Omnidirectional (or 360°) cameras are acquisition devices that, in the next few years, could have a big impact on video surveillance applications, research, and industry, as they can record a spherical view of a whole environment from every perspective. This paper presents two new contributions to the research community: the CVIP360 dataset, an annotated dataset of 360° videos for distancing applications, and a new method to estimate the distances of objects in a scene from a single 360° image. The CVIP360 dataset includes 16 videos acquired outdoors and indoors, annotated by adding information about the pedestrians in the scene (bounding boxes) and the distances to the camera of some points in the 3D world by using markers at fixed and known intervals. The proposed distance estimation algorithm is based on geometry facts regarding the acquisition process of the omnidirectional device, and is uncalibrated in practice: the only required parameter is the camera height. The proposed algorithm was tested on the CVIP360 dataset, and empirical results demonstrate that the estimation error is negligible for distancing applications. Full article

Falls are one of the most critical health care risks for elderly people, being, in some adverse circumstances, an indirect cause of death. Furthermore, demographic forecasts for the future show a growing elderly population worldwide. In this context, models for automatic fall detection and prediction are of paramount relevance, especially AI applications that use ambient, sensors or computer vision. In this paper, we present an approach for fall detection using computer vision techniques. Video sequences of a person in a closed environment are used as inputs to our algorithm. In our approach, we first apply the V2V-PoseNet model to detect 2D body skeleton in every frame. Specifically, our approach involves four steps: (1) the body skeleton is detected by V2V-PoseNet in each frame; (2) joints of skeleton are first mapped into the Riemannian manifold of positive semidefinite matrices of fixed-rank 2 to build time-parameterized trajectories; (3) a temporal warping is performed on the trajectories, providing a (dis-)similarity measure between them; (4) finally, a pairwise proximity function SVM is used to classify them into fall or non-fall, incorporating the (dis-)similarity measure into the kernel function. We evaluated our approach on two publicly available datasets URFD and Charfi. The results of the proposed approach are competitive with respect to state-of-the-art methods, while only involving 2D body skeletons. Full article

In this work, an unsupervised volumetric semantic instance segmentation of the plasma membrane of HeLa cells as observed with serial block face scanning electron microscopy is described. The resin background of the images was segmented at different slices of a 3D stack of 518 slices with 8192 × 8192 pixels each. The background was used to create a distance map, which helped identify and rank the cells by their size at each slice. The centroids of the cells detected at different slices were linked to identify them as a single cell that spanned a number of slices. A subset of these cells, i.e., the largest ones and those not close to the edges were selected for further processing. The selected cells were then automatically cropped to smaller regions of interest of 2000 × 2000 × 300 voxels that were treated as cell instances. Then, for each of these volumes, the nucleus was segmented, and the cell was separated from any neighbouring cells through a series of traditional image processing steps that followed the plasma membrane. The segmentation process was repeated for all the regions of interest previously selected. For one cell for which the ground truth was available, the algorithm provided excellent results in Accuracy (AC) and the Jaccard similarity Index (JI): nucleus: JI $=0.9665$, AC $=0.9975$, cell including nucleus JI $=0.8711$, AC $=0.9655$, cell excluding nucleus JI $=0.8094$, AC $=0.9629$. A limitation of the algorithm for the plasma membrane segmentation was the presence of background. In samples with tightly packed cells, this may not be available. When tested for these conditions, the segmentation of the nuclear envelope was still possible. All the code and data were released openly through GitHub, Zenodo and EMPIAR. Full article

This paper describes in detail VISIONE, a video search system that allows users to search for videos using textual keywords, the occurrence of objects and their spatial relationships, the occurrence of colors and their spatial relationships, and image similarity. These modalities can be combined together to express complex queries and meet users’ needs. The peculiarity of our approach is that we encode all information extracted from the keyframes, such as visual deep features, tags, color and object locations, using a convenient textual encoding that is indexed in a single text retrieval engine. This offers great flexibility when results corresponding to various parts of the query (visual, text and locations) need to be merged. In addition, we report an extensive analysis of the retrieval performance of the system, using the query logs generated during the Video Browser Showdown (VBS) 2019 competition. This allowed us to fine-tune the system by choosing the optimal parameters and strategies from those we tested. Full article

