Projects

 ​​Project Title ​Automatic License Plate Recognition
​Group Members Junaid Ibn-e-Tanveer Malik

Ehtasham Anwar

Omer bin Dilawar

​​Project Supervisor(s) ​​Dr Shahzor Ahmad
​Project Abstract The aim of our final year project is to detect the license plate from the whole image and then recognize the characters of the detected license plate. There are many online Github open-source code and many other online platforms that are aimed at detecting and recognizing the License Plate of International dataset (i.e. cars). But unfortunately there were not any of the online platforms available that were aimed strictly at detecting and recognizing the license plate of Pakistani vehicles. Therefore, we wanted to devise a framework that was strictly limited to Pakistani vehicles to efficiently perform ALPR on Pakistani dataset
​​Project Title ​Fleet Management System
​Group Members ​Shayan Ali Sadiq

Amaad Ali

GC Haider Imtiaz

GC Haris Ahmed

​​Project Supervisor(s) ​​Dr Qasim Umer Khan
​Project Abstract Fleet Management system Commercial engine vehicles, for example vehicles, vans, trucks, expert vehicles, forklifts, and trailers Private vehicles utilized for work purposes Aviation apparatus, airplane Ships Rail vehicles.

With the ascent in the number of business Fleet vehicles consistently, it is hard for the Fleet supervisors to utilize conventional and manual methods of dealing with its Fleet. Utilizing the present mechanical progressions, it is conceivable to grow such a framework, that deals with all the concerns of the Fleet chief. Developed innovations like Global Positioning System (GPS), Global System for Mobile Communications (GSM), General Packet Radio Service (GPRS), and WI-FI can be used to devise such a framework. Knowing where the vehicles are, what the drivers are doing, and checking each occasion progressively is the key boundary for an all-around oversaw dynamic procedure.

The proposed Intelligent Fleet Management System will permit Fleet administrators to distantly follow vehicles utilizing reasonable guides and perspectives produced from Global Positioning System (GPS) information. Also, it will likewise be equipped for giving ongoing rate, continuous forecast of appearance time at the goal, driving conduct of the driver and convenient support alarms, and so on. These additional highlights will make this framework insightful and shrewd. This framework will help in getting more authority over drivers and vehicles, forestalling delays in conveyances, improving driving propensities, forestalling questionable revealing and decreasing upkeep costs, and so on.

​​Project Title ​Digital Current Control Unit
​Group Members ​Awais Ahmad

Usman Waqar

Ammar Tariq

​​Project Supervisor(s) ​​Dr Muwahida Liaquat
​Project Abstract ​Electrolysis is a process of producing Hydrogen free from oxygen atoms from water. This process uses Electricity to split Hydrogen atom from the bonded oxygen atom. This process takes place in an Electrolyzer or an Electrolysis plant .We are given a huge Electrolysis plant that has a voltage of 5 Kilo Volts. This process is to be controlled in control room, which has a sophisticated equipment to control the process. This equipment has very low capacity to handle voltages more than the rated voltage. The equipment is very costly so it needs something for handling such high voltage levels.

It uses an Analogue Current controller to limit the voltage. We are to design a Digital Current Control unit that allows the operator to operate at maintained current levels. It should allow the operator to switch between different current levels depending on the need. The current control unit depending upon the setpoint and process value will calculate firing angle to fire the thyristor to provide the necessary current needed. The microcontroller automatically calculates the firing angle for the thyristor before the next cycle comes

​​Project Title Power Monitoring and Optimization System
​Group Members ​Adil Akhtar Ali khan

Syed Haannie Ali Kazmi

Muhammad Abdullah Naeem

​​Project Supervisor(s) ​​Dr Usman Ali
​Project Abstract ​With the usage of electrical appliances and various electrical devices, there is a constant need of knowing where and why the power consumption is excessive. This project aims to monitor the electrical power consumed by different electrical devices; whether at home, office or in an industry. Then notify the user about the how much voltage is being provided by the electric supply companies; how much current is being consumed by different appliances and how much the overall power is being consumed. The project uses a standard Arduino Uno to collect data from its voltage and currents sensors. The micro controller processes the information and provides the results on android application, LCD (Liquid Crystal Display) and on a Serial Monitor on a Computer. RMS (Root Mean Square) voltages and currents are measured to provide the best readings in RMS values. The second part of the project includes the optimization phase. It is to optimize the loads if the power consumption increases from a certain current value. Relays shall operate to counter that. The system is automated.
​​Project Title ​Smart Cabinet
​Group Members ​Minahil Sarmad

