into two main groups: 1. Binary vision sensors 2. Grey level vision sensors Binary vision sensor • This class of sensor produces images whose pixel (pixel = picture element) values are either a black or white luminosity level equivalent to a logic 0 or 1, hence the name 'binary'. • The complete picture is therefore only a series of logic 1 and O. This allows easy distinction of dark objects on light background (and vice versa) • In view of the low visual data content, fast image data manipulation such as object perimeter and/or area calculations. Block diagram of typical binary vision sensor Thresholding • Definition: An image processing method that creates a bitonal (aka binary) image based on setting a threshold value on the pixel intensity of the original image. While most commonly applied to grayscale images, it can also be applied to color images for converting in to binary image. Example of output of binary vision sensor. • In the example shown the vision system has learnt the characteristics of three objects, based on the number of holes, object size and shape features. Thereafter, whenever the vision system is presented with an image containing one of these objects it will be able to 'recognize' it. • This is achieved by comparing the features of the object in the new image with those stored in memory. • This technique of image processing is sometimes referred to as the SRI method (or one of its derivatives) because it was first introduced by Rosen et al. at the Stanford Research Institute (now SRI International) and imposes severe restrictions on the lighting conditions and on the position of the object for a successful operation. • The object must show up as an isolated object and its stable states must be known in advance .Thus overlapping objects and situations with any 3-D freedom of movement are difficult to deal with using binary vision sensors. Grey level vision sensors • This class of sensor produces an output image whose pixel values are quantized into a number of discrete levels, achieved by converting the optical transducer analogue output into the appropriate number of digital levels. • A grey-level image can be produced with the help of some computing power (either within, as in the case of intelligent sensors, or without, by using the vision system main computer). • This procedure is based on processing an appropriate number of binary images obtained using different exposure times, whose difference provides a measure of each pixel intensity in the object image. • In example, the typical grey-level image of a bicycle chain link using eight intensity levels as provided by a 2-D grey level vision sensor based on a 256 x 128 cells DRAM camera. • A comparison of this image with the one obtained using a binary sensor, shows how grey-level vision sensors (in conjunction with reflected illumination) provide more details of the object surface features. This, however, increases the amount of visual data and makes its processing more difficult, slower and computationally more expensive. Example of grey level vision sensor 3D VISION SENSOR • Indirect methods of obtaining depth maps, based largely on triangulation techniques, have provided the largest input in this area. • In computer vision triangulation refers to the process of determining a point in 3D space given its projections onto two, or more, images. ... The triangulation problem is in theory trivial. Since each point in an image corresponds to a line in 3D space, all points on the line in 3D are projected to the point in the image. DISPARATIVE AND PHOTOMETRIC METHOD
• The disparity technique is based on the correlation
between images of the same object taken by two different cameras under the same lighting conditions (Marr and Poggio, 1976), while the photometric technique is based on the correlation between the images taken by the same camera under two different lighting conditions (Ikeuchi and Horn, 1979). (a) Disparity method 1 • Use of two stationary imaging devices. This could be defined as the 'classical' stereo vision method because of its analogy to the human vision system. • It consists of an illumination system and two stationary cameras which provide the required two 2-D images. • This method is inherently more expensive than the other two because it uses 2 cameras but does not require any mechanical movement and, therefore, compared to method 'b' is faster and can provide more accurate measurement of the cameras positions as required for the disparity calculations. Method 2 (b) Disparity method 2. • Use of one imaging device moved to different known positions. • This is essentially a cost variation on the method 'a' ,since it only differs by the use of a single camera which, to provide images from a different angle, is mechanically moved to a different known position. PHOTOMETRIC METHOD IN STEREO VISION. • Use of one stationary imaging device under different lighting conditions. • This method relies on maintaining a camera in the same position, thereby avoiding the pixel correspondence problem, and obtaining multiple images by changing the illumination conditions. Processing of these images can uniquely determine the object surfaces orientation thus enabling its 3-D mapping (Woodham 1978). ULTRASONIC RANGE FINDER • The principle of operation of an ultrasonic sensor is to measure the time delay t between the transmitted and reflected sound pulses which, assuming a constant velocity v for sound propagation, is related to the obstacle distance d by the simple formula d = vt. Steps of ultrasonic rangefinders • diagram illustrates the main steps of the ultrasonic distance measuring method. • A sound pulse is produced by the ultrasonic transducer (pulse length approximately 1 ms and frequency spectrum from 50 kHz to, typically, 60 kHz) which, after a time delay proportional to the object distance from the sensor, also receives the reflected sound pulse or 'echo'. • The hardwired local intelligence then processes these two signals (emitted and reflected pulses) and calculates the obstacle distance from the sensor.