Skin lesion segmentation is a primary step for skin lesion analysis, which can benefit the subsequent classification task. It is a challenging task since the boundaries of pigment regions may be fuzzy and the entire lesion may share a similar color. Prevalent deep learning methods for skin lesion segmentation make predictions by ensembling different convolutional neural networks (CNN), aggregating multi-scale information, or by multi-task learning framework. The main purpose of doing so is trying to make use of as much information as possible so as to make robust predictions. A multi-task learning framework has been proved to be beneficial for the skin lesion segmentation task, which is usually incorporated with the skin lesion classification task. However, multi-task learning requires extra labeling information which may not be available for the skin lesion images. In this paper, a novel CNN architecture using auxiliary information is proposed. Edge prediction, as an auxiliary task, is performed simultaneously with the segmentation task. A cross-connection layer module is proposed, where the intermediate feature maps of each task are fed into the subblocks of the other task which can implicitly guide the neural network to focus on the boundary region of the segmentation task. In addition, a multi-scale feature aggregation module is proposed, which makes use of features of different scales and enhances the performance of the proposed method. Experimental results show that the proposed method obtains a better performance compared with the state-of-the-art methods with a Jaccard Index (JA) of $79.46$, Accuracy (ACC) of $94.32$, SEN of $88.76$ with only one integrated model, which can be learned in an end-to-end manner. Full article

Object detection models are usually trained and evaluated on highly complicated, challenging academic datasets, which results in deep networks requiring lots of computations. However, a lot of operational use-cases consist of more constrained situations: they have a limited number of classes to be detected, less intra-class variance, less lighting and background variance, constrained or even fixed camera viewpoints, etc. In these cases, we hypothesize that smaller networks could be used without deteriorating the accuracy. However, there are multiple reasons why this does not happen in practice. Firstly, overparameterized networks tend to learn better, and secondly, transfer learning is usually used to reduce the necessary amount of training data. In this paper, we investigate how much we can reduce the computational complexity of a standard object detection network in such constrained object detection problems. As a case study, we focus on a well-known single-shot object detector, YoloV2, and combine three different techniques to reduce the computational complexity of the model without reducing its accuracy on our target dataset. To investigate the influence of the problem complexity, we compare two datasets: a prototypical academic (Pascal VOC) and a real-life operational (LWIR person detection) dataset. The three optimization steps we exploited are: swapping all the convolutions for depth-wise separable convolutions, perform pruning and use weight quantization. The results of our case study indeed substantiate our hypothesis that the more constrained a problem is, the more the network can be optimized. On the constrained operational dataset, combining these optimization techniques allowed us to reduce the computational complexity with a factor of 349, as compared to only a factor 9.8 on the academic dataset. When running a benchmark on an Nvidia Jetson AGX Xavier, our fastest model runs more than 15 times faster than the original YoloV2 model, whilst increasing the accuracy by 5% Average Precision (AP). Full article

As difficult vision-based tasks like object detection and monocular depth estimation are making their way in real-time applications and as more light weighted solutions for autonomous vehicles navigation systems are emerging, obstacle detection and collision prediction are two very challenging tasks for small embedded devices like drones. We propose a novel light weighted and time-efficient vision-based solution to predict Time-to-Collision from a monocular video camera embedded in a smartglasses device as a module of a navigation system for visually impaired pedestrians. It consists of two modules: a static data extractor made of a convolutional neural network to predict the obstacle position and distance and a dynamic data extractor that stacks the obstacle data from multiple frames and predicts the Time-to-Collision with a simple fully connected neural network. This paper focuses on the Time-to-Collision network’s ability to adapt to new sceneries with different types of obstacles with supervised learning. Full article

This article presents the smoothed shock filter, which iteratively produces local segmentations in image’s inflection zones with smoothed morphological operators (dilations, erosions). Hence, it enhances contours by creating smoothed ruptures, while preserving homogeneous regions. After describing the algorithm, we show that it is a robust approach for denoising, compared to related works. Then, we expose how we exploited this filter as a pre-processing step in different image analysis tasks (medical image segmentation, fMRI, and texture classification). By means of its ability to enhance important patterns in images, the smoothed shock filter has a real positive impact upon such applications, for which we would like to explore it more in the future. Full article