Salman Ejaz

Amna Asif

​​Project Supervisor(s) ​​Dr Tahir Zaidi
​Project Abstract ​Realising the increasing problem of electricity wastage, and recognising the lack of the access to smart energy saving technologies. We planned to work on a solution which will help save energy and minimize electricity wastage, a system which monitors consumption and makes the data available in real time. Not only that but it will also help locate the vampire loads in our buildings. The modular nature of the Smart Cabinet will make it possible to integrate it with smart switches and smart sockets.The IoT network will enable us to send data over the cloud making the controlling and monitoring of the appliances in the building possible, remotely. An app is also developed for this purpose. We will be able to contribute in solving the energy wastage problem by giving the consumer access to the real-time monitoring of the consumption as well the data of nodes or appliances which are consuming power more than they have to. This will surely help the consumers to be more aware of their billing and energy wastage and will help them reduce it.
​​Project Title ​Customized Power Supply for Li-Ion Version of PAG-Belt
​Group Members ​Sobia Farooq

Sana Riaz

​​Project Supervisor(s) ​​Dr Muwahida Liaquat
​Project Abstract ​Now-a-days, the use of electrical energy is one of the dire needs around the world. PAG rechargeable battery and lighting products are used on a wide range of portable equipment in the professional broadcast, film and video industries. Our objective is to make a customized power supply for li-ion version of PAG belt. As we all know that electronic products need some reliable power supply source to run smoothly and execute all required operations. The main goal of the power supply unit is to covert the AC mains supplied to us to some suitable DC voltages for smooth operations. In more recent designs and power supply units, a SMPS (Switch Mode Power Supply) has become one of the most commonly used architecture. A switch-mode power supply (SMPS) is basically an electronic circuit that converts power using switching devices that are turned on and off at high frequencies, along with the inductors or capacitors (storage components) to provide power in the non-conduction state of switching devices. Using MATLAB simulations and efficient use of TL494 IC, buck converter is designed which is further used for the SMPS design to get the required output. Meanwhile, another circuit is also designed which uses ATMEGA chip to depict the charging status of the power supply.
Project Title Dynamic Cruise Control System for Energy Optimization in Electric Vehicles
Group Members ​Muhammad Azeem Sarwar

Waqar Ali Jan

​​Project Supervisor(s) ​​Lec Sufyan Hafeez Khan
​Project Abstract ​One of the challenges the World is facing currently is Climate change. Climate change is caused primarily by burning of fossil fuels. The major part of these fuels is utilized by automobiles. To counter this, People are working on sustainable form of energies that could run the automobiles, one of which is Electric Vehicles. The major challenge with Electric Vehicle is its Low range and High charging time. To overcome this, the batteries need to be more powerful and efficient. However, due to the limitations caused by the size of vehicle, the overheating caused in the batteries and the explosion in case of mishandling, the batteries have not been as powerful as it needs to be. As a result, we have to think about alternatives such as to find the operating conditions at which the motor will be more efficient. Induction motors, are commercially used in Electric Vehicles such as Tesla. Induction motor has many advantages over other motors for instance, they are more rugged, low maintenance cost and more importantly, they are highly efficient at low speeds. It is also to be considered that at very low speed the total operating time of the induction motor will also increase, consequently, the total power consumption will also go on to increase. That’s why a dynamic setpoint has to be calculated at which the induction motor will be highly efficient. Dynamic set point as the name suggests, will vary in accordance with the variation in the road gradient.
​​Project Title Semi-Automated Annotation of LiDAR Data
​Group Members Amal Saleem

Minhah Saleem

Rabeea Fatima

​​Project Supervisor(s) ​​Dr. Shahzor Ahmad
​Project Abstract ​The purpose of this project is to design a semi-automated annotation tool for LiDAR based data of traffic. Mask R-CNN was trained and used for annotation of RGB Camera images. The annotated labels were then translated on to 3D point cloud. It predicts labels in subsequent frames using tracking algorithm. The web app displays RGB Camera Images with predicted masks, 3D point cloud with adjustable bounding boxes and labels, and cropped image of selected object. It can be very beneficial in annotating LiDAR images, since it only needs a single click on the cluster of object points in 3D point cloud, thus saving a lot of time required otherwise for fully manual annotation.
​​Project Title ​Smart Glove – Real Time Sign Language Interpreting Glove
​Group Members ​Usama Nadeem

