ARCHITECTURAL MODEL OF ROBOT VISION
SYSTEM – SMART CARD TECHNOLOGY
Technological advancement is widening up by the advent of new inventions. Robot is one such invention to overcome the ever-present challenges of high cost of labor, third world combination, and consumer demand for higher quality and greater variety at a lower cost. It is an interdisciplinary field that ranges in scope from the design of mechanical and electrical components to sensor technology, computer systems, and artificial intelligence. It is the Science of designing and building robots suitable for real life applications in manufacturing and other non-manufacturing environment. In non-manufacturing environment robots act as computer-controlled camera that allows it to see its environment and respond accordingly is known as its vision.
In the current scenario, the Robot Vision System is basically used for inspection purposes in Industries such as gauging, verification of presence of components, detection of flaws, etc… In this paper we have designed an architectural model of Robot Vision System, by integrating it with Smart Card. Some of the advanced features of the model are identifying the speeding vehicle, vehicles that are not in proper lanes, reporting and sending the details of the vehicle to nearby Control Station along with the particulars of the vehicle are the hallmarks of the designed system. To avoid the unauthorized use of National Highways, we have introduced a simple chip incorporated into the Robot Vision System. The main aim of our paper is to protect valuable “human lives”. This advanced Smart Card and Robotic Sensors System helps to avert accidents and damage to public property in future.
v MACHINE VISION SYSTEM:
Machine Vision can be defined as acquisition of image data followed by processing and interpretation of data by using computer for some useful applications. The Machine Vision System is generally classified as Two Dimensional and Three Dimensional System. Generally, Three Dimensional is more advantageous, but anyhow Two Dimensional System is much preferred for simple applications. The general applications of Machine Vision System are dimension measuring, gauging, verifying presence of components (flaws), and checking flatness of surface.
v IMAGE ACQUISITION AND DIGITIZATION:
Image Acquisition and Digitization is accomplished using a video camera and a digitizing system to store the image data for subsequent analysis. The camera is focused on the object of interest or the subject of interest and the image is obtained by dividing the viewing area into a matrix of discrete picture elements called pixels, in which each element has a value that is proportional to the light intensity of that portion of the scene.
The intensity value for each pixel is converted into its equivalent digital value by an
ADC (Analog to Digital Converter).
Two types of Vision System:
1. Binary Vision:
In Binary Vision the light intensity of each pixel is ultimately reduced to either of two values, black or white, depending on whether the light intensity exceeds a given threshold level.
2. Gray Scale Vision System:
Gray Scale Vision System is a more sophisticated vision system, which is capable of distinguishing and sorting different shades of gray in the image depending on the intensity level. This type of system can determine not only an object’s outline and area characteristics, but also its surface characteristics such as texture and color. Gray Scale Vision System typically uses 4, 6 or 8 bits of memory.
Each set of digitized pixel value is referred to as a frame. Each frame is stored in a computer memory device called as frame buffer. The process of reading all the pixel values in a frame is performed with the frequency of
30 times per second.
Types of camera:
The two types of cameras that are used in Machine Vision applications are:
1. Vidicon Camera:
Vidicon Cameras are operated by focusing the image onto a photoconductive surface and scanning the surface with an electron beam to obtain the relative pixel values.
2. Solid State Camera:
Solid State Cameras are operated by focusing the image on to 2
Dimensional array of very small finely spaced photosensitive elements which form the matrix of pixels. An electrical charge is generated by each element according to the intensity of light striking the element. The charge is accumulated in a storage device consisting of an array of storage elements corresponding one – to- one with a photosensitive picture element. These charge values are read sequentially in the data processing and analysis function of Machine Vision.
The scene viewed by the vision camera must be well illuminated, and the illumination must be constant over the time. This almost always requires the special lighting to be installed for Machine Vision applications rather than rely on ambient lighting in the surroundings.
Types of Illumination:
1. Front Lighting:
2. Back Lighting:
3. Side Lighting:
4. Structured Lighting using a planar sheet of light:
v IMAGE PROCESSING AND ANALYSIS:
The second function in the operation of Machine Vision System is Image Processing and Analysis. The data that must be processed is significant and the data for each frame must be analyzed within the time required to complete one scan (1/30 second). A number of techniques have been developed for analyzing the image data in Machine Vision System. The two categories in Image Processing and Analysis are:
Segmentation techniques are intended to define and separate regions of interest within the image. Two of the common segmentation techniques are thresholding and edge detection.
Thresholding involves the conversion of each pixel intensity level into a binary value, representing either whit or black. This is done by comparing the intensity value of each pixel with defined threshold value. If the pixel value is greater than the threshold, it is given the binary bit value of white, say 1; if less than the defined threshold, then it is given the bit value of black, say 0.
Edge detection is concerned with determining the location of boundaries between an object and its surroundings in an image. This is accomplished by identifying the contrast in light intensity that exists between
adjacent pixels at the borders of the object. A number of software for algorithms has been developed for following the border around the object.
2. Feature Extraction:
Most of the Machine Vision System characterizes an object in the image by means of the object’s features. Some of the features of an object include the object’s area, length, width, diameter, perimeter and center of gravity. Feature Extraction method are designed to determine these features based on a area and boundaries of the object
The interpretation function is usually concerned with recognizing the object, a task termed object recognition or pattern recognition. The objective in these tasks is to identify the object in the image by comparing it with predefined models. Two commonly used interpretation techniques are:
1. Template Matching:
Template Matching is the name given to various methods that attempt to compare one or more features of an image with the corresponding features of a model or templates stored in computer memory. The most basic template matching technique is one in which the image is compared, pixel-by-pixel, with the corresponding computer model.
