2017 – Raspberry Pi Eye

17May 2017 by pi-eye-admin

Visual Field Construction – Heal Plot

Starting with this earlier post we have been discussing the construction of a stable visual field using techniques that use key-point matching and motion sensing. In both cases we attempt to map input from a three-dimensional scan onto an easily viewed two-dimensional surface. But any notion that we have a hi-def flat screen in our head or visual system is surely misguided. The world we live in is inherently a three dimensional space and we should be looking at how to properly represent a 3D world into a 3D data structure. Fortunately, this same problem came up in an earlier and completely different context. NASA launched satellites to study the cosmic microwave background (CMB) anisotropy (cosmic radiation in the universe) and needed software that met certain criteria for mapping radiation…

17May 2017 by pi-eye-admin

Object Detection – Haar Cascades

Object Detection, Open CV

Face detection and tracking can be done using the OpenCV Haar Cascade object detection algorithms. What is Haar Cascade? A Haar filter is a type of wavelet filter which resembles a truncated sine wave. The cascade is formed by lining up Haar filters in layers to optimize the detection of particular objects. At the 2017 Maker Faire in San Mateo, California, the Pi Eye participated in a demonstration of Haar-Cascade face detection where the face was a Beagle named "Penny". The "Find Penny" project (organized by a fifth-grader named Vian) used 43 images of the beagle and 111 images without the beagle in 28 layers of Haar-Cascade training that took nearly 24 hours to complete. [caption id="attachment_116" align="aligncenter" width="640"] The "Find Penny" demonstration at the Bay Area Maker Faire 2017[/caption]…

17May 2017 by pi-eye-admin

Visual Field Construction – Sensors

Open CV, Visual Field

In our previous post on visual field construction we discussed motion and how motion feed-forward may be used to create a stable visual field. Our body has such sensors in the head and their is no question that they play an important part in visual processing. From the Wikipedia article on the Inner Ear: "The vestibular system of the inner ear is responsible for the sensations of balance and motion. It uses the same kinds of fluids and detection cells (hair cells) as the cochlea uses, and sends information to the brain about the attitude, rotation, and linear motion of the head. The type of motion or attitude detected by a hair cell depends on its associated mechanical structures, such as the curved tube of a semicircular canal or the…

17May 2017 by pi-eye-admin

Visual Field Construction – Motion Feed Forward

Open CV, Visual Field

The first post in this series on visual field construction discussed eye motion and the problem of creating a stable visual field. A solution using photo-stitching was presented and shown to yield visually pleasing results. Stitching, however, is an after-the-fact remedy, a post-processing of visual input deriving results when the image in question might have already come and gone. This post proposes a second method of stabilization relying on "motion feed forward". When our brain decides to move our body a complex series of neuronal messages goes out to all parts, to the feet, the torso, the head and elsewhere to effect that move. It would make sense for the visual system to siphon off some of these commands and prep the visual field for an incoming adjustment, e.g. the…

17May 2017 by pi-eye-admin

Visual Field Construction – Stitching

Open CV, Visual Field

The study of visual perception has engaged philosophers and scientists for centuries if not millennia. And the problem is still not well understood, despite new results using machine learning and technologies such as convolutional deep neural networks. How photons impinging on the retina convert into visual perceptions in the mind has been the center of volumes and volumes of scholarly articles and debate. We won't solve this problem here, but I do wish to explore one area of this discussion which concerns eye movements and construction of the visual field. So much visual research starts with a simple static image (ImageNet now has over 14 million such classified images) and tries to derive a response from the image. The computer is presented with an image of a bowl of fruit…

17May 2017 by pi-eye-admin

What is Open CV?

Open CV

The OpenCV (Open Source Computer Vision Library) is a set of libraries and programs which may be used to rapidly accelerate experimentation and research in computer vision and related image and visual processing studies. The library may be installed and compiled on the Raspberry Pi in a few hours and provides a wealth of programs and subroutines to make image processing on the Pi easy. The Pi Eye Project has used OpenCV for many different functions: Image transforms and projections Displaying images on the screen Object detection (e.g. face detection) Manipulation of visual arrays And more ... The main website for OpenCV is at opencv.org and there are many tutorials and examples on the web for its use. From the OpenCV website : "OpenCV is released under a BSD license…