Search

Deep learning architecture with convolutional neural network (CNN) achieves outstanding success in the field of computer vision. Where U-Net, an encoder-decoder architecture structured by CNN, makes a great breakthrough in biomedical image segmentation and has been applied in a wide range of practical scenarios. However, the equal design of every downsampling layer in the encoder part and simply stacked convolutions do not allow U-Net to extract sufficient information of features from different depths. The increasing complexity of medical images brings new challenges to the existing methods. In this paper, we propose a deeper and more compact split-attention u-shape network (DCSAU-Net), which efficiently utilises low-level and high-level semantic information based on two novel frameworks: primary feature conservation and compact split-attention block. We evaluate the proposed model on CVC-ClinicDB, 2018 Data Science Bowl, ISIC-2018 and SegPC-2021 datasets. As a result, DCSAU-Net displays better performance than other state-of-the-art (SOTA) methods in terms of the mean Intersection over Union (mIoU) and F1-socre. More significantly, the proposed model demonstrates excellent segmentation performance on challenging images. The code for our work and more technical details can be found at https://github.com/xq141839/DCSAU-Net.

Classifiers trained on disjointed classes with few labelled data points are used in one-shot learning to identify visual concepts from other classes. Recently, Siamese networks and similarity layers have been used to solve the one-shot learning problem, achieving state-of-the-art performance on visual-character recognition datasets. Various techniques have been developed over the years to improve the performance of these networks on fine-grained image classification datasets. They focused primarily on improving the loss and activation functions, augmenting visual features, employing multiscale metric learning, and pre-training and fine-tuning the backbone network. We investigate similarity layers for one-shot learning tasks and propose two frameworks for combining these layers into a MergedNet network. On all four datasets used in our experiment, MergedNet outperformed the baselines based on classification accuracy, and it generalises to other datasets when trained on miniImageNet.

Automated image-based phenotyping has become widely accepted in crop phenotyping, particularly in cereal crops, yet few traits used by breeders in the strawberry industry have been automated. Early phenotypic assessment remains largely qualitative in this area since the manual phenotyping process is laborious and domain experts are constrained by time. Precision agriculture, facilitated by robotic technologies, is increasing in the strawberry industry, and the development of quantitative automated phenotyping methods is essential to ensure that breeding programs remain economically competitive. In this review, we investigate the external morphological traits relevant to the breeding of strawberries that have been automated and assess the potential for automation of traits that are still evaluated manually, highlighting challenges and limitations of the approaches used, particularly when applying high-throughput strawberry phenotyping in real-world environmental conditions.

Tea chrysanthemum detection at its flowering stage is one of the key components for selective chrysanthemum harvesting robot development. However, it is a challenge to detect flowering chrysanthemums under unstructured field environments given variations on illumination, occlusion and object scale. In this context, we propose a highly fused and lightweight deep learning architecture based on YOLO for tea chrysanthemum detection (TC-YOLO). First, in the backbone component and neck component, the method uses the Cross-Stage Partially Dense network (CSPDenseNet) and the Cross-Stage Partial ResNeXt network (CSPResNeXt) as the main networks, respectively, and embeds custom feature fusion modules to guide the gradient flow. In the final head component, the method combines the recursive feature pyramid (RFP) multiscale fusion reflow structure and the Atrous Spatial Pyramid Pool (ASPP) module with cavity convolution to achieve the detection task. The resulting model was tested on 300 field images using a data enhancement strategy combining flipping and rotation, showing that under the NVIDIA Tesla P100 GPU environment, if the inference speed is 47.23 FPS for each image (416 × 416), TC-YOLO can achieve the average precision (AP) of 92.49% on our own tea chrysanthemum dataset. Through further validation, it was found that overlap had the least effect on tea chrysanthemum detection, and illumination had the greatest effect on tea chrysanthemum detection. In addition, this method (13.6 M) can be deployed on a single mobile GPU, and it could be further developed as a perception system for a selective chrysanthemum harvesting robot in the future.

Marker-less motion capture is a rapidly advancing field that can take simple RGB image sequences, or more advanced Red Green Blue Depth (RGB-D) image sequences obtained using depth sensors, and outputs an estimated human pose. This method of human pose estimation allows for the extraction of biomechanical features which can then be analysed by clinicians to give more insights into a patient’s movement capabilities. When compared to other, more clinically proven technologies such as the Knee Kinesiography (KneeKG), biomechanics presented have the advantage of being more representative of natural movement without the obstructive markers placed on the body. This Significant difference of up to 10 degrees in a range of motion for the knee could be the key to better identifying a person’s gait or tracking their natural walking pattern over time, while also being more robust and better suited to a smaller clinical environment.

