About

John Aloimonos is a professor in the Department of Computer Science at the University of Maryland, affiliated with UMIACS and Cfar. He earned his Ph.D. from the University of Rochester in 1987. His research areas include AI and Robotics, Computer Vision and Machine Perception, Graphics Visualization, and Virtual Reality and Augmented Reality. His interests focus on artificial intelligence, vision, robotics, learning, and neuro-informatics. Throughout his career, he has been recognized with honors such as the NSF National Young Investigator award in 1990. He has advised numerous Ph.D. students and has been highlighted in various media and research rankings, notably being listed among the top scientists by Guide2Research in 2021. His work has contributed significantly to the fields of computer vision and robotics, and he is actively involved in advancing research in these areas.

Research topics

• Computer science
• Artificial intelligence
• Computer vision
• Mathematics
• Algorithm

Selected publications

• Automated rhinoceros detection in satellite imagery using deep learning

  Scientific Reports · 2025-11-10 · 4 citations

  articleOpen accessSenior author

  Rhinoceroses face severe threats from poaching, habitat fragmentation, and ongoing habitat degradation. Monitoring rhinoceros across the vast, often inaccessible landscapes they inhabit is challenging. In this study, we assess the feasibility of detecting white rhinoceroses using very high-resolution (33-36 cm) satellite imagery acquired over the world's largest private rhinoceros reserve in South Africa using a YOLO-based object detection model (YOLOv12x). We test whether synthetic imagery enhances model performance, whether rhinoceroses can be reliably distinguished from elephants in satellite imagery, and whether synthetically generated rhinoceroses are visually distinguishable from real ones by human annotators. We achieve an average precision (AP) of 0.65 in detection accuracy with synthetic augmentation yielding a marginal improvement. This study provides a demonstration of monitoring rhinos using this approach and introduces an open-access dataset to support the development and testing of new models. The aim is to facilitate effective monitoring of rhinos across the vast landscapes they inhabit. Developing new detection techniques can strengthen conservation and recovery initiatives, including translocations, assessment of breeding program success, and evaluation of anti-poaching efforts.

  PublisherOA PDFDOI

• Editorial: Brain-inspired Hyperdimensional Computing: Algorithms, models, and architectures

  Frontiers in Neuroscience · 2022-12-08 · 2 citations

  editorialOpen accessSenior author

  EDITORIAL article Front. Neurosci., 08 December 2022Sec. Neuromorphic Engineering Volume 16 - 2022 | https://doi.org/10.3389/fnins.2022.1102568

  PublisherOA PDFDOI

• Real-Time Distributed Algorithms for Visual and Battlefield Reasoning

  2006-08-01

  reportSenior author

  Information is key to the success of the next generation battlefield. There is a critical need to determine, in real-time, what the enemy is doing, and to interpret that information in the context of past related events. In this project we examined two aspects of this issue: development of a high-level task definition language for tasking a network of sensors to carry out given objectives, and interpreting recounted events so that past related scenarios could be automatically identified from a case database.

  PublisherDOI

• Determining three dimensional transformation parameters from images: Theory

  2005-03-23 · 6 citations

  articleSenior author

  We present a theory for the determination of the three dimensional transformation parameters of an object, from its images. The input to this process is the image intensity function and its temporal derivative. In particular, our results are: 1) If the structure of the transforming object in view is known, then the transformation parameters are determined from the solution of a linear system. Rigid motion is a special ease of our theory. 2)If the structure of the object in view is not known, then both the structure and transformation parameters may be computed through a hill climbing or simulated annealing algorithm.

  PublisherDOI

• Optimal Computing Of Structure From Motion Using Point Correspondences In Two Frames

  2005-08-24 · 55 citations

  articleSenior author

  One of the problems associated with any approach to the structure from motion problem using point correspondence, i.e. recovering the structure of a moving object from its successive images, is the use of least squares on dependent variables. We formulate the problem as a quadratic minimization problem with a non-linear constraint. Then we derive the condition for i,he solution to be optimal under the assumption of Gaussian noise in the input, in the Maximum Likelihood Principle sense. This constraint minimization reduces to the solution of a nonlinear system which in the presence of modest noise is easy to approximate. We present two efficient ways to approximate it and we discuss some inherent limitations of the structure from motion problem when two frames are used that should be taken into account in robotics applications that involve dynamic imagery. In addition, our formulation introduces a framework in which previous works on the subject become special cases.

