You are on page 1of 2

3-D Motion Detection from a sequence of Image Frames

Abstract:

The most prominent area where the potential of neural networks under study is

that of engineering applications, such as image and speech recognition. In this paper, the

design of neural networks for sequential domains is another interesting direction. This

paper describes a 3d motion detection system. This system consists of 3 stages, The

rough motion detection stage, the moving object extraction stage and the object

identification and 3d motion detection stage. Five neural networks the correlation

network, the rough motion detection network, the edge enhancement network, the

background remover, and the Normalization network, are designed for the

implementation of these three stages.

Software Used:

Front End: C# .Net

Modules 3-D Motion Detection from a Sequence of Image Frames:

1. Background:

Basic understanding of AI approaches e.g. neural networks, support vector


machines, nearest neighbour classifiers. Image descriptive and transform methods
as wavelets, edge extraction, image statistics, histograms. C++/C# experience as
in this article you will find how to invoke C++ dll methods from within C#
application.

2. Using the application:

You need to use unknown category along with the others you'd like to
classify to. As otherwise AI classifier would be able to identify only e.g. animals,
flowers, landscapes, sunsets with every image you give. But in real world there
are other types of images that do not fall into either of the above presented
categories, so you will need to meddle with AI classification thresholds which is
rather cumbersome and awkward. But having additional unknown category AI
classifier the results of the image identification will be as either one of the known
image categories or simply unknown image type the computer can not identify
using its petty knowledge.

3. Methodology

Due to the competing interests with the former organizations and the
current one I work for, I will not be able to describe in minute details the
methodology and feature extraction methods. I would rather present the general
trend and categories of the features used for description of images. As searching
over internet for corresponding feature computation will reveal all the necessary
papers with particular formulae.

ALIP features
Source code tips
4. ALIP results

I deliberatly selected the most simple image features, that do not look like
a features at all, due to competing intrests with the former funding organization
System7. I used just image itself, downscaled it to 16x16 and converted to YCbCr
colorspace. Obviously that is not the proper feature to start with, as others would
significantly outperform it in discrimination ability. However, though I anticipated
the classification would be completely incorrect, to my great suprise it performed
pretty well, producing quite precise results.

Animals category
Flowers category
Landscapes category
Sunsets category

You might also like