Vassilios Morellas

• University of Minnesota, PhD
• Research Professor at University of Minnesota

Current methods require robots to be reprogrammed for every new task, consuming many engineering resources. This work focuses on integrating real and simulated environments for our proposed “Internet of Skills,” which enables robots to learn advanced skills from a small set of expert demonstrations. By expanding on recent work in the areas of Learn...

Representations in the form of Symmetric Positive Definite (SPD) matrices have been popularized in a variety of visual learning applications due to their demonstrated ability to capture rich second-order statistics of visual data. There exist several similarity measures for comparing SPD matrices with documented benefits. However, selecting an appr...

Representations in the form of Symmetric Positive Definite (SPD) matrices have been popularized in a variety of visual learning applications due to their demonstrated ability to capture rich second-order statistics of visual data. There exist several similarity measures for comparing SPD matrices with documented benefits. However, selecting an appr...

Neuropsychiatric disorders are highly prevalent conditions with significant individual, societal, and economic impacts. A major challenge in the diagnosis and treatment of these conditions is the lack of sensitive, reliable, objective, quantitative tools to inform diagnosis, and measure symptom severity. Currently available assays rely on self-repo...

Introduction: Cancerous Tissue Recognition (CTR) methodologies are continuously integrating advancements at the forefront of machine learning and computer vision, providing a variety of inference schemes for histopathological data. Histopathological data, in most cases, come in the form of high-resolution images, and thus methodologies operating at...

A major component of an efficient farming strategy is the precise detection and characterization of plant deficiencies followed by the proper deployment of fertilizers. Through the thoughtful utilization of modern computer vision techniques, it is possible to achieve positive financial and environmental results for these tasks. This work introduces...

High resolution RGB imagery collected using a UAV and a handheld camera was used with structure from motion to reconstruct 3D canopies of small groups of corn plants. A methodology for the automated extraction of phenotypic characteristics of individual plants is presented based on these 3D reconstructed canopies. Such information can enhance the e...

We and others have successfully applied computer vision to diagnosing a variety of malignant neoplasms in histopathologic images. Machine learning being an opaque process, little is known about the basis on which computer vision makes its diagnostic decisions in surgical pathology. Here, we use class saliency maps to determine which parts of the im...

Financial and social elements of modern societies are closely connected to the cultivation of corn. Due to its massive production, deficiencies during the cultivation process directly translate to major financial losses. Since proper surveillance in a large scale is still very challenging, the companies that specialize in optimizing crop yield are...

Kidney cancer is projected to be the sixth most common cancer in men and the tenth most common cancer in women in 2018 [PMID29313949]. The morphological and anatomic features of kidneys and renal tumors have been shown to correlate with important patient outcomes [1]. Automatic segmentation with deep learning offers a way to compute these features...

Mental health disorders are a leading cause of disability in North America. An important aspect in treating mental disorders is early intervention, which dramatically increases the probability of positive outcomes; however, early intervention hinges upon knowledge and detection of risk markers for particular disorders. Ideally, the screening of the...

Computer Aided Diagnosis (CAD) systems are adopting advancements at the forefront of computer vision and machine learning towards assisting medical experts with providing faster diagnoses. The success of CAD systems heavily relies on the availability of high-quality annotated data. Towards supporting the annotation process among teams of medical ex...

Symmetric positive definite (SPD) matrices are useful for capturing second-order statistics of visual data. To compare two SPD matrices, several measures are available, such as the affine-invariant Riemannian metric, Jeffreys divergence , Jensen-Bregman logdet divergence, etc.; however , their behaviors may be application dependent, raising the nee...

Symmetric positive definite (SPD) matrices are useful for capturing second-order statistics of visual data. To compare two SPD matrices, several measures are available, such as the affine-invariant Riemannian metric, Jeffreys divergence, Jensen-Bregman logdet divergence, etc.; however, their behaviors may be application dependent, raising the need...

Objectives: The clinical presentation of pediatric obsessive-compulsive disorder (OCD) is heterogeneous, which is a stumbling block to understanding pathophysiology and to developing new treatments. A major shift in psychiatry, embodied in the Research Domain Criteria (RDoC) initiative of National Institute of Mental Health, recognizes the pitfall...

Objectives Previous research has examined the influence of the physical environment on the manifestation of mental health conditions such as ASD. This pilot study sought to identify differences in visual preferences in children and adolescents with OCD to begin exploring how visual design may impact OCD and how it may be used to create environments...

Determining and detecting risk markers for mental illness remains a labor intensive process, requiring vast amounts of observations by clinical professionals. Motor stereotypies, which are defined as involuntary repetitive motor behaviors, invariant in form, that, to an observer, appear to serve no purpose, are a class of risk markers which are ver...

The continuously growing need for increasing the production of food and reducing the degradation of water supplies, has led to the development of several precision agriculture systems over the past decade so as to meet the needs of modern societies. The present study describes a methodology for the detection and characterization of Nitrogen (N) def...

Symmetric Positive Definite (SPD) matrices emerge as data descriptors in several applications of computer vision such as object tracking, texture recognition, and diffusion tensor imaging. Clustering these data matrices forms an integral part of these applications, for which soft-clustering algorithms (K-Means, Expectation Maximization, etc.) are g...

Sparse models have proven to be extremely successful in image processing and computer vision. However, a majority of the effort has been focused on sparse representation of vectors and low-rank models for general matrices. The success of sparse modeling, along with popularity of region covariances, has inspired the development of sparse coding appr...

This paper presents a new nearest neighbor (NN) retrieval framework: robust sparse hashing (RSH). Our approach is inspired by the success of dictionary learning for sparse coding. Our key idea is to sparse code the data using a learned dictionary, and then to generate hash codes out of these sparse codes for accurate and fast NN retrieval. But, dir...

The early detection of developmental disorders is key to child outcome, allowing interventions to be initiated which promote development and improve prognosis. Research on autism spectrum disorder (ASD) suggests that behavioral signs can be observed late in the first year of life. Many of these studies involve extensive frame-by-frame video observa...

Recognizing actions is one of the important challenges in computer vision with respect to video data, with applications to surveillance, diagnostics of mental disorders, and video retrieval. Compared to other data modalities such as documents and images, processing video data demands orders of magnitude higher computational and storage resources. O...

Tractor-trailer freight hauling has increased markedly within the United States over the past several years, resulting in higher truck volumes. commercial heavy vehicle drivers are required under federal Hours Of Services rules to rest and take breaks to mitigate driving while fatigued. Although there are many rest area facilities available to truc...

In recent years, there has been extensive research on sparse representation of vector-valued signals. In the matrix case, the data points are merely vectorized and treated as vectors thereafter (for example, image patches). However, this approach cannot be used for all matrices, as it may destroy the inherent structure of the data. Symmetric positi...

Computer vision as an entire field has a wide and diverse range of applications. The specific application for this project was in the realm of dance, notably ballet and choreography. This project was proof-of-concept for a choreography assistance tool used to recognize and record dance movements demonstrated by a choreographer. Keeping the commerci...

Presented are results demonstrating that, in developing a system with its first objective being the sustained detection of adults and young children as they move and interact in a normal preschool setting, the direct application of the straightforward RGB-D innovations presented here significantly outperforms even far more algorithmically advanced...

Video object segmentation is a challenging problem due to the presence of deformable, connected, and articulated objects, intra- and inter-object occlusions, object motion, and poor lighting. Some of these challenges call for object models that can locate a desired object and separate it from its surrounding background, even when both share similar...

Object recognition algorithms often focus on determining the class of a detected object in a scene. Two significant phases are usually involved in object recognition. The first phase is the object representation phase, in which the most suitable features that provide the best discriminative power under constraints such as lighting, resolution, scal...

The early detection of developmental disorders is key to child outcome, allowing interventions to be initiated that promote development and improve prognosis. Research on autism spectrum disorder (ASD) suggests behavioral markers can be observed late in the first year of life. Many of these studies involved extensive frame-by-frame video observatio...

The early detection of developmental disorders is key to child outcome, allowing interventions to be initiated that promote development and improve prognosis. Research on autism spectrum disorder (ASD) suggests behavioral markers can be observed late in the first year of life. Many of these studies involved extensive frame-by-frame video observatio...

Early intervention in mental disorders can dramatically increase an individual's quality of life. Additionally, when symptoms of mental illness appear in childhood or adolescence, they represent the later stages of a process that began years earlier. One goal of psychiatric research is to identify risk-markers: genetic, neural, behavioral and/or so...

We study Nearest Neighbors (NN) retrieval by introducing a new approach: Robust Sparse Hashing (RSH). Our approach is inspired by the success of dictionary learning for sparse coding; the key innovation is to use learned sparse codes as hashcodes for speeding up NN. But sparse coding suffers from a major drawback: when data are noisy or uncertain,...

Object recognition entails extracting information about which object class(es) are present in an image. In order to enhance the performance of object recognition, reducing the redundancy in the data is absolutely essential. Prior literature [1, 2] introduced local and global self-similarity features to highlight the areas in an image which are usef...

Object classification is a widely researched area in the field of computer vision. Lately there has been a lot of attention to appearance based models for representing objects. The most important feature of classifying objects such as pedestrians, vehicles, etc. in traffic scenes is that we have motion information available to us. The motion inform...

One of the most important tasks for mobile robots is to sense their environment. Further tasks might include the recognition of objects in the surrounding environment. Three dimensional range finders have become the sensors of choice for mapping the environment of a robot. Recognizing objects in point clouds provided by such sensors is a difficult...

