Module-1

INTRODUCTION

What is computer vision?

The human visual system has no problem interpreting the subtle variations in translucency and shading in this photograph and correctly segmenting the object from its

background.

Some examples of computer vision algorithms and applications

Why is vision so difficult?

Some common optical illusions and what they might tell us about the visual system

Computer Vision Real-World Applications

1. Optical character recognition (OCR)
2. Machine inspection
3. Retail
4. Warehouse logistics
5. Medical imaging
6. Self-driving vehicles
7. 3D model building (photogrammetry)
8. Match move
9. Motion capture (mocap)
10. Surveillance
11. Fingerprint recognition and biometrics

Some industrial applications of computer vision

Consumer-level Applications

​

1. Stitching
2. Exposure bracketing
3. Morphing
4. 3D modelling
5. Video match move and stabilization
6. Photo-based walkthroughs
7. Face detection
8. Visual authentication

Brief History

Photometric image formation

• In modeling the image formation process, 3D geometric features in the world are projected into 2D features in an image.
• However, images are not composed of 2D features. Instead, they are made up of discrete color or intensity values.
• Where do these values come from?
• How do they relate to the lighting in the environment, surface properties and geometry, camera optics, and sensor properties?

​

Lighting

​

• Images cannot exist without light. To produce an image, the scene must be illuminated with one or more light sources.
• Light sources can generally be divided into point and area light sources.
• A point light source originates at a single location in space (e.g., a small light bulb), potentially at infinity (e.g., the Sun).
• In addition to its location, a point light source has an intensity and a color spectrum, i.e., a distribution over wavelengths L().
• Area light sources are more complicated. A simple area light source such as a fluorescent ceiling light fixture with a diffuser can be modeled as a finite rectangular area emitting light equally in all directions.

• A more complex light distribution that approximates, say, the incident illumination on an object sitting in an outdoor courtyard, can often be represented using an environment map.
• This representation maps incident light directions to color values (or wavelengths,λ ), and is equivalent to assuming that all light sources are at infinity

​

​

• Environment maps can be represented as a collection of cubical faces, as a single longitude–latitude map or as the image of a reflecting sphere.
• A convenient way to get a rough model of a real-world environment map is to take an image of a reflective mirrored sphere and to unwrap this image onto the desired environment map.

Reflectance and shading

​

When light hits an object’s surface, it is scattered and reflected

​

• Many different models have been developed to describe this interaction.
• The most general form, the bidirectional reflectance distribution function.

​

The Bidirectional Reflectance Distribution Function (BRDF)

• The most general model of light scattering is the bidirectional reflectance distribution function (BRDF).
• Relative to some local coordinate frame on the surface, the BRDF is a four dimensional function that describes how much of each wavelength arriving at an incident direction ^vi is emitted in a reflected direction. The function can be written in terms of the angles of the incident and reflected directions relative to the surface frame as

​

​

• Most surfaces are isotropic, i.e., there are no preferred directions on the surface as far as light transport is concerned. (The exceptions are anisotropic surfaces such as brushed (scratched) aluminum, where the reflectance depends on the light orientation relative to the direction of the scratches.) For an isotropic material, we can simplify the BRDF to

​

​

BRDFs for a given surface can be obtained through

• physical modeling
• heuristic modeling
• empirical observation

Typical BRDFs can often be split into their diffuse and specular components

​

Diffuse reflection

• The diffuse component (also known as Lambertian or matte reflection) scatters light uniformly in all directions and is the phenomenon we most normally associate with shading, e.g., the smooth (non-shiny) variation of intensity with surface normal that is seen when observing a statue.
• Diffuse reflection also often imparts a strong body color to the light, as it is caused by selective absorption and re-emission of light inside the object’s material.

​

the amount of light depends on the angle between the incident light direction and the surface normal i. This is because the surface area exposed to a given amount of light becomes larger at oblique angles, becoming completely self-shadowed as the outgoing surface normal points away from the light. The shading equation for diffuse reflection can

thus be written as

Di-chromatic reflection model

​

Global illumination (ray tracing and radiosity)

​

• The simple shading model presented thus far assumes that light rays leave the light sources, bounce off surfaces visible to the camera, thereby changing in intensity or color, and arrive at the camera. In reality, light sources can be shadowed by occluders and rays can bounce multiple times around a scene while making their trip from a light source to the camera.
• Two methods have traditionally been used to model such effects.
• If the scene is mostly specular-the preferred approach is ray tracing or path tracing. which follows individual rays from the camera across multiple bounces towards the light sources (or vice versa).
• If the scene is composed mostly of uniform albedo simple geometry illuminators and surfaces, radiosity (global illumination) techniques are preferred.
• Combinations of the two techniques have also been developed, as well as more general light transport techniques for simulating effects such as the caustics cast by rippling water.
• The basic ray tracing algorithm associates a light ray with each pixel in the camera image and finds its intersection with the nearest surface.
• A primary contribution can then be computed using the simple shading equations.
• Additional secondary rays can then be cast along the specular direction towards other objects in the scene, keeping track of any attenuation or color change that the specular reflection induces.