  PublisherDOI

• Optimal motion estimation

  2003-01-07 · 42 citations

  articleSenior author

  The problem of using feature correspondences to recover the structure and 3D motion of a moving object from its successive images is analyzed. They formulate the problem as a quadratic minimization problem with a nonlinear constraint. Then they derive the condition for the solution to be optimal under the assumption of Gaussian noise in the input, in the maximum-likelihood-principle sense. The authors present two efficient ways to approximate it and discuss some inherent limitations of the structure-from-motion problem when two frames are used that should be taken into account in robotics applications that involve dynamic imagery. Finally, it is shown that some of the difficulties inherent in the two-frame approach disappear when redundancy in the data is introduced. This is concluded from experiments using a structure-from-motion algorithm that is based on multiple frames and uses only the rigidity assumption.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

  PublisherDOI

• Purposive and qualitative active vision

  2002-12-04 · 290 citations

  article1st authorCorresponding

  The traditional view of the problem of computer vision as a recovery problem is questioned, and the paradigm of purposive-qualitative vision is offered as an alternative. This paradigm considers vision as a general recognition problem (recognition of objects, patterns or situations). To demonstrate the usefulness of the framework, the design of the Medusa of CVL is described. It is noted that this machine can perform complex visual tasks without reconstructing the world. If it is provided with intentions, knowledge of the environment, and planning capabilities, it can perform highly sophisticated navigational tasks. It is explained why the traditional structure from motion problem cannot be solved in some cases and why there is reason to be pessimistic about the optimal performance of a structure from motion module. New directions for future research on this problem in the recovery paradigm, e.g., research on stability or robustness, are suggested.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

  PublisherDOI

• Resolving the intractability of the 'warehouseman's problem' using temporary storage space and other constraints

  2002-12-04 · 2 citations

  articleSenior author

  The coordination problem of rearranging rectangular blocks enclosed in a rectangular room, or the warehouseman's problem, which is known to be PSPACE-hard, is treated. The approach used is to find constraints that, when imposed on the general instance of a provably hard problem, lead to guaranteed polynomial-time solutions. The notion of reserving a portion of the available space for holding the blocks temporarily during the rearrangement process is introduced. This use of temporary storage space (TSS) helps to formalize the intuitive idea of available space, and puts restrictions on the actual distribution of free space. The TSS idea provides a way of parameterizing the control of the environment (using the area of the TSS) to observe its effect on the solution of the motion coordination problem. The other constraints are then used to lower the area of the TSS, since it is an overhead. The algorithms are given for square blocks in a square configuration, but can be easily modified to solve the more general problem with rectangular blocks in a rectangular configuration.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

  PublisherDOI

• Approximate constrained motion planning

  2002-12-04 · 8 citations

  articleSenior author

  The problem of finding a collision-free path connecting two points (start and goal) in the presence of obstacles, with constraints on the curvature of the path, is examined. This problem of curvature-constrained motion planning arises when, for example, a vehicle with constraints on its steering mechanism needs to be maneuvered through obstacles. Though no lower bound on the difficulty of the problem in 2-D is known, exact algorithms given to date for the reachability questions are exponential. It is shown that a variation of the problem is NP-hard. Notably, however, the same variation to polynomially solvable motion planning problems does not make them intractable. In addition, it is proven that epsilon -approximations to this problem cannot exist unless the underlying decision problem is polynomially solvable. An algorithm which is expected to find a desired path, when one exists, with a required probability is presented. Results indicate that a variable-size discretization is necessary for the task, linking the required probability to the size of the discretization locally.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

  PublisherDOI

• Purposive and qualitative active vision

  2002-12-09 · 13 citations

  article1st authorCorresponding

  Qualitative vision, which in the past has been wrongly called inexact, makes sense when it is coupled with purposive vision, which formulates questions for which qualitative solutions are possible. To demonstrate the usefulness of this approach, the author considers visual motion (or navigation) problems, and assumes that the observer is active. He describes the preliminary design of Medusa, a purposive and qualitative visual motion machine that can robustly solve many navigational problems without reconstructing the scene.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

  PublisherDOI

Frequent coauthors

• Minas E. Spetsakis

  York University

  5 shared

• David Shulman

  5 shared

• Anup Basu

  University of Alberta

  5 shared

• Amit Bandyopadhyay

  Washington State University

  3 shared

• Paul B. Chou

  University Health Network

  3 shared

• Chris Brown

  Virginia Tech

  2 shared

• J.-Y. Herve

  HelpAge International

  2 shared

• Dan Moldovan

  Arizona State University

  2 shared

Labs

• CLIP LabPI

Awards & honors

• NSF National Young Investigator (1990)
• Qualcomm Innovation Fellowship (2011)
• Adam Porter: CMNS Board of Visitors Creative Educator Award…