Graphics and Computer Vision | My Assignment Tutor

1School of Computing ModuleCoordinatorOther lecturersDr. Jiacheng TanDate IssuedTBCCodeGACV/M30242TitleGraphics and Computer Vision Schedule and Deliverables ItemValueFormatDeadlineLat deadlineEcf deadlineCoursework50%A single .zip filecontaining all sourcecode and documents2021-01-15 23:59 [GMT]2021-01-29 23:59FinalExamination50%Paper-based, closedbook examination.Timetabled assessmentperiod:2021-01-25 to 2021-02-05 Notes and Advice● The Extenuating Circumstances procedure is there to support you if you have had anycircumstances (problems) that have been serious or significant enough to prevent you fromattending, completing or submitting an assessment on time.● ASDAC are available to any students who disclose a disability or require additional supportfor their academic studies with a good set of resources on the ASDAC moodle site● The University takes plagiarism seriously. Please ensure you adhere to the plagiarismguidelines. And watch the video on Plagiarism● Any material included in your coursework should be fully cited and referenced in APA 7format. Detailed advice on referencing is available from the library● Any material submitted that does not meet format or submission guidelines, or falls outside ofthe submission deadline could be subject to a cap on your overall result or disqualificationentirely.● If you need additional assistance, you can ask your personal tutor, student engagementofficer [email protected] , academic tutor [email protected] or your lecturers.2M30242 Graphics and Computer Vision 2020-21CourseworkThis assessment accounts for 50% of the overall assessment of the module. It consists of twotasks that assess the learning outcomes 3 and 4.This assignment document contains two appendices.Warnings:1. The work you submit must be of your own. You may reference the numerousexamples on the web, but you must NOT copy any of the examples. Failure tocomply with this requirement may result in plagiarism procedures being taken.2. The programs you submitted must be compatible with the software and hardwaresettings on standard University lab PCs without requiring installation of anyadditional libraries or updates. It is your responsibility to make sure all the files areintact and compatible with version of the software provided by the IT Service of theuniversity (see for detailed information)Submission1. Submit all the deliverables of both Task 1 and 2 in the form of a single zip filenamed with your student number through the Coursework Submission folder on theunit base on Moodle.2. Submission on Moodle will open a week before the deadline and close at 23:59 onthe deadline day.3. The submission must be anonymous. Do NOT write your name on any artefact.4. Emailed work will NOT be accepted.3Task One (50%)Warning: For this task, you are NOT allowed to use any WebGL library that has built-infunctions for creating, drawing, texturing geometric primitives such as spheres, cubes, and soon. You need to generate the vertex data of such objects, i.e., vertex coordinates, texturecoordinates and normals, and perform the relevant operations, such as texture mapping,lighting and shading calculations, by yourself.SpecificationIn this task, you are required to create an animation. The scene consists of the planet earth inthe middle with a satellite orbiting around it along a circular orbit within the horizontalplane. The scene is illuminated from top-right by a directional light that is at a 60-degreeangle with the horizontal plane if viewed in front view.The earth model is a sphere of radius 10 and mapped with an earth image. The earth rotatesslowly around its own vertical axis. An image of the earth is provided for texturing thesphere.The satellite consists of a main body of a cube of size of 2x2x2 and two “solar panels” thatare attached to the two opposite sides of the main body through two connection “rods”. Therods are cuboids of size 0.2×0.2×0.5 and golden in colour. The solar panels are blueish thinrectangular objects of 1×2 in size. For simplicity, we assume that the panels always faceupwards. One side of the cube representing the main body of the satellite has a black colour,which will constantly face the earth while orbiting the earth. A golden antenna dish of adiameter of 4 is attached to the black side by a golden rod of 0.2×0.2×0.4. The antenna willface the earth.The animation will be interactive: You should be able to control the radius of the circularorbit (with the left and right arrow keys) and the speed (up and down arrow keys) of thesatellite at runtime. You should have full viewport/scene-navigation control: translationsalong x- (shift plus mouse drag), y- (alt plus mouse drag) and z-direction (mouse wheel) androtations around x- and y-axes (mouse drags). The translation controls should be independentof the rotation controls.Your application should work with standard browsers on University lab PCs withoutrequiring any special set-up or configuration of software or hardware. Firefox browser ispreferred because textures may not work properly in Google Chrome if its security policyprevents loading texture files locally. You should extensively test the animation controls toensure that any control action will not cause the system to freeze, crash, or any scene objectsto disappear or behave in a strange