| |
Having an innovative idea such as Dream Recorder is a first step. But bringing it to life requires a lot of technology and data processing. The osX framework offers the ideal technology more than any other platform. We brought the know-how and inventiveness. Dream Recorder has been designed and realised by professionals of the field of scientific instrumentation.
 |
OsX embeded technologies
|
Interfacing a computer with humans requires a lot of technology. The Apple know-how in that field is still unbeaten. OsX was the ideal environment for developing such a project. For developers like us, Core Audio and Core Image are outstanding toolkits taking care of most data operations in an efficient manner. Just invent and forget about optimization... Indeed, keeping the processing power low, thus avoiding fan noise, while implementing complex real-time image and audio processing is a challenge.
 |
Night vision processing
|
Dream Recorder uses an image processing algorithm that stems from professional astronomers, using large CCD for deep star fields observation. A CCD sensor yields intrisic perturbations called the dark current and read-out noise. This makes the images looking grainy in dark environments.
On successive iSight images, the noise pixels will be different as they are random. On the other hand, real information will be present each time. Dream Recorder analyses the correlation between pixel information, image after image, and filters the noise by calculating the statistical variance. Moreover, the image motifs are spread above many pixels. Here again, neighbor pixels will keep the same contrast, giving an additional noise rejection criteria.
Dream Recorder typically takes 60 dark images and produces a rendered 3D model used for motion detection.
This methods works only on static subjects, which is of course the case of a sleeping person. This would not be efficient when filming moving subjects.
Dream Recorder processes about sixty images to get 3D model used for motion detection.
 |
Voice processing
|
Dream Recorder permanently analyses each sounds of the night. It recognizes them and makes the difference between a person talking and snoring.
When you tell about the dream you just had, the sound processing will automatically record your voice and log it for you, without even touching the keyboard. After some seconds of silence, Dream Recorder will switch back to survey mode.
In the firrt version of Dream Recorder, snoring was not distinguished from voices. Our users had gigabytes of snoring logged on their hard disk... Today's versions can just skip snoring. The amount of snoring is logged for statistics, and some snoring whistles can also be emmited by Dream Recorder... even if this feature is more a kind of gadget, but appreciated by some of our user's partner.
The voice processing is done through the analysis of sound spectrograms, using the Core Audio framework of osX.
This spectrogram is these of a person snoring. It shows some repeating patterns, at the rythm of the sleeper's breath.
Snoring spectrograms show repeating patterns detected by Dream Recorder.
Voice spectrograms do not show repeating patterns. Silences and ambiant noise levels are used for automatic recordings.
|
 |
 |
 |
|
Cameras
|
Dream Recorder is optimized for iSight cameras, built-in and firewire. You will get different image quality, depending on which camera you are using. The firewire iSight has a CCD sensor. It will be efficient on long range — up to 4 meters — but with images of lower quality. Built-in iSights use CMOS sensors. They will provide better images but at shorter ranges. You may use Dream Recorder with a firewire camcorder. These often come with a embedded hardware night vision system.
|
|
|
|
|
You may use any cameras with Dream Recorder to some extent. However, iSights are very good webcams compared to many others. Cheap ones will give cheap results.
One straightforward way of testing if a camera can be used with Dream Recorder is to test it with iChat. If it works in iChat, it will work with Dream Recorder as both programs use the same Quicktime framework. Some usb cameras need additional drivers to work with osX. You could test these solution providers:
• IOXWebcam X, from IOXperts, $19.95
• Macam, open source, free
among others...
|
|
Infrared Cameras
|
There are some infrared webcam on the market that give good results. They are quite normal webcams without IR filters. Indeed, most CCD sensors are very sensitive to infrared and manufacturers generally filter this part of the light spectrum with a filter. Handymen will find many sites on the web that explain how to turn cameras to infrared.
However, from our practice, you do no need to buy a special infrared camera or fudge your hardware, taking the risk of breaking it. Do the following experiment. Take a remote control with an infrared LED. Use it in front of your iSight and you will notice that the LED is seen by the camera when not with your eyes. A good source of information on how to turn a standard webcam into IR webcam can be found on wikipedia
|
|
|
|
|
Your iSights are actually quite good IR cameras, at least enough for Dream Recorder. The only thing you need is an IR source of light. You will find IR lamp almost everywhere on the web, when not at your market store down the street. We have tested Dream Recorder with several lamps as the one shown on the next image.
|
|
|
 |
|
|
This kind of lamp is generally used for heating purposes. When on, it shows a non disturbing dark red glow. Over 2 meters, you will not notice this source of heat. This gives very good results so far.
|
|
|
|
 |
|
 |
|
|