Response evaluation criteria in solid tumours (RECIST) v1.1 are currently the reference standard for evaluating efficacy of therapies in patients with solid tumours who are included in clinical trials, and they are widely used and accepted by regulatory agencies. This expert statement discusses the principles underlying RECIST, as well as their reproducibility and limitations. While the RECIST framework may not be perfect, the scientific bases for the anticancer drugs that have been approved using a RECIST-based surrogate endpoint remain valid. Importantly, changes in measurement have to meet thresholds defined by RECIST for response classification within thus partly circumventing the problems of measurement variability. The RECIST framework also applies to clinical patients in individual settings even though the relationship between tumour size changes and outcome from cohort studies is not necessarily translatable to individual cases. As reproducibility of RECIST measurements is impacted by reader experience, choice of target lesions and detection/interpretation of new lesions, it can result in patients changing response categories when measurements are near threshold values or if new lesions are missed or incorrectly interpreted. There are several situations where RECIST will fail to evaluate treatment-induced changes correctly; knowledge and understanding of these is crucial for correct interpretation. Also, some patterns of response/progression cannot be correctly documented by RECIST, particularly in relation to organ-site (e.g. bone without associated soft-tissue lesion) and treatment type (e.g. focal therapies). These require specialist reader experience and communication with oncologists to determine the actual impact of the therapy and best evaluation strategy. In such situations, alternative imaging markers for tumour response may be used but the sources of variability of individual imaging techniques need to be known and accounted for. Communication between imaging experts and oncologists regarding the level of confidence in a biomarker is essential for the correct interpretation of a biomarker and its application to clinical decision-making. Though measurement automation is desirable and potentially reduces the variability of results, associated technical difficulties must be overcome, and human adjudications may be required., peer-reviewed

Most deep-learning frameworks for understanding biological swarms are designed to fit perceptive models of group behavior to individual-level data (e.g., spatial coordinates of identified features of individuals) that have been separately gathered from video observations. Despite considerable advances in automated tracking, these methods are still very expensive or unreliable when tracking large numbers of animals simultaneously. Moreover, this approach assumes that the human-chosen features include sufficient features to explain important patterns in collective behavior. To address these issues, we propose training deep network models to predict system-level states directly from generic graphical features from the entire view, which can be relatively inexpensive to gather in a completely automated fashion. Because the resulting predictive models are not based on human-understood predictors, we use explanatory modules (e.g., Grad-CAM) that combine information hidden in the latent variables of the deep-network model with the video data itself to communicate to a human observer which aspects of observed individual behaviors are most informative in predicting group behavior. This represents an example of augmented intelligence in behavioral ecology -- knowledge co-creation in a human-AI team. As proof of concept, we utilize a 20-day video recording of a colony of over 50 Harpegnathos saltator ants to showcase that, without any individual annotations provided, a trained model can generate an "importance map" across the video frames to highlight regions of important behaviors, such as dueling (which the AI has no a priori knowledge of), that play a role in the resolution of reproductive-hierarchy re-formation. Based on the empirical results, we also discuss the potential use and current challenges., Best Paper Winner at the 4th International Symposium on Swarm Behavior and Bio-Inspired Robotics (SWARM 2021)

The analysis of retinal Spectral-Domain Optical Coherence Tomography (SD-OCT) images by trained medical professionals can be used to provide useful insights into various diseases. It is the most popular method of retinal imaging due to its non-invasive nature and the useful information it provides for making an accurate diagnosis. A deep learning approach for automating the segmentation of Cystoid Macular Edema (fluid) in retinal OCT B-Scan images was developed that is consequently used for volumetric analysis of OCT scans. This solution is a fast and accurate semantic segmentation network that makes use of a shortened encoder-decoder UNet like architecture with an integrated Dense ASPP module and Attention Gate for producing an accurate and refined retinal fluid segmentation map. Our system was evaluated against both publicly and privately available datasets; on the former the network achieved a Dice coefficient of 0.804, thus making it the current best performing approach on this dataset, and on the very small and challenging private dataset, it achieved a score of 0.691. Due to the lack of publicly available data in this domain, a Graphical User Interface that aims to semi-automate the labelling process of OCT images was also created, thus greatly simplifying the process of the dataset creation and potentially leading to an increase in labelled data production.

This paper explores the application of unsupervised learning to detecting anomalies in mouse video data. The two models presented in this paper are a dual stream, 3D convolutional autoencoder (with residual connections) and a dual stream, 2D convolutional autoencoder. The publicly available dataset used here contains twelve videos of a single home-caged mice alongside frame level annotations. Under the pretext that the autoencoder only sees normal events, the video data was handcrafted to treat each behaviour as a pseudo-anomaly thereby eliminating them from the others during training. The results are presented for one conspicuous behaviour (hang) and one inconspicuous behaviour (groom). The performance of these models is compared to a single stream autoencoder and a supervised learning model, which are both based on the custom CAE encoder. Both models are also tested on the CUHK Avenue dataset were found to perform as well as some state-of-the-art architectures.

Work in robotic phenotyping requires computer vision methods that estimate the number of fruit or grains in an image. To decide what to use, we compared three methods for counting fruit and grains, each method representative of a class of approaches from the literature. These are two methods based on density estimation and regression (single and multiple column), and one method based on object detection. We found that when the density of objects in an image is low, the approaches are comparable, but as the density increases, counting by regression becomes steadily more accurate than counting by detection. With more than a hundred objects per image, the error in the count predicted by detection-based methods is up to 5 times higher than when using regression-based ones.

