Revealing Stereo And 3D
Introduction
Home | Downloads | DCB | Store | Boot | Xprmnts | Intro | Bib | Motion | Focus | Sgmnt | Rcgntn | Depth | Build | Fail
        The challenge of interacting with humans constrains how our robots appear physically, how they move, how they perceive the world, and how their behaviors are organized. We want it to interact with us as easily as any another human. We want it to do things that are assigned to it with a minimum of our interaction. In other words we can never predict how it is going to react to a stimulus and what decision it is going to take.
For robots and humans to interact meaningfully, it is important that they understand each other enough to be able to shape each other’s behavior. This has several implications. One of the most basic is that robots and humans should have at least some overlapping perceptual abilities. Otherwise, they can have little idea of what the other is sensing and responding to. Vision is one important sensory modality for human interaction, and the one in focus here. We have to endow our robots with visual perception that is human-like in its physical implementation. Similarity of perception requires more than similarity of sensors. Not all sensed stimuli are equally behaviorally relevant. It is important that both human and robot find the same types of stimuli salient in similar conditions. Our robots have a set of perceptual biases based on the human pre-attentive visual system. Computational steps are applied much more selectively, so that behaviorally relevant parts of the visual field can be processed in greater detail.

        Before the process of capturing the image it is required to focus properly to the object of interest. In order to achieve this, one of the techniques that is used is, finding out the place where maximum contrast is obtained. When we say that an object is being seen it is only a part of the entire scene captured that is of interest to us.

To segregate things from one another a technique called segmentation is used. Segmentation is an edge detection technique, which isolates bounded edges of similar color.

The concept of stereovision brings in a greater limitation in the size of the scene analyzed. To achieve this it is necessary to have a pair of cameras. Humans perceive depth due to the presence of two eyes. The disparity between the left and the right images gives us the presence of depth. Stereovision together with focusing distinguishes the background from the foreground object that is under observation.  In a robot correlation together with triangulation is used to measure depth. In case the correlation between the two images is absent, then one of the images needs to be suppressed in order to avoid binocular rivalry.

        Another major aspect of computer vision in robotics is motion detection. Since foveal vision serves only a small portion of the visual scene motion detection is incorporated in order to know the changes in the surrounding scene. In order to detect motion the dissimilarity between two consequent frames is checked.

 
Here are some links to my photography gallaries: