Gregor Miller

OpenVL: Abstracting Vision Tasks Using a Segment-Based Language Model

Computer vision is a complex field which can be challenging for those outside the community to ap... more Computer vision is a complex field which can be challenging for those outside the community to apply in the real world. In this paper we show one method to provide access to sophisticated computer vision methods to general developers, hobbyists or researchers outside the field. Our contribution is an abstraction utilising fundamental vision operations based on a single unit, the segment, can be used to describe images, local image conditions and between-image conditions. We illustrate how a descriptive language model can be built on the segment to provide an intuitive mental model of computer vision to mainstream developers. We demonstrate how we can map a description of the task composed of the segment-based language into the space of algorithms, to choose an appropriate method to solve the problem. We use the problems of segmentation, correspondence and image registration to show how end-to-end problems may be constructed using our novel metaphor.

Download

Video Navigation using a Personal Viewing History

by Gregor Miller and Matthew Fong

We describe a new video interface based on a recorded personal navigation history which provides ... more We describe a new video interface based on a recorded personal navigation history which provides simple mechanisms to quickly find and watch previously viewed intervals, highlight segments of video the user found interesting and support other video tasks such as crowd-sourced video popularity measures and consumer-level video editing. Our novel history interface lets users find previously viewed intervals more quickly and provides a more enjoyable video navigation experience, as demonstrated by the study we performed. The user study tasked participants with viewing a pre-defined history of a subset of the video and answering questions about the video content: 83.9% of questions (average) were answered correctly using the personal navigation history, while 65.5% were answered using the state-of-art method; they took significantly less time to answer a question using our method. The full video navigation interface received an 82% average QUIS rating. The results show that our history interface can be an effective part of video players and browsers.

Download

Transforming Cluster-Based Segmentation for Use in OpenVL by Mainstream Developers

ABSTRACT The majority of vision research focusses on advancing technical methods for image analys... more ABSTRACT The majority of vision research focusses on advancing technical methods for image analysis, with a coupled increase in complexity and sophistication. The problem of providing access to these sophisticated techniques is largely ignored, leading to a lack of application by mainstream applications. We present a feature-based clustering segmentation algorithm with novel modifications to fit a developer-centred abstraction. This abstraction acts as an interface which accepts a description of segmentation in terms of properties (colour, intensity, texture, etc.), constraints (size, quantity) and priorities (biasing a segmentation). This paper discusses the modifications needed to fit the algorithm into the abstraction, which conditions of the abstraction it supports, and results of the various conditions demonstrating the coverage of the segmentation problem space. The algorithm modification process is discussed generally to help other researchers mould their algorithms to similar abstractions.

Interactive free-viewpoint video

This paper introduces a representation for multiple view video to support high-quality interactiv... more This paper introduces a representation for multiple view video to support high-quality interactive free-viewpoint rendering of moving people. Multiple wide baseline views are integrated into a view-dependent representation based on pair wise refinement of the visual-hull. An exact viewdependent visual-hull (VDVH) algorithm is presented to compute an initial approximation of the scene geometry. Refinement of the VDVH surface is then performed using photo-consistency and stereo. Interactive rendering with user control of viewpoint is achieved by front-to-back rendering of the refined surfaces with view-dependent texture. Results demonstrate that this representation achieves high-quality rendering of moving people from wide-baseline views without the visual-artefacts associated with previous visual-hull and photo-hull approaches.

Download

Transforming Cluster-Based Segmentation for Use in OpenVL by Mainstream Developers

Lecture Notes in Computer Science, 2013

ABSTRACT The majority of vision research focusses on advancing technical methods for image analys... more ABSTRACT The majority of vision research focusses on advancing technical methods for image analysis, with a coupled increase in complexity and sophistication. The problem of providing access to these sophisticated techniques is largely ignored, leading to a lack of application by mainstream applications. We present a feature-based clustering segmentation algorithm with novel modifications to fit a developer-centred abstraction. This abstraction acts as an interface which accepts a description of segmentation in terms of properties (colour, intensity, texture, etc.), constraints (size, quantity) and priorities (biasing a segmentation). This paper discusses the modifications needed to fit the algorithm into the abstraction, which conditions of the abstraction it supports, and results of the various conditions demonstrating the coverage of the segmentation problem space. The algorithm modification process is discussed generally to help other researchers mould their algorithms to similar abstractions.