Methods for No-Reference Video Quality Assessment (NR-VQA) of consumer-produced video content are largely investigated due to the spread of databases containing videos affected by natural distortions. In this work, we design an effective and efficient method for NR-VQA. The proposed method exploits a novel sampling module capable of selecting a predetermined number of frames from the whole video sequence on which to base the quality assessment. It encodes both the quality attributes and semantic content of video frames using two lightweight Convolutional Neural Networks (CNNs). Then, it estimates the quality score of the entire video using a Support Vector Regressor (SVR). We compare the proposed method against several relevant state-of-the-art methods using four benchmark databases containing user generated videos (CVD2014, KoNViD-1k, LIVE-Qualcomm, and LIVE-VQC). The results show that the proposed method at a substantially lower computational cost predicts subjective video quality in line with the state of the art methods on individual databases and generalizes better than existing methods in cross-database setup. Full article

Compared to single source systems, stereo X-ray CT systems allow acquiring projection data within a reduced amount of time, for an extended field-of-view, or for dual X-ray energies. To exploit the benefit of a dual X-ray system, its acquisition geometry needs to be calibrated. Unfortunately, in modular stereo X-ray CT setups, geometry misalignment occurs each time the setup is changed, which calls for an efficient calibration procedure. Although many studies have been dealing with geometry calibration of an X-ray CT system, little research targets the calibration of a dual cone-beam X-ray CT system. In this work, we present a phantom-based calibration procedure to accurately estimate the geometry of a stereo cone-beam X-ray CT system. With simulated as well as real experiments, it is shown that the calibration procedure can be used to accurately estimate the geometry of a modular stereo X-ray CT system thereby reducing the misalignment artifacts in the reconstruction volumes. Full article

In recent years, automatic tissue phenotyping has attracted increasing interest in the Digital Pathology (DP) field. For Colorectal Cancer (CRC), tissue phenotyping can diagnose the cancer and differentiate between different cancer grades. The development of Whole Slide Images (WSIs) has provided the required data for creating automatic tissue phenotyping systems. In this paper, we study different hand-crafted feature-based and deep learning methods using two popular multi-classes CRC-tissue-type databases: Kather-CRC-2016 and CRC-TP. For the hand-crafted features, we use two texture descriptors (LPQ and BSIF) and their combination. In addition, two classifiers are used (SVM and NN) to classify the texture features into distinct CRC tissue types. For the deep learning methods, we evaluate four Convolutional Neural Network (CNN) architectures (ResNet-101, ResNeXt-50, Inception-v3, and DenseNet-161). Moreover, we propose two Ensemble CNN approaches: Mean-Ensemble-CNN and NN-Ensemble-CNN. The experimental results show that the proposed approaches outperformed the hand-crafted feature-based methods, CNN architectures and the state-of-the-art methods in both databases. Full article

Visual features and representation learning strategies experienced huge advances in the previous decade, mainly supported by deep learning approaches. However, retrieval tasks are still performed mainly based on traditional pairwise dissimilarity measures, while the learned representations lie on high dimensional manifolds. With the aim of going beyond pairwise analysis, post-processing methods have been proposed to replace pairwise measures by globally defined measures, capable of analyzing collections in terms of the underlying data manifold. The most representative approaches are diffusion and ranked-based methods. While the diffusion approaches can be computationally expensive, the rank-based methods lack theoretical background. In this paper, we propose an efficient Rank-based Diffusion Process which combines both approaches and avoids the drawbacks of each one. The obtained method is capable of efficiently approximating a diffusion process by exploiting rank-based information, while assuring its convergence. The algorithm exhibits very low asymptotic complexity and can be computed regionally, being suitable to outside of dataset queries. An experimental evaluation conducted for image retrieval and person re-ID tasks on diverse datasets demonstrates the effectiveness of the proposed approach with results comparable to the state-of-the-art. Full article

