For this week, I focused on figuring out how to detect resistors on a breadboard and get their locations as accurately and efficiently as possible. I considered standard deep learning approaches that would find bounding boxes around resistors it found in a given image. The three alternatives for\u00a0 this were<\/p>\n
With both of these options as back ups, due to the constrained nature of the problem, I believe I can use normal image processing techniques from the openCV library to accurately detect the resistor locations. I anticipate that once I get a dataset of images of resistors on a breadboard from a bird’s eye view, the image processing approach will suffice. If it does not, I will get started on trying out the YOLO algorithm.<\/p>\n
Also, I am working on setting up the development environment on the Raspberry pi, making sure the camera we got it working, and figuring out the quality of images the camera takes.<\/p>\n","protected":false},"excerpt":{"rendered":"
For this week, I focused on figuring out how to detect resistors on a breadboard and get their locations as accurately and efficiently as possible. I considered standard deep learning approaches that would find bounding boxes around resistors it found in a given image. The three alternatives for\u00a0 this were Faster RCNN –> the most accurate but slow and takes up memory YOLO –> much faster and lightweight alternative but accuracy is lower With both of these options as back…<\/p>\n