Browsed by
Author: arkar1

Arka’s Status Update for 04/19

Arka’s Status Update for 04/19

This week, I worked mainly on edge detection and color extraction. Both approaches were changed from initial plan: Classic edge detection methods and built in open cv libraries were not providing proper performance regardless of how well the image was taken and preprocessed. Switched to an approach which detects color changes in a linear scan across resistor body. This method is working much better, though is dependent on quality of color classification Color classification was originally going to be performed…

Read More Read More

Arka’s Status Update for 3/29

Arka’s Status Update for 3/29

Past Week To Do: Embedded: Reset up Rpi Computer Vision: Work on edge detection to find color bands on each resistor Work Log: Embedded: Need to place order for the right cable to connect Rpi to my computer Computer Vision: Working on playing with different edge detection techniques to get best result at color band detection Next Week: Embedded: Set up Rpi and get back to the point pre-Corona Crisis Computer Vision: Figure out a decent edge detection technique that…

Read More Read More

Arka’s Status Update for 03/22

Arka’s Status Update for 03/22

Well, as we all know, this week has been crazy due to the outbreak of COVID-19 as a global pandemic. In order to do my part in preventing a worse spread of this disease, after returning from Spring Break, I spent most of my time preparing for a 2 week self-quarantine. After receiving guidance from the course staff as to how to move forward, we had multiple team discussions in which we rescoped the project to accommodate remote work with…

Read More Read More

Arka’s Status Update for 02/29

Arka’s Status Update for 02/29

Past Week To Do: Embedded: Set up ssh capabilities on Rpi Set up image capture pipeline on Rpi Test and time object detection code on Rpi Computer Vision: Begin working on resistor classification Take output of object detection Work on cropping and rotating each subimage Get to at least color space transformation in classification pipeline Work Log: Embedded: Set up ssh to rpi Set up camera connection to rpi Set up python script to display preview and prompt me to…

Read More Read More

Arka’s Status Update for 02/22

Arka’s Status Update for 02/22

This week, I finished working on the object detection pipeline. Last week, I was struggling to properly filter our the background resistor board. I figured out the appropriate HSV values to filter it out, which should stay the same under these lighting conditions across images. I used CLAHE to reduce the effect of reflections of the resistors, morphological closing to close any holes that appeared in the resistors, and contouring to find and draw edges around the resistors. I cleaned…

Read More Read More

Arka’s Status Update for 02/15

Arka’s Status Update for 02/15

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  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…

Read More Read More