OpenVL: A task-based abstraction for developer-friendly computer vision

2013 IEEE Workshop on Applications of Computer Vision (WACV), 2013

Research into computer vision techniques has far outpaced the development of interfaces (such as ... more Research into computer vision techniques has far outpaced the development of interfaces (such as APIs) to support the techniques' accessibility, especially to developers who are not experts in the field. We present a new description-based interface designed to be mainstreamdeveloper-friendly while retaining sufficient power and flexibility to solve a wide variety of computer vision problems. The interface presents vision at the task level (hiding algorithmic detail) and uses a task-based description derived from definitions of vision problems. We show that after interpretation, the description can be used to invoke an appropriate method to provide the developer's requested result. Our implementation interprets the description and invokes various vision methods with automatically derived parameters, which we demonstrate on a range of tasks.

Download

VisionGL

ACM SIGGRAPH 2014 Posters on - SIGGRAPH '14, 2014

An Abstraction for Correspondence Search Using Task-Based Controls

Lecture Notes in Computer Science, 2015

MiniDiver: A Novel Mobile Media Playback Interface for Rich Video Content on an iPhoneTM

Lecture Notes in Computer Science, 2009

We describe our new mobile media content browser called a MiniDiver. MiniDiving considers media b... more We describe our new mobile media content browser called a MiniDiver. MiniDiving considers media browsing as a personal experience that is viewed, personalized, saved, shared and annotated. When placed on a mobile platform, such as the iPhone TM , consideration of the particular interface elements lead to new ways to experience media content. The MiniDiver interface elements currently supports multicamera selection, video hyperlinks, history mechanisms and semantic and episodic video search. We compare performance of the MiniDiver on different media streams to illustrate its feasibility.

Download

Task-based control of articulated human pose detection for OpenVL

IEEE Winter Conference on Applications of Computer Vision, 2014

ABSTRACT Human pose detection is the foundation for many applications, particularly those using g... more ABSTRACT Human pose detection is the foundation for many applications, particularly those using gestures as part of a natural user interface. We introduce a novel task-based control method for human pose detection, encoding specialist knowledge in a descriptive abstraction for application by non-experts, such as developers, artists and students. The abstraction hides the details of a set of algorithms which specialise either in different estimations of pose (e.g. articulated, body part) or under different conditions (e.g. occlusion, clutter). Users describe the conditions of their problem, which is used to select the most suitable algorithm (and automatically set up the parameters). The task-based control is evaluated with images described using the abstraction. Expected outcomes are compared to results and demonstrate that describing the conditions is sufficient to allow the abstraction to produce the required result.

Moving Target Selection in 2D Graphical User Interfaces

by Gregor Miller and Michael Ilich

Lecture Notes in Computer Science, 2011

Target selection is a fundamental aspect of interaction and is particularly challenging when targ... more Target selection is a fundamental aspect of interaction and is particularly challenging when targets are moving. We address this problem by introducing a novel selection technique we call Hold which temporarily pauses the content while selection is in progress to provide a static target. By studying users, we evaluate our method against two others for acquiring moving targets in one and two dimensions with variations in target size and velocity. Results demonstrate that Hold outperforms traditional approaches in 2D for small or fast-moving targets. Additionally, we investigate a new model to describe acquisition of 2D moving targets based on Fitts' Law. We validate our novel 2D model for moving target selection empirically. This model has application in the development of acquisition techniques for moving targets in 2D encountered in domains such as hyperlinked video and video games.

Download

Video Navigation with a Personal Viewing History

Lecture Notes in Computer Science, 2013

We describe a new video interface based on a recorded personal navigation history which provides ... more We describe a new video interface based on a recorded personal navigation history which provides simple mechanisms to quickly find and watch previously viewed intervals, highlight segments of video the user found interesting and support other video tasks such as crowd-sourced video popularity measures and consumer-level video editing. Our novel history interface lets users find previously viewed intervals more quickly and provides a more enjoyable video navigation experience, as demonstrated by the study we performed. The user study tasked participants with viewing a pre-defined history of a subset of the video and answering questions about the video content: 83.9% of questions (average) were answered correctly using the personal navigation history, while 65.5% were answered using the state-of-art method; they took significantly less time to answer a question using our method. The full video navigation interface received an 82% average QUIS rating. The results show that our history interface can be an effective part of video players and browsers.