The global pandemic of coronavirus disease 2019 (COVID-19) is continuing to have a significant effect on the well-being of the global population, thus increasing the demand for rapid testing, diagnosis, and treatment. As COVID-19 can cause severe pneumonia, early diagnosis is essential for correct treatment, as well as to reduce the stress on the healthcare system. Along with COVID-19, other etiologies of pneumonia and Tuberculosis (TB) constitute additional challenges to the medical system. Pneumonia (viral as well as bacterial) kills about 2 million infants every year and is consistently estimated as one of the most important factor of childhood mortality (according to the World Health Organization). Chest X-ray (CXR) and computed tomography (CT) scans are the primary imaging modalities for diagnosing respiratory diseases. Although CT scans are the gold standard, they are more expensive, time consuming, and are associated with a small but significant dose of radiation. Hence, CXR have become more widespread as a first line investigation. In this regard, the objective of this work is to develop a new deep transfer learning pipeline, named DenResCov-19, to diagnose patients with COVID-19, pneumonia, TB or healthy based on CXR images. The pipeline consists of the existing DenseNet-121 and the ResNet-50 networks. Since the DenseNet and Resnet have orthogonal performances in some instances, in the proposed model we have created an extra layer with convolutional neural network (CNN) blocks to join these two models together to establish superior performance as compared to the two individual networks. This strategy can be applied universally in cases where two competing networks are observed. We have tested the performance of our proposed network on two-class (pneumonia and healthy), three-class (COVID-19 positive, healthy, and pneumonia), as well as four-class (COVID-19 positive, healthy, TB, and pneumonia) classification problems. We have validated that our proposed network has been able to successfully classify these lung-diseases on our four datasets and this is one of our novel findings. In particular, the AUC-ROC are 99.60, 96.51, 93.70, 96.40% and the F1 values are 98.21, 87.29, 76.09, 83.17% on our Dataset X-Ray 1, 2, 3, and 4 (DXR1, DXR2, DXR3, DXR4), respectively., Graphical abstract

Advanced 3D imaging modalities, such as micro-computed tomography (micro-CT), have been incorporated into the high-throughput embryo pipeline of the International Mouse Phenotyping Consortium (IMPC). This project generates large volumes of raw data that cannot be immediately exploited without significant resources of personnel and expertise. Thus, rapid automated annotation is crucial to ensure that 3D imaging data can be integrated with other multi-dimensional phenotyping data. We present an automated computational mouse embryo phenotyping pipeline that harnesses the large amount of wild-type control data available in the IMPC embryo pipeline in order to address issues of low mutant sample number as well as incomplete penetrance and variable expressivity. We also investigate the effect of developmental substage on automated phenotyping results. Designed primarily for developmental biologists, our software performs image pre-processing, registration, statistical analysis and segmentation of embryo images. We also present a novel anatomical E14.5 embryo atlas average and, using it with LAMA, show that we can uncover known and novel dysmorphology from two IMPC knockout lines., Summary: Introducing an easy-to-use automated anatomical phenotyping pipeline for mouse embryos along with a highly-detailed anatomical E14.5 atlas.

For adoption of Autonomous Mobile Robots (AMR) across a breadth of industries, they must navigate around humans in a way which is safe and which humans perceive as safe, but without greatly compromising efficiency. This work proposes a novel classifier of the Human-Robot Spatial Interaction (HRSI) situation of an interacting human and robot, to be applied in Human-Aware Navigation (HAN) to account for situational context. A classifier comprised of per-situation Hidden Markov Models is developed, and trained with sequences of states in Qualitative Trajectory Calculus, representing relative human and robot movements in various HRSI situations. This multi-HMM HRSI situation classifier is created as a component of the safety stack for the EU Horizon 2020 ILIAD Project, and the theoretical foundation and implementation of this system is described, along with the results of a HRI study that evaluates the classification performance of this work’s novel classifier. The aim of this work is to demonstrate accurate continuous real-time classification of a set of socially legible HRSI situations that occur when a proximate human and heavy industrial robot are moving through a shared space. High classification performance is demonstrated, with future work currently being conducted by ILIAD colleagues to test a complete HAN system that employs this real-time situation classification to apply situational qualitative motion constraints, as well as testing the ILIAD safety stack as a whole.

Retail food packaging contains information which informs choice and can be vital to consumer health, including product name, ingredients list, nutritional information, allergens, preparation guidelines, pack weight, storage and shelf life information (use-by/best before dates). The presence and accuracy of such information is critical to ensure a detailed understanding of the product and to reduce the potential for health risks. Consequently, erroneous or illegible labeling has the potential to be highly detrimental to consumers and many other stakeholders in the supply chain. In practice, due to the high volume of food packages that go through the supply chain, mistakes do occur therefore good quality of images are needed to verify the correctness of the information. In this paper, a multi-source deep learning-based domain adaptation system is proposed and tested to identify and verify the presence and legibility of use-by date information from food packaging photos taken as part of the validation process as the products pass along the food production line. This was achieved by improving the generalization of the techniques via incorporating new loss functions and making use of multi-source datasets in order to extract domain-invariant representations for all domains and aligning distribution of all pairs of source and target domains in a common feature space, along with the class boundaries. The proposed system performed very well in the conducted experiments, for automating the verification process and reducing labeling errors that could otherwise threaten public health and contravene legal requirements for food packaging information and accuracy. Comprehensive experiments on our food packaging datasets demonstrate that the proposed multi-source deep domain adaptation method significantly improves the classification accuracy and therefore has great potential for application and beneficial impact in food manufacturing control systems.

A method for quantifying aggregate size distribution from the images of soil samples is introduced. Knowledge of soil aggregate size distribution can help to inform soil management practices for the sustainable growth of crops. While current in-field approaches are mostly subjective, obtaining quantifiable results in a laboratory is labour- and time-intensive. Our goal is to develop an imaging technique for quantitative analysis of soil aggregate size distribution, which could provide the basis of a tool for rapid assessment of soil structure. The prediction accuracy of pattern spectra descriptors based on hierarchical representations from attribute morphology are analysed, as well as the impact of using images of different quality and scales. The method is able to handle greater sample complexity than the previous approaches, while working with smaller samples sizes that are easier to handle. The results show promise for size analysis of soils with larger structures, and minimal sample preparation, as typical of soil assessment in agriculture.

The study presents a novel approach, based on deep learning, for diagnosis of Parkinson's disease through medical imaging. The approach includes analysis and use of the knowledge extracted by deep convolutional and recurrent neural networks when trained with medical images, such as magnetic resonance images and dopamine transporters scans. Internal representations of the trained DNNs constitute the extracted knowledge which is used in a transfer learning and domain adaptation manner, so as to create a unified framework for prediction of Parkinson's across different medical environments. A large experimental study is presented illustrating the ability of the proposed approach to effectively predict Parkinson's, using different medical image sets from real environments.

Insects of the family Orthoptera: Acrididae including grasshoppers and locust devastate crops and eco-systems around the globe. The effective control of these insects requires large numbers of trained extension agents who try to spot concentrations of the insects on the ground so that they can be destroyed before they take flight. This is a challenging and difficult task. No automatic detection system is yet available to increase scouting productivity, data scale and fidelity. Here we demonstrate MAESTRO, a novel grasshopper detection framework that deploys deep learning within RBG images to detect insects. MAESTRO uses a state-of-the-art two-stage training deep learning approach. The framework can be deployed not only on desktop computers but also on edge devices without internet connection such as smartphones. MAESTRO can gather data using cloud storage for further research and in-depth analysis. In addition, we provide a challenging new open dataset (GHCID) of highly variable grasshopper populations imaged in Inner Mongolia. The detection performance of the stationary method and the mobile App are 78 and 49 percent respectively; the stationary method requires around 1000 ms to analyze a single image, whereas the mobile app uses only around 400 ms per image. The algorithms are purely data-driven and can be used for other detection tasks in agriculture (e.g. plant disease detection) and beyond. This system can play a crucial role in the collection and analysis of data to enable more effective control of this critical global pest.

There exist various types of information on retail food packages, including use by date, food product name and so on. The correct coding of use by dates on food packages is vitally important for avoiding potential health risks to customers caused by erroneous mislabelling of use by dates. It is extremely tedious and laborious to check the use by dates coding manually by a human operator, which is prone to generate errors thus an automatic system for validating the correctness of the coding of use by dates is needed. In order to construct such a system, firstly it needs to correctly automatic recognize use by dates on food packages. In this work, we propose a novel dual deep neural networks-based methodology for automatic recognition of use by dates in food package photographs recorded by a camera, which is a combination of two networks: a fully convolutional network for use by date ROI detection and a convolutional recurrent neuron network for date character recognition. The proposed methodology is the first attempt to apply deep learning for automatic use by date recognition. From comprehensive experimental evaluations, it is shown that the proposed method can achieve high accuracies in use by date recognition (more than 95% on our testing dataset), given food package images with varying lighting conditions, poor printing quality and varied textual/pictorial contents collected from multiple real retailer sites.

Oncological diseases account for a significant portion of the burden on public healthcare systems with associated costs driven primarily by complex and long-lasting therapies. Through the visualization of patient-specific morphology and functional-molecular pathways, cancerous tissue can be detected and characterized non-invasively, so as to provide referring oncologists with essential information to support therapy management decisions. Following the onset of stand-alone anatomical and functional imaging, we witness a push towards integrating molecular image information through various methods, including anato-metabolic imaging (e.g., PET/CT), advanced MRI, optical or ultrasound imaging.This perspective paper highlights a number of key technological and methodological advances in imaging instrumentation related to anatomical, functional, molecular medicine and hybrid imaging, that is understood as the hardware-based combination of complementary anatomical and molecular imaging. These include novel detector technologies for ionizing radiation used in CT and nuclear medicine imaging, and novel system developments in MRI and optical as well as opto-acoustic imaging. We will also highlight new data processing methods for improved non-invasive tissue characterization. Following a general introduction to the role of imaging in oncology patient management we introduce imaging methods with well-defined clinical applications and potential for clinical translation. For each modality, we report first on the status quo and, then point to perceived technological and methodological advances in a subsequent status go section. Considering the breadth and dynamics of these developments, this perspective ends with a critical reflection on where the authors, with the majority of them being imaging experts with a background in physics and engineering, believe imaging methods will be in a few years from now.Overall, methodological and technological medical imaging advances are geared towards increased image contrast, the derivation of reproducible quantitative parameters, an increase in volume sensitivity and a reduction in overall examination time. To ensure full translation to the clinic, this progress in technologies and instrumentation is complemented by advances in relevant acquisition and image-processing protocols and improved data analysis. To this end, we should accept diagnostic images as “data”, and – through the wider adoption of advanced analysis, including machine learning approaches and a “big data” concept – move to the next stage of non-invasive tumour phenotyping. The scans we will be reading in 10 years from now will likely be composed of highly diverse multi-dimensional data from multiple sources, which mandate the use of advanced and interactive visualization and analysis platforms powered by Artificial Intelligence (AI) for real-time data handling by cross-specialty clinical experts with a domain knowledge that will need to go beyond that of plain imaging.

