By Katie Knorr

Four student teams from the Master’s in Professional Computer Science Program (MPCS) at Simon Fraser University were awarded the School of Computing Science Innovation Prize. The award was established in 2019 by parents Yi Sun and Wen Min Dai in memory of their son Tiger Sun, who was an undergraduate student at the School of Computing Science.

The family’s generous funding supports graduate students who develop innovative computer science solutions. MPCS instructors chose the competing teams based on the overall quality of their projects. The teams then presented their work to the MPCS advisory council, comprised of over 20 senior professionals specializing in data engineering, visual computing or cybersecurity.

The advisory board considered three criteria in its evaluation: innovation, potential impact and quality of implementation. After careful deliberation, the following teams were awarded $2,500 each for their projects.

GCEngine: A Cheat Engine to Scan and Manipulate Memory Regions of Video Games

Mohammad Reza Bagheri, Keith Lo, Wilson Oen

With the increasing popularity of eSports, cheating is also on the rise. To guarantee fair gameplay in a competition, game creators invest in anti-cheat engines. But if we want to create a workable anti-cheat engine, we need to first understand how cheating in a game works. By utilizing the Windows API, we created a gaming cheat engine tool that automatically searches for Process ID given a game window name and can scan and manipulate game memory with a specific value. In addition, the tool can locate and modify unknown values of game items such as health bars or icons. Lastly, we demonstrate how to bypass ASLR and manipulate the specific game item value with the help of pointers.

Disaster Damage Assessment from Satellite Imagery

Navjot Kaur

Much of life-saving humanitarian aid and disaster response work is guided by post-disaster damage assessments that are obtained through analysis of satellite images of an affected area. Most recent work in this field uses either a Siamese network or a difference module in the spatial domain to assess damage, and applies attention mechanisms on the temporal features independently instead of their difference. In this project, we propose a novel transformer-based network for damage assessment. This proposed network achieves state-of-the-art performance on a large-scale disaster damage dataset for building localization and damage classification.

A Computer Vision Pipeline to Match Lost and Found Dogs

Anant Sunilam Awasthy, Rishabh Kaushal, Karthik Srinatha, Aidan Vickars

In this project we developed an Android application where users can submit an image of their lost dog, and the most similar lost dogs that have been found will be shown. Similarly, users that find a lost dog will submit an image, and the most similar dogs that have been lost will be returned. The app uses three convolutional neural networks that process visual input, analyze dog breeds, and eventually calculate a similarity score between two images to identify if there is a match.

The Waste Sorting Bin Conundrum: Image-Based Waste Sorting

Anirban Banerjee, Siddhartha Haldar, Tanmay Jain, Ayush Raina

Proper waste sorting is critical for recycling. Given the large and varied amount of waste generated by the typical household, it can sometimes be difficult to know how to properly dispose of any given waste item. With our project, we aimed to create a web app to easily, efficiently, and automatically identify and sort waste items by using neural networks to detect and classify waste items in images.

For more information about these projects, visit our Project Showcase page.