Question

1. write a critique of the use of computer vision technology in any sporting activity of your choice

2. Using practical examples, describe how expert systems perform inference and discuss five paradigms involved in solving problems using an Expert system

Answer 1

1a)Computer vision is a part of artificial intelligence and machine learning that develops techniques to train computers to interpret and understand the content inside images this can also be applied to videos as a video is a collection of consecutive images or frames.

Computer vision aims to replicate parts of the complexities in human vision system and visual perceptions by applying deep learning models to accurately detect and classify objects from the dynamic and varying physical world.

The first basic neural networks were developed around 1950's to detect edges of simple objects and sort them into categories i.e circles,triangles squares and so on .

These systems were further developed to help the blind by enabling them to recognise written and typed text characters using a method known as optical character recognition.

Due to internet 1990's the unprecedented datasets of images were regularly being shared and generated across the web.

These visual datasets enabled researchers to better train their models and develops face recognition programs that helped computers identify specific pictures inside of photos and videos.

The advancement in smartphone technologies, social media and their frequent use by billions of users.

More than 3 billions images are shared online through web and continuously generating greater amount of visual data with the increased accessibility to large computers power and the innovations in deep learning and neural networks algorithms the availability of such increase amount of images have brought to learn the patterns and characteristics of these images and enhance accuracy rates to 99% in number of their applications.

Computer vision is now able to perform a variety of tasks in a wide range of fields from self driving cars to medical diagnosis some of these tasks include photo classification, object detection face recognition and searching image and videos content .

They first need to read images in most raw numerical form the matrix of their pixels their matrix represents the brightness of eachpixel in an image from the darkest black at value 0 to darkest white to at value 255.

Images are made up of thousands of pixels these pixels are one dimensional array with values from 0 to 255.

One single image will contain 3 different matrices for these components that represent the three primary colours red,green,blue(RGB).

Deep learning algorithms in computer vision make use of these pixel arrays to apply statistical learning methods such as linear regression, decision tree or support vector machines (SVM).

By analysing the brightness values of a pixel and comparing it to its neighbouring pixels.

A Computer vision model is able to identify edges ,detect patterns and eventually classify and detect objects in an image based on previously learned patterns.

The applications of computer vision in sports:

In sports artificial intelligence was virtually unknown less than 5 years ago but today deep learning and computer vision are making their way into a number of sports industry applications. Whether it is used by broadcasters to enhance spectators experience of a sport or by a clubs themselves to became more competitive and achieve success and increased its adoptions of these modern techniques.

Most major sport involve fast and accurate motion that can sometimes becomes challenging for coaches and analyses to track and analyze in great detail

This is particularly difficult in those situation when the use of wearable tracking equipments and sensors to augment data collection is not a option

In training certain matches especially of they are a televised performance analyst are able to obtain limited number of angles of videos footage this footage is limited to providing visualisations of the player movement rather than detailed analysis

The data and insights obtained from.the footage requires the analyst to spend numerous hours manually noting and collecting events as they replay the video scenarios such as they replay the video scenarios such as this is where the applications of computer visions techniques can bridges the gap between the sporting event and analytical insights by offering novel ways to gather data and obtain valuable analysis through automated systems that locate and each player of interest and following them over the duration of the video.

In the context of sports footage is usually acquired through one or more cameras installed at close proximity of where the event takes place I.e the sidelines of training field or the stadium during a match

The angle positioning hardware and other filming configurations of these cameras can vary greatly from.sport to sport went to event or ever within the different cameras used for the same match or training session.

Computer vision applications to accurately to detect the precise positioning of objects on direction of movements as they may fail to understand the varying configurations used to capture the different footage presented to them.

Traditionally, costly camera calibration for multi camera tracking systems was essential for football and players tracking systems for fixed angle cameras this could be done through scene calibration, where balls were rolled over the ground to account for non planarity of the playing surface

However broadcast cameras present addtional challenges in that often change their pan,tilt and zoom

Performance analysis department within football clubs limiting their capacity to apply advanced tracking of players.

Computer vision has solved these limitations with its application of image processing, Computer vision systems are now able to distinguish between the ground player and foreground player

1b)Expert system:expert system is an interactive and reliable computer based decision making system which uses both facts and heuristics to solve complex decision making problems .

The purpose of expert system is an artificial intelligence resolves many issues which generally would require human experts

It is based on knowledge acquired from an expert and capable of expressing and reasoning about domain of knowledge

Expert system were the predecessors for current artificial intelligence ,machine learning and deep learning

Practical examples of expert systems

Are MYCIN  used to detect acute bacteria infection

DENDOR used to in chemical analysis to predict molecular structure

PXDES :to detect lung cancer occur

CADET used in detection of cancer

Characters of expert system

1highest level of expertise

2used to react fastly

3 good reliabilty

4 flexible

5 effective mechanism

6 capable of handling challenging decisions

Components of the expert system:

user interface :

the user the crucial part of the expert system software this component takes the user query in a readiable form and passes it to the inference engine after that it displays results to the user

Inference engine:

Is The brain of the expert system

Inference contains rules to solve a specific

Problem.

It refers the knowledge from the knowledge base it selects facts and rules to apply when trying to answer the users query.it helps in deducting the problem to find the solution.

Knowledge base:

The knowledge base is a repository of facts

It stores all the knowledge about the problem domain

It is like a large container of knowledge which is obtained from different experts of specific domain

The success of an expert system software depends on the highly accurate and precise knowledge.

Applications of expert systems these inference engine rules to solve s specific problems is:

1information management

2)hosipital and medical facilities

3)helps desk management

4)loan analysis

5)virus detection

6)employee performance evaluation

7)warehouse optimization

8)helps in repairs and maintenance of projects

9)configuring manufactured objects

10)financial decision making

11)process monitoring and control

12)planning and scheduling

13)supervise the operation of plants and controller

14)airline scheduling and cargo scheduler

Benefits of expert system:

1.it improves the decision quality

2.cut the expense of consulting experts for problem solving

3.it can provide fast and efficient solution

4.it can gather scarce expertise and used it efficiently

5.maintain significant level of information

6.helps is to get fast and accurate results

7.a proper explanation of decision making

8.able to solve complex problem issues

9.it can steadily work without getting emotional tensed or fatigue.