In this study the problem of fitting shape primitives to point cloud scenes was tackled as a parameter optimisation procedure, and solved using the popular bees algorithm. Tested on three sets of clean and differently blurred point cloud models, the bees algorithm obtained performances comparable to those obtained using the state-of-the-art random sample consensus (RANSAC) method, and superior to those obtained by an evolutionary algorithm. Shape fitting times were compatible with real-time application. The main advantage of the bees algorithm over standard methods is that it doesn&rsquo, t rely on ad hoc assumptions about the nature of the point cloud model like RANSAC approximation tolerance.

Highlights • Segmentation and classification pipeline fully relying on attribute morphology. • Strong locality of the approach avoids resulting foreground noise. • Segmentation outputs regions directly, avoiding the component labelling step. • Max-tree structure enables feature calculation during segmentation. • Competitive classification of plant regions into crop/weed for varying plant types., Discriminating value crops from weeds is an important task in precision agriculture. In this paper, we propose a novel image processing pipeline based on attribute morphology for both the segmentation and classification tasks. The commonly used approaches for vegetation segmentation often rely on thresholding techniques which reach their decisions globally. By contrast, the proposed method works with connected components obtained by image threshold decomposition, which are naturally nested in a hierarchical structure called the max-tree, and various attributes calculated from these regions. Image segmentation is performed by attribute filtering, preserving or discarding the regions based on their attribute value and allowing for the decision to be reached locally. This segmentation method naturally selects a collection of foreground regions rather than pixels, and the same data structure used for segmentation can be further reused to provide the features for classification, which is realised in our experiments by a support vector machine (SVM). We apply our methods to normalised difference vegetation index (NDVI) images, and demonstrate the performance of the pipeline on a dataset collected by the authors in an onion field, as well as a publicly available dataset for sugar beets. The results show that the proposed segmentation approach can segment the fine details of plant regions locally, in contrast to the state-of-the-art thresholding methods, while providing discriminative features which enable efficient and competitive classification rates for crop/weed discrimination.

Human beings can achieve reliable and fast visual pattern recognition with limited time and learning samples. Underlying this capability, ventral stream plays an important role in object representation and form recognition. Modeling the ventral steam may shed light on further understanding the visual brain in humans and building artificial vision systems for pattern recognition. The current methods to model the mechanism of ventral stream are far from exhibiting fast, continuous, and event-driven learning like the human brain. To create a visual system similar to ventral stream in human with fast learning capability, in this paper, we propose a new spiking neural system with an event-driven continuous spike timing dependent plasticity (STDP) learning method using specific spiking timing sequences. Two novel continuous input mechanisms have been used to obtain the continuous input spiking pattern sequence. With the event-driven STDP learning rule, the proposed learning procedure will be activated if the neuron receive one pre- or post-synaptic spike event. The experimental results on MNIST database show that the proposed method outperforms all other methods in fast learning scenarios and most of the current models in exhaustive learning experiments.

Detecting changed regions between two given synthetic aperture radar images is very important to monitor change of landscapes, change of ecosystem and so on. This can be formulated as a classification problem and addressed by learning a classifier, traditional machine learning classification methods very easily stick to local optima which can be caused by noises of data. Hence, we propose an unsupervised algorithm aiming at constructing a classifier based on self-paced learning. Self-paced learning is a recently developed supervised learning approach and has been proven to be capable to overcome effectively this shortcoming. After applying a pre-classification to the difference image, we uniformly select samples using the initial result. Then, self-paced learning is utilized to train a classifier. Finally, a filter is used based on spatial contextual information to further smooth the classification result. In order to demonstrate the efficiency of the proposed algorithm, we apply our proposed algorithm on five real synthetic aperture radar images datasets. The results obtained by our algorithm are compared with five other state-of–the-art algorithms, which demonstrates that our algorithm outperforms those state-of-the-art algorithms in terms of accuracy and robustness.

International audience; A theoretical and experimental analysis related to the effect of noise in the task of vertex identification in unknown shapes is presented. Shapes are seen as real functions of their closed boundary. An alternative global perspective of curvature is examined providing insight into the process of noise-enabled vertex localization. The analysis reveals that noise facilitates in the localization of certain vertices. The concept of noising is thus considered and a relevant global method for localizing Global Vertices is investigated in relation to local methods under the presence of increasing noise. Theoretical analysis reveals that induced noise can indeed help localizing certain vertices if combined with global descriptors. Experiments with noise and a comparison to localized methods validate the theoretical results.

High-throughput phenotyping is a cornerstone of numerous functional genomics projects. In recent years, imaging screens have become increasingly important in understanding gene–phenotype relationships in studies of cells, tissues and whole organisms. Three-dimensional (3D) imaging has risen to prominence in the field of developmental biology for its ability to capture whole embryo morphology and gene expression, as exemplified by the International Mouse Phenotyping Consortium (IMPC). Large volumes of image data are being acquired by multiple institutions around the world that encompass a range of modalities, proprietary software and metadata. To facilitate robust downstream analysis, images and metadata must be standardized to account for these differences. As an open scientific enterprise, making the data readily accessible is essential so that members of biomedical and clinical research communities can study the images for themselves without the need for highly specialized software or technical expertise. In this article, we present a platform of software tools that facilitate the upload, analysis and dissemination of 3D images for the IMPC. Over 750 reconstructions from 80 embryonic lethal and subviable lines have been captured to date, all of which are openly accessible at mousephenotype.org. Although designed for the IMPC, all software is available under an open-source licence for others to use and develop further. Ongoing developments aim to increase throughput and improve the analysis and dissemination of image data. Furthermore, we aim to ensure that images are searchable so that users can locate relevant images associated with genes, phenotypes or human diseases of interest.

