20, 2012, and July 15, 2016, we identified 648 eligible patients and recruited 348 participants: 171 participants were allocated to receive hip arthroscopy and 177 to receive personalised hip therapy. Three further patients were excluded from the trial after randomisation because they did not meet the eligibility criteria. Follow-up at the primary outcome assessment was 92% (319 of 348 participants). At 12 months after randomisation, mean iHOT-33 scores had improved from 39·2 (SD 20·9) to 58·8 (27·2) for participants in the hip arthroscopy group, and from 35·6 (18·2) to 49·7 (25·5) in the personalised hip therapy group. In the primary analysis, the mean difference in iHOT-33 scores, adjusted for impingement type, sex, baseline iHOT-33 score, and centre, was 6·8 (95% CI 1·7–12·0) in favour of hip arthroscopy (p=0·0093). This estimate of treatment effect exceeded the minimum clinically important difference (6·1 points). There were 147 patient-reported adverse events (in 100 [72%] of 138 patients) in the hip arthroscopy group) versus 102 events (in 88 [60%] of 146 patients) in the personalised hip therapy group, with muscle soreness being the most common of the...