320 likes | 451 Views
The AutoArch initiative, led by researchers at the University of Bristol, automates the generation of 3D models and the archiving of wildlife film footage. Utilizing simple setups and efficient algorithms, it transforms physical objects into 3D models using minimal equipment. Innovations include extracting motions from animations and managing video segmentation for richer metadata generation. The project aims to enhance accessibility, streamline archiving processes, and improve visual representations of wildlife content, fostering easier searching and summarization.
E N D
Computer Vision and Media Group:Selected Previous Work David Gibson, Neill Campbell Colin Dalton Department of Computer Science University of Bristol AutoArch Overview
Duck: The AutomaticGeneration of 3D Models • Generating 3D computer models is difficult • Put object on turntable • Take 8 pictures of it from different angles • Crank the handle… • No skilled user or expensive equipment • Make avatars by spinning person on chair AutoArch Overview
Cog and Stepper • Automatically inject ‘life’ into computer animations • 3D swathe through 4D space time • Where space is 3D computer model • Or just to make things look strange! AutoArch Overview
Casablanca: Motion Ripper • Computer animation driven by film • Animator labels a small number of points • System then tracks these points over all frames • Motions are extracted and used to drive animation AutoArch Overview
Laughing ManMotion Ripper Part 2 • Automatic video creation • Points are marked and tracked • System learns the motions • System generates new motions which are different but ‘correct’ • Forever! AutoArch Overview
AutoArch: The Automatic Archiving of Wildlife Film Footage David Gibson, Neill Campbell David Tweed, Sarah Porter Department of Computer Science University of Bristol AutoArch Overview
Motivation • BBC Natural History Unit • Manual archiving/meta data generation • Reuse problematic • Inefficient/time consuming • Expensive • Limited access • Obvious need to automate AutoArch Overview
Objectives • Generate efficient visual representations • Video segmentation • Visual browsing/summarisation • Visual searching • Generate as much meta data automatically • Camera motions/effects • Scene structure • Scene content AutoArch Overview
Visualisation and Searching Visualisation based algorithms Shot Segmentation Visual Summarisation Motion Analysis Colour/Texture Analysis Meta data extraction algorithms Catalogue Entry System Overview AutoArch Overview
Video Segmentation AutoArch Overview
Visual Summarisation • Key frame extraction AutoArch Overview
Entire shot Visual Summarisation Tree Level of detail AutoArch Overview
Visual Searching • Layered 2D representation of high D clip space AutoArch Overview
Motion Analysis using point tracking • Camera Motion Estimation • Event/Area of Interest Detection • Gait Analysis • Foreground/Background Separation • Combine with Colour and Texture for Classification • See cheetah track avi AutoArch Overview
Camera Pan BCD0111.09_0085.epslines = 47, curls = 98, shorts = 5long lines = 47, mode = 95.00, mean = 95.21, std = 4.15zoom centre = (603.01, 63.65), val = -0.2356zoom residual per line = 22.92zoom residual #2 per line = 28.92Average line vector: 109.94 -8.27pan/tilt angle: 94.30, vector: (109.94 -8.27)pan/tilt residual per line = 21.67pan/tilt residual #2 per line = 33.38percentage of lines within 5% of mode: 89.36 AutoArch Overview
Camera Zoom BCD0113.15_0067.epslines = 142, curls = 1, shorts = 7long lines = 134, mode = 340.00, mean = 227.24, std = 128.76zoom centre = (182.97, 55.52), val = 0.2063zoom residual per line = 4.86zoom residual #2 per line = 6.90Average line vector: -3.81 17.28pan/tilt angle: 347.57, vector: (-3.81 17.28)pan/tilt residual per line = 13.85pan/tilt residual #2 per line = 16.13percentage of lines within 5% of mode: 17.16 AutoArch Overview
Tracking Failure This could be an interesting event in its self: flocking, herding, close up of lots of activity, shot grouping, etc. AutoArch Overview
Event/Area of InterestDetection AutoArch Overview
Frequency Analysis:Gait Detection After trajectory segmentation FFT AutoArch Overview
Foreground model Feature space #2 Background model Feature space #1 Foreground/BackgroundExtraction Which pixels are foreground? AutoArch Overview
Animal Identification Give models a name: = zebra = cheetah = lion = elephant AutoArch Overview
Some Problems • Noise in images • Noise in measurements • Camouflage • Occlusion • Answer: Need higher level models • See next few slides AutoArch Overview
Model Based Tracking AutoArch Overview
Lion Tracking • Synchronise horse model with lion points • Move and deform horse model to lion points • See avi • To do: Improve spatial deformation, especially for legs, using colour and texture AutoArch Overview
Multiple Object Tracking AutoArch Overview
Conclusions • Visualisation is very powerful • Combined with text is even better! • Assists searching and communication • Lots of meta data can be auto generated • Assists archiving • Help to prioritise manual archiving • Can be applied to any visual media AutoArch Overview