2. Feature Weighting:
Feature Weighting is a technique in which several features such as area, length, perimeter, etc… are combined into a single measure by assigning a weight to each feature according to its relative importance in identifying the object. The score of the object in the image is compared with the score of an ideal object residing in computer memory to achieve proper identification.
SMART CARD TECHNOLOGY:
Smart Card is a technological advancement, which has the potential to make a significant impact on the quality of human life. It is manufactured using Semi Conducting and Magnetic Materials.
There are two types of Smart Cards namely Contact Smart Cards for which a Smart Card reader is required, and the Contact-less Smart Cards, which can be waved in front of Sensors and used accordingly. This type of Smart Card is very useful for Mass Transit and applications where large number of movement of people happen very quickly and frequently. The main application of these Smart Cards are data carrier, identification and financial.
PROPOSED MODEL OF ROBOT VISION USING SMART CARD TECHONOLOGY
After a study regarding the accidents in National Highways, it was found the main cause behind these were due to over speeding of vehicles and change of lanes during the course of travel. In addition to this we have introduced a chip card, which will prevent the unauthorized usage of National Highways. In order to avert these we have designed a paper, which would be valuable.
ACCM: AUTOMATED CARD CHECKING MACHINE
REGN. CHECK: REGISTRATION NUMBER CHECK UP
SPEED CHECK: DONE USING OPTICAL ENCODERS
v PROCESSES INVOLVED:
SMART CARDS FOR TOLL COLLECTION:
Several states in India have a system of Tax called octroi which is tax collected for goods or entry. This introduces a tremendous amount of paper work and also lack of transparency. By usage of Automated Fare Collection System (prepaid Smart Card) will assist in reducing paper work and also will ensure complete transparency at the toll. A contact less Smart Card with electronicasssslly pre-loaded money is used to pay the exact fare by flashing the card to contact less Smart Card reader. The Card communicates with the uuthe Highways Department.
The procedure is that the highway user should buy the Smart Card in ssssuadvance to his usage of the National Highway. The highway user is expected to insert the Smart Card in the Automated Card checking System and if the required conditions were satisfied, the user would be permitted to enter the National Highway.
v ROBOT VISION SYSTEM:
The Robotic Sensors have the capability of identifying the vehicle to a distance of 50 meters on either side and accordingly the Robotic Sensors are placed.
v IMAGE ACQUISITION AND DIGITIZATION:
Video Camera: SOLID STATE CAMERA
Vision System: GRAY SCALE VISION SYSTEM
1. The basic idea of using a Gray Scale Vision System is to exactly get the image of the vehicle and the Registration Number of the vehicle so as to be compared with the images already stored in the host computer.
2. If the Registration Number of the vehicle that is traced is not present in the sorted list of Registration Numbers then this indicates an unauthorized usage of the highway for which the highway user is to be fined.
Illumination: STROBE LIGHTING
In Strobe Lighting, a short pulse of high -intensity illuminates the scene
Light, which causes a moving object to appear stationery? The pulse of light
can last 5-500 microseconds. This is sufficient time for camera to capture the image although the camera actuation must be synchronized with that of the strobe light.
v IMAGE PROCESSING AND ANALYSIS:
Thresholding is one of the Segmentation techniques. This technique is very useful in getting the image of the approaching vehicle with the Registration Number in white or black.
Technique used: TEMPLATE MATCHING
The images of most commonly used models of vehicles are stored in the host computer. The image of the approaching vehicle is compared with the images in the host computer. And if the images of the vehicle don’t match, then it indicates the improper usage of lanes. Then immediately the particulars about the vehicle are stored and informed immediately to nearby Control Station.
The speed of the vehicles is calculated using the Velocity Sensors.
The velocity Sensor used in this system is Encoders.
Encoders are non-contact type position sensors. Unlike potentiometers, which give analog signals, encoders give digital signals directly. They basically consist of a photo transmitter (light source), photo receiver (photo cell).
Types of Encoders:
1. Incremental Encoders:
2. Absolute Encoders:
*ROBOTIC SENSOR SYSTEM FOR CHECKING UNAUTHORISED ENTRY
ADVANTAGES OF VISION SYSTEM:
1. In current scenario, a system exists in United States of America, that identifies the over speeding vehicles and automatically spikes appears within a certain distance both in front and at back of the vehicle, which may lead to traffic jam in the Highway till officials from the Control Station comes and clears it, and it also causes damage to the vehicle.
But in Robot Vision System, no damage is caused to vehicle but it identifies the vehicle uniquely using the Registration Number and they are ultimately fined.
2. When accidents occur in National Highways, the clear picture of the
Accident can be got, and the culprit can be held with then help of Registration Number.
3. Unauthorized use of National Highway could be averted.
ADVATANGES OF AUTOMATED FARE COLLECTION SYSTEM
(Using SMART CARD)
1. This improves the operational efficiency.
2. Minimization of Revenue leakage.
3. Increased Cash flow due to advance collection.
4. Highway user gets better service.
This system if implemented in National Highways would be very helpful in reducing the number of accidents. In future this system would be forced to be implemented as the usage of vehicles is on a constant increase. So we recommend this paper to the Highways Department. The modified version of system can also be introduced in the Railways, as it will be useful in averting the collusions between the trains due to improper signaling.
Robotics by William P.Groover.
Robotics and Automation Engineering by S.R. Deb