Sohaib Rasool

Asfandyar Orakzai

​​Project Supervisor(s) ​​Dr. Shahzor Ahmad
​Project Abstract Communication plays a vital role in our lives. Communication not only allows people to share their knowledge and ideas, but, at the same time, it allows them to understand emotion, feelings, and thoughts. The smart glove will not only fulfill a fundamental tenet of sign language, which is effective communication, but also help bridge the gap in a more cost-effective manner. The glove will use static and dynamic hand gestures to deliver its intended message. This project report proposes a novel approach towards interpreting sign language using an MPU-consisting smart glove.
​​Project Title Car Make and Model Recognition using Deep Learning
​Group Members ​Amna Saleem

Abdullah Saad

Syed Muhammad Usman Ghani

​​Project Supervisor(s) ​Asst. Prof. Sobia Hayee
​Project Abstract ​Security and Surveillance is one of the major problem. Due to human error the degree of security is at risk. Car make and model recognition system will assist the security agencies to catch the culprit as soon as possible by identifying the make and model of the car. It can help many businessmen who wants to open car show room as they can observe the new trends through Car Make and Model Recognition System. Though descriptors such as SIFT, SURF, HOG are used to extract features or key points of the image but it cannot be applied on thousands of images due to computational problems. A system with heavy RAM and multiple GPUs will be required so ‘Deep Neural Network’ are very helpful in this case. We trained Stanford car dataset on ResNet50 model. Performed training with and without augmentation to observe the difference in the accuracy of the model and the classifier. Classifier accuracy with data augmentation is 87.60% and without data augmentation is 77.91%.
​​Project Title Radar Signal Processing on FPGA
​Group Members ​Arooj Khan

Muhammad Suhaib Hussain

​​Project Supervisor(s) ​​Lec Aamir Javed
​Project Abstract ​There are many applications that require a short-range radar system to find the range and velocity of the targets. For example, in ADAS (Advanced driver-assistance systems), we continuously need to monitor the range and velocity of obstacles and other vehicles. Radars can extract information about targets or obstacles using EM waves. FMCW radars are widely used in such applications where we need short-range coverage. In our FYP we have implemented the signal processor for an FMCW radar on the Zynq SoC kit, to detect short-range targets and determine their velocity and range. For this, we used MATLAB to generate the simulated data of FMCW radar. We implemented the UART interface between MATLAB and Xilinx Zynq SoC to transfer simulated data to Xilinx Zynq SoC. Simulated data is first stored in DDR memory on the processing system (PS) side. Then it is transferred from the Processing system (PS) to programmable logic (PL) part of Zynq SoC, using AXI DMA, to apply signal processing algorithms like FFT and CFAR to extract the beat frequencies. This information is transferred to PS, and then to MATLAB on the UART interface. The final output containing range and velocity of targets is displayed on MATLAB.
​​Project Title ​Smart Security System
​Group Members ​Kamran Fazal,

Taimur Hayat Khan,

Zain Noman

​​Project Supervisor(s) ​​Dr Muhammad Zeeshan
​Project Abstract ​Burglary and home invasion both involve forcibly entering and breaking into a property with the intention of committing a crime. Home invasion is defined as forcible entrance into an occupied residence while burglary is defined as breaking into any protected structure, inhabited or not. Hence there is a need for security systems to protect residential and industrial properties to prevent financial and physical lossesThe project aims to develop a smart security system that can monitor both residential and industrial areas. The security system consists of a camera integrated with proximity sensor and motion detection sensor. The camera feeds live video footage to a convolutional neural network (CNN) which detects presence of different kinds of objects including humans, animals etc. The proximity sensor is fitted at the entrance door of the property and detects whether the door has been opened or not. The motion detector, as the name suggests, detects motion in the vicinity. The CNN calculates confidence rates of the object and creates bounding boxes around the object. All the information from the CNN and sensors is fed into a perceptron that calculates the threat level of the intrusion. This threat level and the output of the sensors and CNN are uploaded to a web API. The owner of the property can then access this data using a mobile app and safely secure their property.
​​Project Title ​Detection of Abnormalities in Chest Radiographs Using Deep Learning
​Group Members ​Aiman Tariq

Azka Rehman

Mushkbar Fatima

​​Project Supervisor(s) ​​Asst. Prof. Sobia Hayee
​Project Abstract ​A chest x-ray radiograph is a crucial tool to diagnose numerous diseases. Diagnosing and treating patients timely is crucial which results in overworking the radiologists. With the development of AI and particularly deep neural networks, it has become possible to assist different professionals with their tasks. This project aimed at training convolutional neural network on the dataset containing thousands of chest x-ray images for finding chest abnormalities. DenseNet121 was selected for training. Chexpert, a large chest radiograph dataset from Stanford was acquired for training. The trained model on this dataset optimizes the loss function and reports the test accuracy of 81% with dataset having unbalanced classes but with poor f1 score. So, the model was trained again on balanced classes and f1 score was significantly improved with test accuracy of 90%.
​​Project Title Micro Inverter with Lithium Ion Battery
​Group Members ​Muhammad Danial Khilji