It is of significant importance for any classification and recognition system, which claims near or better than human performance to be immune to small perturbations in the dataset. Researchers found out that neural networks are not very robust to small perturbations and can easily be fooled to persistently misclassify by adding a particular class of noise in the test data. This, so-called adversarial noise severely deteriorates the performance of neural networks, which otherwise perform really well on unperturbed dataset. It has been recently proposed that neural networks can be made robust against adversarial noise by training them using the data corrupted with adversarial noise itself. Following this approach, in this paper, we propose a new mechanism to generate a powerful adversarial noise model based on K-support norm to train neural networks. We tested our approach on two benchmark datasets, namely the MNIST and STL-10, using muti-layer perceptron and convolutional neural networks. Experimental results demonstrate that neural networks trained with the proposed technique show significant improvement in robustness as compared to state-of-the-art techniques.

In this prospective study, 36 patients with stage III non-small cell lung cancers (NSCLC), who underwent dynamic contrast-enhanced MRI (DCE-MRI) before concurrent chemo-radiotherapy (CCRT) were enrolled. Pharmacokinetic analysis was carried out after non-rigid motion registration. The perfusion parameters [including Blood Flow (BF), Blood Volume (BV), Mean Transit Time (MTT)] and permeability parameters [including endothelial transfer constant (Ktrans), reflux rate (Kep), fractional extravascular extracellular space volume (Ve), fractional plasma volume (Vp)] were calculated, and their relationship with tumor regression was evaluated. The value of these parameters on predicting responders were calculated by receiver operating characteristic (ROC) curve. Multivariate logistic regression analysis was conducted to find the independent variables. Tumor regression rate is negatively correlated with Ve and its standard variation Ve_SD and positively correlated with Ktrans and Kep. Significant differences between responders and non-responders existed in Ktrans, Kep, Ve, Ve_SD, MTT, BV_SD and MTT_SD (P e e was a significant predictor. Baseline perfusion and permeability parameters calculated from DCE-MRI were seen to be a viable tool for predicting the early treatment response after CCRT of NSCLC.

A decentralized approach for multi-view multi-person tracking in VSNs.Design overcomplete dictionaries matched to the structure of likelihoods functions.Obtain sparse representation of likelihoods to reduce communication in the network.Comparison on well-known L1-solvers to choose a fast and reliable method.Qualitatively and quantitatively, our framework outperforms previous approaches. Recent developments in low-cost CMOS cameras have created the opportunity of bringing imaging capabilities to sensor networks and a new field called visual sensor networks (VSNs) has emerged. VSNs consist of image sensors, embedded processors, and wireless transceivers which are powered by batteries. Since energy and bandwidth resources are limited, setting up a tracking system in VSNs is a challenging problem. In this paper, we present a framework for human tracking in VSN environments. The traditional approach of sending compressed images to a central node has certain disadvantages such as decreasing the performance of further processing (i.e., tracking) because of low quality images. Instead, in our decentralized tracking framework, each camera node performs feature extraction and obtains likelihood functions. We propose a sparsity-driven method that can obtain bandwidth-efficient representation of likelihoods extracted by the camera nodes. Our approach involves the design of special overcomplete dictionaries that match the structure of the likelihoods and the transmission of likelihood information in the network through sparse representation in such dictionaries. We have applied our method for indoor and outdoor people tracking scenarios and have shown that it can provide major savings in communication bandwidth without significant degradation in tracking performance. We have compared the tracking results and communication loads with a block-based likelihood compression scheme, a decentralized tracking method and a distributed tracking method. Experimental results show that our sparse representation framework is an effective approach that can be used together with any probabilistic tracker in VSNs.

Pursuit robots (autonomous robots tasked with tracking and pursuing a moving target) require accurate tracking of the target's position over time. One possibly effective pursuit platform is a quadcopter equipped with basic sensors and a monocular camera. However, combined noise of the quadcopter's sensors causes large disturbances of target's 3D position estimate. To solve this problem, in this paper, we propose a novel method for joint localization of a quadcopter pursuer with a monocular camera and an arbitrary target. Our method localizes both the pursuer and target with respect to a common reference frame. The joint localization method fuses the quadcopter's kinematics and the target's dynamics in a joint state space model. We show that predicting and correcting pursuer and target trajectories simultaneously produces better results than standard approaches to estimating relative target trajectories in a 3D coordinate system. Our method also comprises a computationally efficient visual tracking method capable of redetecting a temporarily lost target. The efficiency of the proposed method is demonstrated by a series of experiments with a real quadcopter pursuing a human. The results show that the visual tracker can deal effectively with target occlusions and that joint localization outperforms standard localization methods.

We present a fast and precise vision-based software intended for multiple robot localization. The core component of the software is a novel and efficient algorithm for black and white pattern detection. The method is robust to variable lighting conditions, achieves sub-pixel precision and its computational complexity is independent of the processed image size. With off-the-shelf computational equipment and low-cost cameras, the core algorithm is able to process hundreds of images per second while tracking hundreds of objects with a millimeter precision. In addition, we present the method's mathematical model, which allows to estimate the expected localization precision, area of coverage, and processing speed from the camera's intrinsic parameters and hardware's processing capacity. The correctness of the presented model and performance of the algorithm in real-world conditions is verified in several experiments. Apart from the method description, we also make its source code public at \emph{http://purl.org/robotics/whycon}; so, it can be used as an enabling technology for various mobile robotic problems.

Obtaining a "correct" view in echocardiography is a subjective process in which an operator attempts to obtain images conforming to consensus standard views. Real-time objective quantification of image alignment may assist less experienced operators, but no reliable index yet exists. We present a fully automated algorithm for detecting incorrect medial/lateral translation of an ultrasound probe by image analysis. The ability of the algorithm to distinguish optimal from sub-optimal four-chamber images was compared to that of specialists-the current "gold-standard." The orientation assessments produced by the automated algorithm correlated well with consensus visual assessments of the specialists ([Formula: see text]) and compared favourably with the correlation between individual specialists and the consensus, [Formula: see text]. Each individual specialist's assessments were within the consensus of other specialists, [Formula: see text] of the time, and the algorithm's assessments were within the consensus of specialists 85% of the time. The mean discrepancy in probe translation values between individual specialists and their consensus was [Formula: see text], and between the automated algorithm and specialists' consensus was [Formula: see text]. This technology could be incorporated into hardware to provide real-time guidance for image optimisation-a potentially valuable tool both for training and quality control.

The rapidly increasing quantity of publicly available videos has driven research into developing automatic tools for indexing, rating, searching and retrieval. Textual semantic representations, such as tagging, labelling and annotation, are often important factors in the process of indexing any video, because of their user-friendly way of representing the semantics appropriate for search and retrieval. Ideally, this annotation should be inspired by the human cognitive way of perceiving and of describing videos. The difference between the low-level visual contents and the corresponding human perception is referred to as the ‘semantic gap’. Tackling this gap is even harder in the case of unconstrained videos, mainly due to the lack of any previous information about the analyzed video on the one hand, and the huge amount of generic knowledge required on the other. This paper introduces a framework for the Automatic Semantic Annotation of unconstrained videos. The proposed framework utilizes two non-domain-specific layers: low-level visual similarity matching, and an annotation analysis that employs commonsense knowledgebases. Commonsense ontology is created by incorporating multiple-structured semantic relationships. Experiments and black-box tests are carried out on standard video databases for action recognition and video information retrieval. White-box tests examine the performance of the individual intermediate layers of the framework, and the evaluation of the results and the statistical analysis show that integrating visual similarity matching with commonsense semantic relationships provides an effective approach to automated video annotation.

Integration is a crucial step in the reconstruction of complete 3D surface model from multiple scans.\ud Ever-present registration errors and scanning noise make integration a nontrivial problem. In this paper,\ud we propose a novel method for multi-view scan integration where we solve it as a labelling problem.\ud Unlike previous methods, which have been based on various merging schemes, our labelling-based\ud method is essentially a selection strategy. The overall surface model is composed of surface patches from\ud selected input scans. We formulate the labelling via a higher-order Markov Random Field (MRF) which\ud assigns a label representing an index of some input scan to every point in a base surface. Using a higherorder\ud MRF allows us to more effectively capture spatial relations between 3D points. We employ belief\ud propagation to infer this labelling and experimentally demonstrate that this integration approach\ud provides significantly improved integration via both qualitative and quantitative comparisons.

This paper presents an approach to categorize typical places in indoor environments using 3D scans provided by a laser range finder. Examples of such places are offices, laboratories, or kitchens. In our method, we combine the range and reflectance data from the laser scan for the final categorization of places. Range and reflectance images are transformed into histograms of local binary patterns and combined into a single feature vector. This vector is later classified using support vector machines. The results of the presented experiments demonstrate the capability of our technique to categorize indoor places with high accuracy. We also show that the combination of range and reflectance information improves the final categorization results in comparison with a single modality.

In this paper, we propose a novel computer vision-based fall detection system for monitoring an elderly person in a home care, assistive living application. Initially, a single camera covering the full view of the room environment is used for the video recording of an elderly person's daily activities for a certain time period. The recorded video is then manually segmented into short video clips containing normal postures, which are used to compose the normal dataset. We use the codebook background subtraction technique to extract the human body silhouettes from the video clips in the normal dataset and information from ellipse fitting and shape description, together with position information, is used to provide features to describe the extracted posture silhouettes. The features are collected and an online one class support vector machine (OCSVM) method is applied to find the region in feature space to distinguish normal daily postures and abnormal postures such as falls. The resultant OCSVM model can also be updated by using the online scheme to adapt to new emerging normal postures and certain rules are added to reduce false alarm rate and thereby improve fall detection performance. From the comprehensive experimental evaluations on datasets for 12 people, we confirm that our proposed person-specific fall detection system can achieve excellent fall detection performance with 100% fall detection rate and only 3% false detection rate with the optimally tuned parameters. This work is a semiunsupervised fall detection system from a system perspective because although an unsupervised-type algorithm (OCSVM) is applied, human intervention is needed for segmenting and selecting of video clips containing normal postures. As such, our research represents a step toward a complete unsupervised fall detection system.

We propose a novel computer vision based fall detection system for monitoring an elderly person in a home care application. Background subtraction is applied to extract the foreground human body and the result is improved by using certain post-processing. Information from ellipse fitting and a projection histogram along the axes of the ellipse are used as the features for distinguishing different postures of the human. These features are then fed into a directed acyclic graph support vector machine (DAGSVM) for posture classification, the result of which is then combined with derived floor information to detect a fall. From a dataset of 15 people, we show that our fall detection system can achieve a high fall detection rate (97.08%) and a very low false detection rate (0.8%) in a simulated home environment.