Download

Visualization of personal history for video navigation

by Gregor Miller and Matthew Fong

Proceedings of the 32nd annual ACM conference on Human factors in computing systems - CHI '14, 2014

. Our prototype history-based interface called the Video History System (VHS) aids navigation thr... more . Our prototype history-based interface called the Video History System (VHS) aids navigation through the management of a user's personal viewing history. Playback of video is controlled with familiar tools such as play/pause, seek and filmstrip (left) -the VHS records each part of the video viewed by the user. The history is then visualized in one of two ways: as Video Tiles (centre) or as a Video Timeline (right). 1

Download

Uniform access to the cameraverse

Proceedings of the Fourth ACM/IEEE International Conference on Distributed Smart Cameras - ICDSC '10, 2010

Volumetric stereo with silhouette and feature constraints

Procedings of the British Machine Vision Conference 2006, 2006

This paper presents a novel volumetric reconstruction technique that combines shape-from-silhouet... more This paper presents a novel volumetric reconstruction technique that combines shape-from-silhouette with stereo photo-consistency in a global optimisation that enforces feature constraints across multiple views. Human shape reconstruction is considered where extended regions of uniform appearance, complex self-occlusions and sparse feature cues represent a challenging problem for conventional reconstruction techniques. A unified approach is introduced to first reconstruct the occluding contours and left-right consistent edge contours in a scene and then incorporate these contour constraints in a global surface optimisation using graph-cuts. The proposed technique maximises photo-consistency on the surface, while satisfying silhouette constraints to provide shape in the presence of uniform surface appearance and edge feature constraints to align key image features across views.

Download

Developer-friendly segmentation using OpenVL, a high-level task-based abstraction

2013 1st IEEE Workshop on User-Centered Computer Vision (UCCV), 2013

ABSTRACT Research into computer vision techniques has far out-paced the development of interfaces... more ABSTRACT Research into computer vision techniques has far out-paced the development of interfaces (such as APIs) to support the techniques&#39; accessibility, especially to developers who are not experts in the field. We present a new interface, specifically for segmentation methods, designed to be application-deveLoper-friendly while retaining sufficient power and flexibility to solve a wide variety of problems. The interface presents segmentation at a higher level (above algorithms) and uses a task-based description derived from definitions of low-level segmentation. We show that through interpretation, the description can be used to invoke an appropriate method to provide the developer&#39;s requested result. Our proof-of-concept implementation interprets the model description and invokes one of six segmentation methods with automatically derived parameters, which we demonstrate on a range of segmentation tasks. We also discuss how the concepts presented for segmentation may be extended to other computer vision problems.

An End-to-End Framework for Multi-view Video Content: Creating Multiple-Perspective Hypervideo to View on Mobile Platforms

by Michael Ilich, Gregor Miller, and Kelvie Wong

Lecture Notes in Computer Science, 2011

We present a work-in-progress novel framework for the creation, delivery and viewing of multi-vie... more We present a work-in-progress novel framework for the creation, delivery and viewing of multi-view hypermedia intended for mobile platforms. We utilize abstractions over creation and delivery of content and a unified language scheme (through XML) for communication between components. The delivery mechanism incorporates server-side processing to allow inclusion of additional features such as computer vision-based analysis or visual effects. Multi-view video is streamed live to mobile devices which offer several mechanisms for viewing hypermedia and perspective selection.

Download

Using temporal video annotation as a navigational aid for video browsing

Adjunct proceedings of the 23nd annual ACM symposium on User interface software and technology - UIST '10, 2010

Video is a complex information space that requires advanced navigational aids for effective brows... more Video is a complex information space that requires advanced navigational aids for effective browsing. The increasing number of temporal video annotations offers new opportunities to provide video navigation according to a user&amp;amp;amp;#x27;s needs. We present a novel video browsing interface called TAV (Temporal Annotation Viewing) that provides the user with a visual overview of temporal video annotations. TAV enables the

Developer-centred interface design for computer vision

2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), 2011

Abstract The rise in popularity of products and interfaces which use computer vision has not been... more

OpenVL

ACM SIGGRAPH 2014 Talks on - SIGGRAPH '14, 2014

Uploads

Papers by Gregor Miller

Log In