A Review on Computer Vision-Based Methods for Human Action Recognition.

Human action recognition targets recognising different actions from a sequence of observations and different environmental conditions. A wide different applications is applicable to vision based action recognition research. This can include video surveillance, tracking, health care, and human-computer interaction. However, accurate and effective vision based recognition systems continue to be a big challenging area of research in the field of computer vision. This review introduces the most recent human action recognition systems and provides the advances of state-of-the-art methods. To this end, the direction of this research is sorted out from hand-crafted representation based methods including holistic and local representation methods with various sources of data, to a deep learning technology including discriminative and generative models and multi-modality based methods. Next, the most common datasets of human action recognition are presented. This review introduces several analyses, comparisons and recommendations that help to find out the direction of future research.

Fiber-Based Composite Meshes with Controlled Mechanical and Wetting Properties for Water Harvesting.

Water is the basis of life in the world. Unfortunately, resources are shrinking at an alarming rate. The lack of access to water is still the biggest problem in the modern world. The key to solving it is to find new unconventional ways to obtain water from alternative sources. Fog collectors are becoming an increasingly important way of water harvesting as there are places in the world where fog is the only source of water. Our aim is to apply electrospun fiber technology, due to its high surface area, to increase fog collection efficiency. Therefore, composites consisting of hydrophobic and hydrophilic fibers were successfully fabricated using a two-nozzle electrospinning setup. This design enables the realization of optimal meshes for harvesting water from fog. In our studies we focused on combining hydrophobic polystyrene (PS) and hydrophilic polyamide 6 (PA6), surface properties in the produced meshes, without any chemical modifications, on the basis of new hierarchical composites for collecting water. This combination of hydrophobic and hydrophilic materials causes water to condense on the hydrophobic microfibers and to run down on the hydrophilic nanofibers. By adjusting the fraction of PA6 nanofibers, we were able to tune the mechanical properties of PS meshes and importantly increase the efficiency in collecting water. We combined a few characterization methods together with novel image processing protocols for the analysis of fiber fractions in the constructed meshes. The obtained results show a new single-step method to produce meshes with enhanced mechanical properties and water collecting abilities that can be applied in existing fog water collectors. This is a new promising design for fog collectors with nano- and macrofibers which are able to efficiently harvest water, showing great application in comparison to commercially available standard meshes.

Deep Learning of Fuzzy Weighted Multi-Resolution Depth Motion Maps with Spatial Feature Fusion for Action Recognition.

Human action recognition (HAR) is an important yet challenging task. This paper presents a novel method. First, fuzzy weight functions are used in computations of depth motion maps (DMMs). Multiple length motion information is also used. These features are referred to as fuzzy weighted multi-resolution DMMs (FWMDMMs). This formulation allows for various aspects of individual actions to be emphasized. It also helps to characterise the importance of the temporal dimension. This is important to help overcome, e.g., variations in time over which a single type of action might be performed. A deep convolutional neural network (CNN) motion model is created and trained to extract discriminative and compact features. Transfer learning is also used to extract spatial information from RGB and depth data using the AlexNet network. Different late fusion techniques are then investigated to fuse the deep motion model with the spatial network. The result is a spatial temporal HAR model. The developed approach is capable of recognising both human action and human-object interaction. Three public domain datasets are used to evaluate the proposed solution. The experimental results demonstrate the robustness of this approach compared with state-of-the art algorithms.

Multiscale Shannon's Entropy Modeling of Orientation and Distance in Steel Fiber Micro-Tomography Data.

This paper is concerned with the modeling and analysis of the orientation and distance between steel fibers in X-ray micro-tomography data. The advantage of combining both orientation and separation in a model is that it helps provide a detailed understanding of how the steel fibers are arranged, which is easy to compare. The developed models are designed to summarize the randomness of the orientation distribution of the steel fibers both locally and across an entire volume based on multiscale entropy. Theoretical modeling, simulation, and application to real imaging data are shown here. The theoretical modeling of multiscale entropy for orientation includes a proof showing the final form of the multiscale taken over a linear range of scales. A series of image processing operations are also included to overcome interslice connectivity issues to help derive the statistical descriptions of the orientation distributions of the steel fibers. The results demonstrate that multiscale entropy provides unique insights into both simulated and real imaging data of steel fiber reinforced concrete.

Automatic bootstrapping and tracking of object contours.

A new fully automatic object tracking and segmentation framework is proposed. The framework consists of a motion-based bootstrapping algorithm concurrent to a shape-based active contour. The shape-based active contour uses finite shape memory that is automatically and continuously built from both the bootstrap process and the active-contour object tracker. A scheme is proposed to ensure that the finite shape memory is continuously updated but forgets unnecessary information. Two new ways of automatically extracting shape information from image data given a region of interest are also proposed. Results demonstrate that the bootstrapping stage provides important motion and shape information to the object tracker. This information is found to be essential for good (fully automatic) initialization of the active contour. Further results also demonstrate convergence properties of the content of the finite shape memory and similar object tracking performance in comparison with an object tracker with unlimited shape memory. Tests with an active contour using a fixed-shape prior also demonstrate superior performance for the proposed bootstrapped finite-shape-memory framework and similar performance when compared with a recently proposed active contour that uses an alternative online learning model.

Adaptive partial volume classification of MRI data.

Tomographic biomedical images are commonly affected by an imaging artefact known as the partial volume (PV) effect. The PV effect produces voxels composed of a mixture of tissues in anatomical magnetic resonance imaging (MRI) data resulting in a continuity of these tissue classes. Anatomical MRI data typically consist of a number of contiguous regions of tissues or even contiguous regions of PV voxels. Furthermore discontinuities exist between the boundaries of these contiguous image regions. The work presented here probabilistically models the PV effect using spatial regularization in the form of continuous Markov random fields (MRFs) to classify anatomical MRI brain data, simulated and real. A unique approach is used to adaptively control the amount of spatial regularization imposed by the MRF. Spatially derived image gradient magnitude is used to identify the discontinuities between image regions of contiguous tissue voxels and PV voxels, imposing variable amounts of regularization determined by simulation. Markov chain Monte Carlo (MCMC) is used to simulate the posterior distribution of the probabilistic image model. Promising quantitative results are presented for PV classification of simulated and real MRI data of the human brain.

Statistical morphological skull stripping of adult and infant MRI data.

This paper describes a novel automatic statistical morphology skull stripper (SMSS) that uniquely exploits a statistical self-similarity measure and a 2-D brain mask to delineate the brain. The result of applying SMSS to 20 MRI data set volumes, including scans of both adult and infant subjects is also described. Quantitative performance assessment was undertaken with the use of brain masks provided by a brain segmentation expert. The performance is compared with an alternative technique known as brain extraction tool. The results suggest that SMSS is capable of skull-stripping neurological data with small amounts of over- and under-segmentation.