way.Deliverables1. The source code of the entire WebGL application and any necessary supporting files suchas libraries and textures. The program code should be suitably commented and come withnecessary instruction for using it.2. An electronic copy of a short report (no more than 1000 words) that documents thedesign/implementation decisions, difficulties or problems (if any) and evidence and/orconclusions of test and evaluation of the application against the specification.4Task Two (50%)Application Scenario and ConditionsTo control the traffic at the entrance of a narrow tunnel, a computer vision system is used tointercept oversized or speeding vehicles. Any vehicle that exceeds 2.5m in width and/or 30miles per hour in speed will be diverted or stopped by traffic lights or police officers uponreceiving the warnings from the system. Fire engines (assuming that they are mainly red incolour and have a width/length ratio of approximately 1:3) are the only vehicles exemptedfrom the control.The system consists of a video camera fixed right above the centre of the lane of a straightroad and is 7m off the ground. Its optical axis is 30 degrees off the horizon and pointing tothe lane along the direction of traffic. A diagram showing the camera configuration is givenin the Appendix. The resolution of the sensor of the camera is 640X480 pixels. Forsimplicity, it is assumed that the pixels of the camera sensor are square and each sensor pixelis equivalent to 0.042 degrees in view angle. The camera grabs a video frame (an image) ofthe lane at 0.1s intervals. It is further assumed that each frame contains only one vehicle. Theoutput frames from the camera will be the only input to the vision system. You should notmake any assumptions about the identity of the vehicle contained in a frame beforeprocessing the frame.Requirements1. Functions or Functional Blocks. Design and implement in Matlab a computer visionapplication that fully meets the specification. Your application should contain the followingbasic functions or functional blocks: Size detection, Speed detection, Colour detection2. Outputs and Information. Your program should output the results of the key processingsteps, for example smoothed images, colour blobs, centres, outlines or bounding box, anddocument them in the report (see Requirement 4) in the form of screenshots.Your program must output the following values or information in the command line window:Car width: metersCar length: metersCar width/length ratio:Car colour:Car speed: mphCar is speeding (Y/N):Car is oversized (Y/N)Car is fire engine (Y/N):3. Test and Verification. Include the following script (name it as Test.m) in yourapplication and use it to test your application. The coursework assessors will run the script toverify the intermediate and final outputs of the application.clear,close all,img1=imread(“xxx.jpg”),img2=imread(“xxx.jpg”),my_application(img1,img2)5Speeding detection could be tested using image pairs 001.jpg vs 002.jpg, 001.jpg vs 003.jpg ,001.jpg vs 004.jpg, and so on by assuming that the images are taken at 0.1s interval in eachcase. Fire engine and oversized vehicle should be tested using the relevant images.4. Documentation and Report. Prepare a report of no more than 1000 words that documentsthe system design, testing and evaluation. The report should• include discussions of the necessary conditions of and/or assumptions about theapplication that may help to justify your design decisions;• provide a concise flow diagram of the entire system to show the important processingsteps;• justify each processing step by discussing or showing the features you want toextract, the method used for extracting the features, and the screenshots of the inputand output of the processing step;• document your test against the application scenarios by providing the inputs, e.g., thenames of image files, and outputs, e.g., the screenshot of the speed/width/colour of avehicle and any command-line messages.Deliverables1. Program code and supporting files. The program code should be in M-file format andsuitably commented and with instructions to use/run it.2. A copy of the coursework report that meets Requirement 4.6Appendix 1 Camera system configuration7Appendix 2 Marking Scheme Task One (50%)Object modelsAccurate models of each elements of the scene.Surface attributesColours and/or texture mapping.LightingUse of light and any justificationAnimation and interactive parameter controlOverall animation, satellite orbit & speed controlScene navigation controlTranslation & rotation controlsTest & evaluationReport156 6126 5Task Two (50%)Correct detection of traffic• Speeding detection (30mph).• Oversize vehicle detection (2.5m).• Fire engine detection.Feature selection and detection• Selection of appropriate features.• Correct detection methods/procedures & appropriate parameters.• Quality of extracted features.Testing & Evaluation• Testing script• Evidence & documentation (screenshots and discussions) of testagainst traffic scenariosReport• Discussions of any conditions/assumptions• Flow diagram and justification (For each processing step: feature &detection-method selection, screenshots of inputs and outputs)• Documentation and discussion of test against traffic scenarios &evaluation against requirements15101015


Leave a Reply

Your email address will not be published.