AI Object Detection for Visually Impaired: Progress Report
Making strides in aiding the visually impaired through AI object detection, with a focus on reducing lighting distortion. Researching, implementing, and overcoming challenges in the project, including exploring YOLO V5 algorithms, mobile app development, and utilizing phone sensors for enhanced data collection.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
Progress report Helping the visually impaired using AI object detection while reducing lighting distortion
2 Object Detection Algorithms We researched and compared multiple algorithms YOLO V5
3 Implementation We implemented the algorithm together Made a list of objects we want to detect Came up with ideas to improve the algorithm Different algorithms depending on light
4 Issues YOLO is only compatible with Nvidia GPU s Object training can be done via CPU but it s slow Swapped out GPU s and got it working until... GPU DIED and now we re waiting on a replacement We haven t heard from Apple yet
5 Mobile implementation Began developing an Android app for testing while we wait for Apple.
6 BIG CONCEPT Using the phones sensors to bring in more data Algorithm to estimate how far an object is Algorithm to estimate the size of an object
7 Weekly Planner Names SUNDAY MONDAY TUESDAY WEDNESDAY THURSDAY FRIDAY SATURDAY Work Work Jose Work --- --- Work --- Frankie Work --- --- --- Work Work Work Eduardo --- --- Work Work --- Work Work Enrique --- Work --- --- Work Work ---
8 Project Progress Recap Week 1 Week 2 Week 3 Research and understand how object detection algorithm works Compared object detection algorithms based on the best performance in a real-world environment Best object detection decided based on YOLO(You Only Look Once) Setup Github and Git for source control Install Microsoft Visual Studio Install CMake for Object Detection Install Cuda Installed Opencv Configured CMake for OpenCV Issues with getting everything to work but was an OS problem Resolved OS issues by updating OS Starting Individual work such as researching different algorithms Looked at different objects YOLOV5 can detect Week 4 Week 5 Week 6 Trouble implementing and removing objects that can be detected Figure out what each portion of the YOLOV5 does Finalized list of objects that YOLOV5 can detect Resolved list of objects that YOLOV5 can detect Start researching IOS mobile development Research Swift programming language Improved structure of YOLOV5 algorithm for easier development Resolved issues with YoloV5 not running as intended Training YOLOV5 in real-time Implementing YOLOV5 in Mobile Development Using Android as a test bed while we wait for IOS