Action classification is an important component of human-computer interaction. Trajectory classification is an effective way of performing action recognition with significant success reported in the literature. We compare two different representation schemes, raw multivariate time-series data and the covariance descriptors of the trajectories, and...

Clinical studies confirm that mental illnesses such as autism, Obsessive Compulsive Disorder (OCD), etc. show behavioral abnormalities even at very young ages; the early diagnosis of which can help steer effective treatments. Most often, the behavior of such at-risk children deviate in very subtle ways from that of a normal child; correct diagnosis...

In developmental disorders such as autism and schizophrenia, observing behavioral precursors in very early childhood can allow for early intervention and can improve patient outcomes. While such precursors open the possibility of broad and large-scale screening, until now they have been identified only through experts' painstaking examinations and...

Sparse models have proven to be extremely successful in image processing and computer vision, and most efforts have been focused on sparse representation of vectors. The success of sparse modeling and the popularity of region covariances have inspired the development of sparse coding approaches for positive definite matrices. While in earlier work...

A robot that can drive autonomously, actively seeking more information about the environment as it attempts to infer it, has significant value in many application areas. Range scanners and depth sensors are one of the most popular sensors used in mobile robotics to accomplish several higher level tasks such as local planning, obstacle avoidance, an...

Covariance matrices of multivariate data capture feature correlations compactly, and being very robust to noise, they have been used extensively as feature descriptors in many areas in computer vision, like, people appearance tracking, DTI imaging, face recognition, etc. Since these matrices do not adhere to the Euclidean geometry, clustering algor...

Background subtraction is a fundamental task in many computer vision applications, such as robotics and automated surveillance systems. The performance of high-level visions tasks such as object detection and tracking is dependent on effective foreground detection techniques. In this paper, we propose a novel background modeling algorithm that repr...

Today, in the academic, corporate and health care world video streaming is widely used to deliver presentations, lectures and to perform remote diagnosis. These videos contain a variety of information presented in various media. For example, a lecture video consists of information presented on assorted media such as a computer and a white board. Th...

In this work we present a moving target seg- mentation technique and apply it to a vision-based robot- following problem. The capability to do autonomous multi-robot following is useful for many robot-team applications; however, the problem becomes very challenging when the robots can carry only a small camera or when they exhibit unpredictable mot...

Approximate Nearest Neighbors (ANN) in high dimensional vector spaces is a fundamental, yet challenging problem in many areas of computer science, including computer vision, data mining and robotics. In this work, we investigate this problem from the perspective of compressive sensing, especially the dictionary learning aspect. High dimensional fea...

A system for autonomous object tracking with static camera arrangements. Each camera arrangement may minimally have a pan-tilt-zoom camera and a range or depth sensor. Imaging may provide coordinates and depth information of a tracked object. Measurements of an image centroid position and width may be obtained with processing. Maintaining an image...

Sparse representation of signals has been the focus of much research in the recent years. A vast majority of existing algorithms deal with vectors, and higher–order data like images are usually vectorized before processing. However, the structure of the data may be lost in the process, leading to poor representation and overall performance degradat...

The objective of object recognition algorithms in computer vision is to quantify the presence or absence of a certain class of objects, for e.g.: bicycles, cars, people, etc. which is highly useful in traffic estimation applications. Sparse signal models and dictionary learning techniques can be utilized to not only classify images as belonging to...

This paper describes a technique for the estimation of the translational and rotational velocities of a miniature helicopter using the video signals from a single onboard camera. For every two consecutive frames from the camera, point correspondences are identified and Epipolar Geometry based algorithms are used to find the likely estimates of the...

Physical constraints that underly the formation of periodic motions can be effectively used to accurately reconstruct the periodic motion from even single camera views. As shown in our earlier work, this reduces to a problem of geometric inference. In this paper, we focus on periodic motions exhibited by humans, which are generally not perfectly pe...

Autonomous estimation of the altitude of an Unmanned Aerial Vehicle (UAV) is extremely important when dealing with flight maneuvers like landing, steady flight, etc. Vision based techniques for solving this problem have been underutilized. In this paper, we propose a new algorithm to estimate the altitude of a UAV from top-down aerial images taken...

In this paper we extend distance metric learning to a new class of descriptors known as region covariance descriptors. Region covariances are becoming increasingly popular as features for object detection and classification over the past few years. Given a set of pairwise constraints by the user, we want to perform semi-supervised clustering of the...

Cameras are becoming a common tool for automated vision purposes due to their low cost. In an era of growing security concerns, camera surveillance systems have become not only important but also necessary. Algorithms for several tasks such as detecting abandoned objects and tracking people have already been successfully developed. While tracking p...