This paper introduces novel non-contact methods for detecting faults in heat seals of food packages. Two alternative imaging technologies are investigated; laser scatter imaging and polarised light stress images. After segmenting the seal area from the rest of the respective image, a classifier is trained to detect faults in different regions of the seal area using features extracted from the pixels in the respective region. A very large set of candidate features, based on statistical information relating to the colour and texture of each region, is first extracted. Then an adaptive boosting algorithm (AdaBoost) is used to automatically select the best features for discriminating faults from non-faults. With this approach, different features can be selected and optimised for the different imaging methods. In experiments we compare the performance of classifiers trained using features extracted from laser scatter images only, polarised light stress images only, and a combination of both image types. The results show that the polarised light and laser scatter classifiers achieved accuracies of 96% and 90%, respectively, while the combination of both sensors achieved an accuracy of 95%. These figures suggest that both systems have potential for commercial development.

In this paper, we introduce a video-based robust fall detection system for monitoring an elderly person in a smart room environment. Video features, namely the centroid and orientation of a voxel person, are extracted. The boundary method, which is an example one class classification technique, is then used to determine whether the incoming features lie in the ‘fall region’ of the feature space, and thereby effectively distinguishing a fall from other activities, such as walking, sitting, standing, crouching or lying. Four different types of boundary methods, k-center, k-th nearest neighbor, one class support vector machine and single class minimax probability machine are assessed on representative test datasets. The comparison is made on the following three aspects: 1). True positive rate, false positive rate and geometric means in detection 2). Robustness to noise in the training dataset 3). The computational time for the test phase. From the comparison results, we show that the single class minimax probability machine achieves the best overall performance. By applying one class classification techniques with 3-d features, we can obtain a more efficient fall detection system with acceptable performance, as shown in the experimental part; besides, it can avoid the drawbacks of other traditional fall detection methods.

This paper presents an approach for tracking multiple persons on a mobile robot with a combination of colour and thermal vision sensors, using several new techniques. First, an adaptive colour model is incorporated into the measurement model of the tracker. Second, a new approach for detecting occlusions is introduced, using a machine learning classifier for pairwise comparison of persons (classifying which one is in front of the other). Third, explicit occlusion handling is incorporated into the tracker. The paper presents a comprehensive, quantitative evaluation of the whole system and its different components using several real world data sets.

We describe a new pose-estimation algorithm via integration of the strength in both empirical mode decomposition (EMD) and mutual information. While mutual information is exploited to measure the similarity between facial images to estimate poses, EMD is exploited to decompose input facial images into a number of intrinsic mode function (IMF) components, which redistribute the effect of noise, expression changes, and illumination variations as such that, when the input facial image is described by the selected IMF components, all the negative effects can be minimized. Extensive experiments were carried out in comparisons to existing representative techniques, and the results show that the proposed algorithm achieves better pose-estimation performances with robustness to noise corruption, illumination variation, and facial expressions.

Foreground segmentation is a fundamental first processing stage for vision systems which monitor real-world activity. In this paper, we consider the problem of achieving robust segmentation in scenes where the appearance of the background varies unpredictably over time. Variations may be caused by processes such as moving water, or foliage moved by wind, and typically degrade the performance of standard per-pixel background models. Our proposed approach addresses this problem by modeling homogeneous regions of scene pixels as an adaptive mixture of Gaussians in color and space. Model components are used to represent both the scene background and moving foreground objects. Newly observed pixel values are probabilistically classified, such that the spatial variance of the model components supports correct classification even when the background appearance is significantly distorted. We evaluate our method over several challenging video sequences, and compare our results with both per-pixel and Markov Random Field based models. Our results show the effectiveness of our approach in reducing incorrect classifications.

Copyright © 2009 Elsevier B.V. All rights reserved. In this paper, a human action recognition system is proposed. The system is based on new, descriptive ‘temporal template’ features in order to achieve high-speed recognition in real-time, embedded applications. The limitations of the well-known ‘Motion History Image’ (MHI) temporal template are addressed and a new ‘Motion History Histogram’ (MHH) feature is proposed to capture more motion information in the video. MHH not only provides rich motion information, but also remains computationally inexpensive. To further improve classification performance, we combine both MHI and MHH into a low dimensional feature vector which is processed by a support vector machine (SVM). Experimental results show that our new representation can achieve a significant improvement in the performance of human action recognition over existing comparable methods, which use 2D temporal template based representations.

This paper presents a vision-based approach to simultaneous localization and mapping (SLAM) in indoor/outdoor environments with minimalistic sensing and computational requirements. The approach is based on a graph representation of robot poses, using a relaxation algorithm to obtain a globally consistent map. Each link corresponds to a relative measurement of the spatial relation between the two nodes it connects. The links describe the likelihood distribution of the relative pose as a Gaussian distribution. To estimate the covariance matrix for links obtained from an omnidirectional vision sensor, a novel method is introduced based on the relative similarity of neighboring images. This new method does not require the determination of distances to image features using multiple-view geometry, for example. Combined indoor and outdoor experiments demonstrate that the approach can handle different environments (without modification of the parameters), and it can cope with violations of the ldquoflat floor assumptionrdquo to some degree and scales well with increasing size of the environment, producing topologically correct and geometrically accurate maps at low computational cost. Further experiments demonstrate that the approach is also suitable for combining multiple overlapping maps, e.g., for solving the multirobot SLAM problem with unknown initial poses.