Category: Takshsheel’s Status Reports

This week I worked on the following tasks:

• Attended class and reviewed final presentations for the remainder of the team’s.
• One out of the 2 counter setups and algorithms was not compatible with a raspberry pi with the camera system, so made it compatible by changing camera parameters and system paths to the camera as well.

This week I’ve not put in nearly enough effort into the class and the project since I focused my attention on the midterms/finals that I had to take 3 days in a row, however, currently, my schedule allows me to put in all the time that I’ve missed out on in the time being, in the coming week. Hopefully I can put in a justifiable and solid amount of time and effort that is expected for the project.

In terms of schedule, I’m still concerned about the porting of the counter code onto our integrated system, however, in the event something goes wrong, I don’t think it should be incredibly long to fix. We should be okay for team schedule in terms of finishing our product for the demo.

For the next week, I hope to have the following deliverables:

• Final poster
• Final decisionmo
• Fully integrated system with counter code
• Final report
• Final demo

This week, I worked on the following tasks:

• Built a second counter program that instead of telling us how much traffic is in and out of a section, gives us information about how many people are present in the aisle.
• Tested the implementation for various distances, varied number of people, and also checked for false positives.

In terms of schedule, from a preliminary standpoint, things are looking like they should be okay, the background subtraction and detection integration is underway, and provided things don’t catastrophically fall apart, we should be okay prior to the final demo. However, there’s also the risk of creating code that might not work with the other subsystems, and for counters, the integration hasn’t yet been tried mainly due to lack of speed in creating the subsystem on my part, but now that is done, hopefully, we can integrate that in as well.

For next week, I hope to have completed the following tasks.

• Integrate both counters for different shelf and camera setups and make a decision on which counter is more accurate and has lesser latency.
• Work on the final presentation slides prior to the presentations in the coming week.

This week, I worked on the following for our capstone project.

• Performed an interim demo for the background subtraction system which shall be used to detect people walking in and out of frame. Worked on and mentioned a foot traffic counter during the demo, which was incomplete and buggy, which I’ve worked on to fix and as of right now, it can be inaccurate at times, but doesn’t immediately crash like it was previously.
• Besides the demo and the counter, I drew a design that I’d like to discuss with my teammates during our meeting slot on Monday, although not time-consuming like the debugging for the counter, it is relevant as it could make a last-minute design improvement.
• Looked into web sockets to transfer data around, since we’d like to use our raspberry pi to run this script and transfer data to our local machine, so, familiarizing myself with the process felt necessary.

In terms of personal progress, I feel like I’ve finally caught back up to where I have wanted to be since the past 2 weeks, and have a good feeling for the project itself.

By next week, I’d like for our team to have made significant progress on the integration of our system, as well as have some physical structure for our system. To make that happen, I’d like to help manufacture the shelves if needed, and set up the camera based off the present/new design that we shall discuss on Monday.

This week I worked on the following tasks:

• Met with our team to discuss the integration framework and subsystems performance and requirements for the same.
• Continued to fix the buggy counter from last week. Close to done fixing, but not just there yet.
• Built a testing framework for different cameras and videos and have tested at various distances and speeds of movement with various number of people for my counter.

My progress has been behind since last week and the buggy implementation I’ve got is still not fixed, so this is a concern and risk I’m aware of. From an integration perspective, we need a lot of work done as a team and from me, and through carnival break, I have to be working and getting a fix for my counter program.

For next week, personally I would like to have a deliverable for the counter, which was supposed to be done last week, and from a team perspective, a testable integrated software for our MVP idea.

This week, in addition to the common team goals, I worked on the following:

• I worked on getting a people counter working with the use of contours along with background subtraction in openCV.
• I also discussed with my teammates about ethical considerations that popped up in my mind after our discussion on monday, particularly to do with how our product could be used, and how much of that should be our responsibility, whether or not that is on us to fix, or is it up to the consumer of our product.

1. In terms of an issue or risk I found, it has taken me longer than I have expected to fix a bug that I have found in my implementation of contouring, and even though I spent a fair amount of time with it, I’m currently not able to understand the bug. Therefore, I’ve decided to look beyond for outside help from faculty members in CMU for advice on how I might either do this differently, or fixing the issue I have found.

This bug I’ve mentioned here definitely puts me behind schedule. I was hoping to have the counter completed by this weekend but I’m currently still stuck with it. Luckily, for our MVP idea, we just need motion detection which is working. However, this is something I was really looking forward to having in our project, so this setback is rather detrimental.

By next week, I hope to have completed the counter, as well as help with the integration process of our wireless communication system.

Through this week, most of my time was spent researching background reduction for openCV, working with our team during class time, to discuss different frameworks for the webapp network as well as different background subtraction algorithms. 

With this time through research, I’ve found there to be a few different algorithms for background subtraction, which is an important step for our openCV processing. The 2 primary algorithms that I believe we’d like to use for our project for background subtraction would be one of BackgroundSubtractorCNT or BackgroundSubtractorMOG2 since these algorithms were designed for detection of foreground motion along with being able to differentiate between movement and their shadows moving. I’m not sure which detection algorithm would be the fastest and accurate enough since our goal is just detection of some motion to begin with. So, I think we shall try to use BackgroundSubtractorMOG2 since I was able to find better documentation with public access for the same, and test if we would need a better algorithm to meet our goals. Should that be the case, I’d like to have a working implementation to test soon.

Beyond that, in terms of intangible time spent, I worked on my presentation delivery since it is an area I struggle with. I don’t have any way to show this at the moment, but I hope to show it through the design review presentation that shall be next week. I spent about 2 hours working on learning our design well as well as practicing my delivery for random presentations. I don’t know if it was worth it, but I needed this time to do it well.

In total, including class time and research time, I spent about 10 hours on capstone this week. It needed to be more, but I had an emergency situation take up more of my time. This situation put me behind on my schedule, but now that it has passed, I plan on using more of that time into the project and have tangible deliverable files next week.

 

For next week I plan to have a deliverable openCV background reduction process, and hopefully tests for different algorithms integrated into it too. Completion and a good presentation of the design review is also something that needs to be done next week and I hope to do well there as well.

 

 

What I researched/worked on this week:

• Researched initial openCV algorithms to use for detection of people in a stationary environment.
• Looked in depth into background subtraction and understood the different steps involved in the algorithm. 
• Preliminary research into keeping count and detecting multiple objects along with background reduction. 
• Research into a possible changing background vs not having our items not be in the background. Research to reason about would we want to use 2 cameras for people vs objects vs 1 camera with 2 settings. (2 cameras is expensive vs 1 camera has more algorithmic complexity) 
• Varying background possibilities due to objects being taken off the shelves one at a time, many at a time etc. 

 

I feel like as a team we are still on track even though post our proposal which was very fleshed out and detailed for which a lot of preliminary research was already done, this week due to the proposals and peer reviewing during the 2 class times which were previously also used for research, but we have made progress with some of the details. On a personal note I think I’m a little behind on the outcomes of the research I wanted to achieve. Eg: Answers to some of the questions that I currently have preliminary research for. To catch up to my perceived readiness, I’d like to ask for advice through our faculty advisor and the TAs, and perform further research as well. 

For next week, I’d like to finish my research and be able to provide a first draft (albeit buggy) of some background subtraction code. So we can check what is visible and what isn’t. I’d also like to finalize what approach I’d like to take with regards to SIFT vs OBS vs SURF etc as well.