Accurate localization of landmarks in the vicinity of a robot is a first step towards solving the SLAM problem. In this work, we propose algorithms to accurately estimate the 3D location of the landmarks from the robot only from a single image taken from its on board camera. Our approach differs from previous efforts in this domain in that it first...

A computer-readable medium having computer-executable instructions for performing a method. The method includes determining the transformation of an origin of an imaging device positioned in a vehicle and implementing exponentially stabilizing control laws based on the determined transformation and a distance to an imaged target. The method also in...

A method to dynamically stabilize a target image formed on an image plane of an imaging device located in a moving vehicle. The method includes setting an origin in the image plane of the imaging device at an intersection of a first axis, a second axis and a third axis, imaging a target so that an image centroid of the target image is at the origin...

A framework for robust foreground detection that works under difficult conditions such as dynamic background and moderately moving camera is presented in this paper. The proposed method includes two main components: coarse scene representation as the union of pixel layers, and foreground detection in video by propagating these layers using a maximu...

In this work, we propose a framework for foreground representation in video and illustrate it with a multi-camera people matching application. We first decompose the video into foreground and background. A low-level coarse segmentation of the foreground is then used to generate a simple graph representation. A vertex in the graph represents the “ap...

In this work, we propose a framework for foreground representation in video and illustrate it with a multi-camera people matching application. We first decompose the video into foreground and background. A low-level coarse segmentation of the foreground is then used to generate a simple graph representation. A vertex in the graph represents the "ap...

Thermal imaging is rightfully a real-world technology proven to bring confidence to daytime, nighttime and all weather security surveillance. Automatic image processing intrusion detection algorithms are also a real world technology proven to bring confidence to system surveillance security solutions. Together, day, night and all weather video imag...

Thermal imaging is rightfully a real-world technology proven to bring confidence to daytime, night-time and all weather security surveillance. Automatic image processing intrusion detection algorithms are also a real world technology proven to bring confidence to system surveillance security solutions. Together, day, night and all weather video ima...

The current security infrastructure can be summarized as follows: (1) Security systems act locally and do not cooperate in an effective manner, (2) Very valuable assets are protected inadequately by antiquated technology systems and (3) Security systems rely on intensive human concentration to detect and assess threats. In this paper we present DET...

We examine the state of the security industry and market and underline the role that it plays in the R&D efforts. We also present a snapshot of the current state-of-the-art in indoor and outdoor surveillance systems for commercial applications. Then, we move on and describe in detail a prototype indoor surveillance system that we recently developed...

Research in the surveillance domain was confined for years in the military domain. Recently, as military spending for this kind of research was reduced and the technology matured, the attention of the research and development community turned to commercial applications of surveillance. In this paper we describe a state-of-the-art monitoring system...

We undertook a study to determine if the automatic detection and counting of vehicle occupants is feasible. In the present paper, we report our findings regarding the appropriate sensor phenomenology and arrangement for the task. We propose a novel system based on fusion of near-infrared imaging signals and demonstrate its adequacy with theoretical...

Wehave developed a sensor based approachto collision avoidance, the virtual bumper which addresses the safety of highwayvehicles, particularly trucks. The virtual bumper is a 2-dimensional control strategy that provides both steering and throttle#braking control so that the vehicle can maneuver to avoid collisions in a dynamically changing environm...

In order to reduce the number of road departure accidents caused by fatigue and driver inattention, we are investigating intervention strategies during critical situations, part of a human centered approach to lateral vehicle control. Alarms and warning devices are for the most part ineffective since their effects on a fatigued driver are only shor...

Presents a methodology which allows an autonomous agent i.e., a mobile robot, to learn and build maps of its operating environment by relying only on its range sensors. The maps, described with respect to the robot's inertial frame, are developed in real time by correlating robot position and sensory data. This latter feature characterizes part of...

While previous work in automated process planning established plan ordering on an empirical basis alone, we derive our process plans based on the Holding-Under-Uncertainty Principle. We will introduce the principle, and we will describe the operational requirements needed to make this principle implementable in practice. The principle takes into ac...

A methodology is presented whereby a neural network is used to learn the inverse kinematic relationship for a robot arm. A two-link, two-degree-of-freedom planar robot arm is simulated, and an accompanying neural network which solves the inverse kinematic problem is presented. The method is based on Kohonen's self-organizing mapping algorithm using...

This paper is concerned with solution by the boundary element method (BEM) of a certain class of inverse linear elastic problems using the spatial regularization method. More specifically, the problem of calculating the boundary and internal conditions on a deformed specimen given approximate information on the displacements at discrete ‘sensor loc...

Computer vision applications that work with videos of-ten require that the foreground, region of interest, be clearly segmented from the un-interesting background. To address this problem, we present a general framework for scene modelling and robust foreground detection that works un-der difficult conditions such as moving camera and dynamic backg...

Thesis (Ph. D.)--University of Minnesota, 1995. Includes bibliographical references.