In "Courtrooms could host virtual crime scenes," New Scientist writes about a software called Instant Scene Modeler (iSM), which can build an interactive 3D model from a few hundred frames of a scene shot by a dual-head camera developed by MD Robotics. Users, who can be lawyers, judges, jurors or detectives, can zoom on any object in the 3D model. Other usages of this gun-shaped camera and its associated software include remote explorations of mines, or even other planets such as Mars. The software works by identifying common features in the sequence of images taken by the special camera. And it has already been used to pilot Aibo, Sony's robotic dog. Read more.
Here are the opening paragraphs of the New Scientist article.
Lawyers, judges and jurors could soon explore crime scenes in three dimensions in the courtroom, in the same way that video gamers explore virtual worlds.
Software called instant Scene Modeler (iSM) re-creates an interactive 3D model from a few hundred frames of a scene captured by a special video camera. Users can zoom in on any object in the 3D model, measure distances between objects and look at scenes from different angles.
Currently investigators try to recreate the scene of the crime in court by sifting through photos or sketches, but this approach is limited and time-consuming, explains Piotr Jasiobedzki, iSM's project manager at MDRobotics in Toronto, Canada. The software could also assist detectives during their investigations.
Here is how this works.
The system uses a gun-shaped stereo-camera that consists of two ordinary video cameras aligned at a set distance from each other. This enables the depth of the captured scene to be calculated at every point, just as a pair of eyes gauges distances. (Image credit: MD Robotics, iSM_InfoSheet (PDF format, 1 page, 1.25 MB)
The basic unit of construction in the theatre is the scene, and the amount of dramatic time that elapses during a scene is roughly equal to the length of time the scene takes to perform. To be sure, some plays cover many years, but in general these years pass “between curtains.” We’re informed that it is “seven years later,” either by a stage direction or by the dialogue. The basic unit of construction in movies is the shot, which can lengthen or shorten time more subtly, since the average shot lasts only ten or fifteen seconds. Drama has to chop out huge blocks of time between the relatively few scenes and acts; films can expand or contract time between the many hundreds of shots.
—Louis D. Gianetti (b. 1937)
And here are links to two animations from MD Robotics showing a crime scene sequence (4.2 MB) and a crime scene 3D model (4.3 MB).
The amazing thing about this software is that it automatically creates calibrated 3D models -- and believe me, this is tricky. iSM is different because it creates a virtual model of the scene that can then be explored from any angle. It does this by using a set of algorithms called SIFT (Scale Invariant Feature Transform) developed by David Lowe, computer vision expert at the University of British Columbia in Vancouver, Canada
SIFT very quickly identifies common features in sequential images, Lowe told New Scientist, allowing separate 3D images to be transformed into a virtual 3D world. The virtual world is rendered by a graphics gaming card inside an ordinary laptop or PC.
For more information about David Lowe's work, you can read one of his latest papers, published by the International Journal of Computer Vision, "Distinctive Image Features from Scale-Invariant Keypoints" (Volume 60, Number 2, November 2004, Pages 91-110). Here is a link to the abstract and here is the beginning of it.
This paper presents a method for extracting distinctive invariant features from images, which can be used to perform reliable matching between different images of an object or scene. The features are invariant to image scale and rotation, and are shown to provide robust matching across a a substantial range of affine distortion, addition of noise, change in 3D viewpoint, and change in illumination. The features are highly distinctive, in the sense that a single feature can be correctly matched with high probability against a large database of features from many images.
Finally, if you're a specialist in this field, here is a link to the full paper (PDF format, 28 pages, 501 KB).
Sources: Celeste Biever, NewScientist.com, March 10, 2005; and various websites
My passion strengthens daily to quit political turmoil, and retire into the bosom of my family, the only scene of sincere and pure happiness.
—Thomas Jefferson (1743–1826)
Related stories can be found in the following categories.
Forensics
Military Applications
Police
Software
Space
Vision and Visualization Applications.