Demand for wind power has grown, and this has increased wind turbine blade (WTB) inspections and defect repairs. This paper empirically investigates the performance of state-of-the-art deep learning algorithms, namely, YOLOv3, YOLOv4, and Mask R-CNN for detecting and classifying defects by type. The paper proposes new performance evaluation measures suitable for defect detection tasks, and these are: Prediction Box Accuracy, Recognition Rate, and False Label Rate. Experiments were carried out using a dataset, provided by the industrial partner, that contains images from WTB inspections. Three variations of the dataset were constructed using different image augmentation settings. Results of the experiments revealed that on average, across all proposed evaluation measures, Mask R-CNN outperformed all other algorithms when transformation-based augmentations (i.e., rotation and flipping) were applied. In particular, when using the best dataset, the mean Weighted Average (mWA) values (i.e., mWA is the average of the proposed measures) achieved were: Mask R-CNN: 86.74%, YOLOv3: 70.08%, and YOLOv4: 78.28%. The paper also proposes a new defect detection pipeline, called Image Enhanced Mask R-CNN (IE Mask R-CNN), that includes the best combination of image enhancement and augmentation techniques for pre-processing the dataset, and a Mask R-CNN model tuned for the task of WTB defect detection and classification. Full article

In this paper, we provide an overview on the foundation and first results of a very recent quantum theory of color perception, together with novel results about uncertainty relations for chromatic opposition. The major inspiration for this model is the 1974 remarkable work by H.L. Resnikoff, who had the idea to give up the analysis of the space of perceived colors through metameric classes of spectra in favor of the study of its algebraic properties. This strategy permitted to reveal the importance of hyperbolic geometry in colorimetry. Starting from these premises, we show how Resnikoff’s construction can be extended to a geometrically rich quantum framework, where the concepts of achromatic color, hue and saturation can be rigorously defined. Moreover, the analysis of pure and mixed quantum chromatic states leads to a deep understanding of chromatic opposition and its role in the encoding of visual signals. We complete our paper by proving the existence of uncertainty relations for the degree of chromatic opposition, thus providing a theoretical confirmation of the quantum nature of color perception. Full article

The empirical wavelet transform is an adaptive multi-resolution analysis tool based on the idea of building filters on a data-driven partition of the Fourier domain. However, existing 2D extensions are constrained by the shape of the detected partitioning. In this paper, we provide theoretical results that permits us to build 2D empirical wavelet filters based on an arbitrary partitioning of the frequency domain. We also propose an algorithm to detect such partitioning from an image spectrum by combining a scale-space representation to estimate the position of dominant harmonic modes and a watershed transform to find the boundaries of the different supports making the expected partition. This whole process allows us to define the empirical watershed wavelet transform. We illustrate the effectiveness and the advantages of such adaptive transform, first visually on toy images, and next on both unsupervised texture segmentation and image deconvolution applications. Full article

(1) Background: Transfer learning refers to machine learning techniques that focus on acquiring knowledge from related tasks to improve generalization in the tasks of interest. In magnetic resonance imaging (MRI), transfer learning is important for developing strategies that address the variation in MR images from different imaging protocols or scanners. Additionally, transfer learning is beneficial for reutilizing machine learning models that were trained to solve different (but related) tasks to the task of interest. The aim of this review is to identify research directions, gaps in knowledge, applications, and widely used strategies among the transfer learning approaches applied in MR brain imaging; (2) Methods: We performed a systematic literature search for articles that applied transfer learning to MR brain imaging tasks. We screened 433 studies for their relevance, and we categorized and extracted relevant information, including task type, application, availability of labels, and machine learning methods. Furthermore, we closely examined brain MRI-specific transfer learning approaches and other methods that tackled issues relevant to medical imaging, including privacy, unseen target domains, and unlabeled data; (3) Results: We found 129 articles that applied transfer learning to MR brain imaging tasks. The most frequent applications were dementia-related classification tasks and brain tumor segmentation. The majority of articles utilized transfer learning techniques based on convolutional neural networks (CNNs). Only a few approaches utilized clearly brain MRI-specific methodology, and considered privacy issues, unseen target domains, or unlabeled data. We proposed a new categorization to group specific, widely-used approaches such as pretraining and fine-tuning CNNs; (4) Discussion: There is increasing interest in transfer learning for brain MRI. Well-known public datasets have clearly contributed to the popularity of Alzheimer’s diagnostics/prognostics and tumor segmentation as applications. Likewise, the availability of pretrained CNNs has promoted their utilization. Finally, the majority of the surveyed studies did not examine in detail the interpretation of their strategies after applying transfer learning, and did not compare their approach with other transfer learning approaches. Full article