Search

Abstract: Motivated by the discriminative ability of shape information and local patterns in object recognition, this paper proposes a window-based object descriptor that integrates both cues. In particular, contour templates representing object shape are used to derive a set of so-called key points at which local appearance features are extracted. These key points are located using an improved template matching method that utilises both spatial and orientation information in a simple and effective way. At each of the extracted key points, a new local appearance feature, namely non-redundant local binary pattern (NR-LBP), is computed. An object descriptor is formed by concatenating the NR-LBP features from all key points to encode the shape as well as the appearance of the object. The proposed descriptor was extensively tested in the task of detecting humans from static images on the commonly used MIT and INRIA datasets. The experimental results have shown that the proposed descriptor can effectively describe non-rigid objects with high articulation and improve the detection rate compared to other state-of-the-art object descriptors. [Copyright &y& Elsevier]

This paper proposes a semantic representation, pose lexicon , for action recognition. The lexicon is composed of a set of semantic poses, a set of visual poses and a probabilistic mapping between the visual and semantic poses. Specially, an action can be represented by a sequence of semantic poses extracted from an associated textual instruction. Visual frames of the action are considered to be generated from a sequence of hidden visual poses. To learn the lexicon, a visual pose model is learned from training samples by a Gaussian Mixture model to characterize the likelihood of an observed visual frame being generated by a visual pose. A pose lexicon model is also learned by an extended hidden Markov alignment model to encode the probabilistic mapping between hidden visual poses and semantic poses sequences. With the lexicon, action classification is formulated as a problem of finding the maximum posterior probability of a given sequence of visual frames that fits to a given sequence of semantic poses through the most likely visual pose and alignment sequences. The efficacy of the proposed method was evaluated on MSRC-12, WorkoutSU-10, WorkoutUOW-18, Combined-15 and Combined-17 action datasets using cross-subject, cross-dataset and zero-shot protocols. [ABSTRACT FROM AUTHOR]

Human action recognition from RGB-D (Red, Green, Blue and Depth) data has attracted increasing attention since the first work reported in 2010. Over this period, many benchmark datasets have been created to facilitate the development and evaluation of new algorithms. This raises the question of which dataset to select and how to use it in providing a fair and objective comparative evaluation against state-of-the-art methods. To address this issue, this paper provides a comprehensive review of the most commonly used action recognition related RGB-D video datasets, including 27 single-view datasets, 10 multi-view datasets, and 7 multi-person datasets. The detailed information and analysis of these datasets is a useful resource in guiding insightful selection of datasets for future research. In addition, the issues with current algorithm evaluation vis-á-vis limitations of the available datasets and evaluation protocols are also highlighted; resulting in a number of recommendations for collection of new datasets and use of evaluation protocols. [ABSTRACT FROM AUTHOR]

The problem of human detection is to automatically locate people in an image or video sequence and has been actively researched in the past decade. This paper aims to provide a comprehensive survey on the recent development and challenges of human detection. Different from previous surveys, this survey is organised in the thread of human object descriptors. This approach has advantages in providing a thorough analysis of the state-of-the-art human detection methods and a guide to the selection of appropriate methods in practical applications. In addition, challenges such as occlusion and real-time human detection are analysed. The commonly used evaluation of human detection methods such as the datasets, tools, and performance measures are presented and future research directions are highlighted. [ABSTRACT FROM AUTHOR]

Fully automatic postural assessment is highly useful, but has been challenging. Conventional methods either require manual assessment by ergonomists or depend on special devices that are intrusive, thus being hardly feasible in daily activities and workplaces. In this work, an attention-based convolutional neural network (CNN) is developed for automatic whole-body postural assessment. The proposed network learns to identify highly relevant regions (or body parts) and extract features automatically. Risk of the posture is estimated from the extracted features accordingly. To evaluate the proposed method, a postural dataset, referred to as pH36M, is created by re-targeting Human3.6M, one of the largest publicly available datasets for pose estimation using the Rapid Entire Body Assessment (REBA) criteria. Experimental results on pH36M demonstrate that proposed method achieves promising performance in comparison to baselines and the average assessment scores are substantially aligned with human assessment with a Kappa value of 0.73. • A novel attention-based CNN for automatic whole-body postural assessment. • The network works directly on single color images rather than 3D skeletons. • A new multi-view and multi-modality dataset is created for postural assessment research. • Results are in substantial or even perfect agreement with human assessors. [ABSTRACT FROM AUTHOR]

This paper presents a new perspective to formulate unsupervised domain adaptation as a multi-task learning problem. This formulation removes the commonly used assumption in the classifier-based adaptation approach that a shared classifier exists for the same task in different domains. Specifically, the source task is to learn a linear classifier from the labelled source data and the target task is to learn a linear transform to cluster the unlabelled target data such that the original target data are mapped to a lower dimensional subspace where the geometric structure is preserved. The two tasks are jointly learned by enforcing the target transformation is close to the source classifier and the class distribution shift between domains is reduced in the meantime. Two novel classifier-based adaptation algorithms are proposed upon the formulation using Regularized Least Squares and Support Vector Machines respectively, in which unshared classifiers between the source and target domains are assumed and jointly learned to effectively deal with large domain shift. Experiments on both synthetic and real-world cross domain recognition tasks have shown that the proposed methods outperform several state-of-the-art unsupervised domain adaptation methods. [ABSTRACT FROM AUTHOR]

Highlights • Automatic generations of SSM does not satisfy clinical applications. • A prototype based SSM building method is proposed to make landmarks configurable. • Remeshing and diffeomorphic registration are used to optimize the correspondence. • The SSMs built by proposal are as better as manually did. Abstract Automatic segmentation of organs from medical images is indispensable for the computer-assisted medical applications. Statistical Shape Models (SSMs) based scheme has been developed as an accurate and robust approach for extraction of anatomical structures, in which a crucial step is the need to place the sampled points (landmarks) with well corresponding across the whole training set. On the one hand, the correspondence of landmarks is related the quality of shape model. On the other hand, in clinical application some key positions of landmarks should be specified by physicians referring to the anatomic structure. In this paper, we develop an interactive method to build SSM that the landmark distribution can be modified manually without influencing the model quality. We extend an existing remeshing method to produce a model prototype in advance and surface features driven registration to insure the universal optimization of correspondence. The key landmarks are fixed during the prototype generation. We experimented and evaluated the proposed SSM method for lung regions, the deformations of which are considerable large. [ABSTRACT FROM AUTHOR]

Automatic detection of micro-aneurysm in color retinal image is important for early screening and diagnosis of diabetic retinopathy. In this paper, a new method is proposed for micro-aneurysm detection based on circular bilateral Gabor filtering. Firstly, a circular bilateral Gabor filter is developed to extract micro-aneurysm candidates. Secondly, false positives are reduced by eliminating small vessels through a process involving local gradient analysis. The proposed method is tested on the retinal images from the Retinopathy Online Challenge database and Tianjin Medical University Metabolic Diseases Hospital. Evaluation results at both image and lesion level demonstrate the efficacy of the proposed method in detecting micro-aneurysm accurately. [ABSTRACT FROM AUTHOR]