Furqan Ahmed Chishti

Fidaullah Noonari

​​Project Supervisor(s) ​​Dr Usman Ali

Dr Aqib Pervwaiz

​Project Abstract ​There is an immense need of a small size of inverter globally. Nowadays an inverter is an  important  element  for  use  as  a  back-up  power  supply  and  it  is  also  an  essential  part  in  generating  off-grid  power  through  solar  panels.  Inverters available in the  market  are considerably big which takes up a lot of space. Most of the commercial inverters available in Pakistan are simply PWM inverters. These inverters have high harmonics and are bulky to move around. Furthermore, they use car batteries as their battery which are dangerous to place in open home environment. These inverters are not only enormous in size but also inefficient for the office equipment use. Most importantly they don’t have an ability to control abrupt power surges.Our main objective was to successfully reduce the size of the inverter while maintaining the efficiency of 220V and 150W which is intentionally designed to work for IT equipment. An inverter is used to convert DC voltage from the battery to AC voltage of the main supply. It also charges up the battery when not in use. Our inverter also filters out the abrupt power surges from the main supply power. This inverter was specifically designed as the universal supply. Its main use will be as an office equipment back-up supply, therefore requires fine sine wave at all time. The technique used is push-pull for the buck and boost as well. We used the Lithium Ion  batteries  instead  of  conventional  chemical  batteries  which  takes  a  lot  of  room  space. Lithium Ion batteries are not only small in size, they also have a greater life cycle with very low or no maintenance at all.
​​Project Title Visual Simultaneous Localisation and Mapping (SLAM) for Indoor Robot Navigation
​Group Members ​Muhammad Hamza Zaid

Israr Zulfiqar

Samama Moud

​​Project Supervisor(s) ​​Dr Shahzor Ahmad
​Project Abstract ​It is an Image Processing/ Computer Vision project whose main objective is to track feature points from continuous frames and extract there movement (translational and rotational).

This project has basically two parts i.e. hardware (control) part and software (mapping) part.

Application of this project is in GPS-denied environments. It can be utilized in areas where humans cannot function for elongated hours, or in applications like virtual/ augmented reality (VR/AR).

​​Project Title 3D Bounding Box Detection of Vehicles
​Group Members ​Ibrar Ahmed

Muneeb Ur Rehman

​​Project Supervisor(s) ​​Dr Shahzor Ahmad
​Project Abstract ​Pakistan has suffered a lot due to traffic accidents and terrorism. Although we have cameras installed all over the public places in our major cities such as Lahore, Karachi, Islamabad, one of the main reason behind the failure of the system is that it depends a lot on the observing capability of the camera operator and human error is a very common thing. An automated surveillance system is thus required to observe and ensure smooth traffic flow.

This project intends to automatically detect any vehicle in a traffic flow and will label it according to its type such as bus, car, van, etc.  In  addition  to  that,  our  system  will  also  be  able  to  detect a 3D bounding box around that detected and classified vehicle.  This will reduce human error in analytics application, thus avoiding incidents from happening.

​​Project Title Sensor Fusion for Intelligent Road Transportation
​Group Members ​Ahmad

Ansub Zia Taimuri

​​Project Supervisor(s) ​​Dr Shahzor Ahmad
​Project Abstract ​Intelligent Transportation Systems is a key area of research for the purpose of improving traffic flow and counter dangers to common lives. This project focuses on out of the box solutions for better management of traffic on Pakistani roads and provide more reliable solution for e-tolling applications. We make use of 2D LiDAR in conjunction with an optical camera to fuse depth and image information. The depth information is well-aligned with an image row. This data can then be used for the purpose of vehicle profiling and speed estimation.
​​Project Title Hybrid Solar Inverter
​Group Members ​Abdullah Shehzad

Hamza Imran

Khalid Hussain

​​Project Supervisor(s) ​​Dr  Usman Ali
​Project Abstract Our objective was to propose a multi-input DC-AC inverter for hybrid PV and Grid powered system which consists of a multi-input DC-DC fly-back converter, a three phase full-bridge DC-AC inverter and a Variable-frequency drive system in order to produce a constant output voltage from the different energy sources which was being used to control the speed of an induction motor. The initial application and aim of the project was to use this system to control the speed of the compressor motor of an Air-conditioning unit, however it can be modified for various other applications. The entire model was simulated on the MATLAB software, which showed successful results for the implementation of the system.