Category: Team Status Reports

This week, everyone met up at Gates to film the demo video! We got really good use case clips of our project (no mask, mask, improper mask, proper temperature, failed temperature). We also were able to take some fancy photos of our device and made it look professional. We will be incorporating these photos in our report and presentation. We also all met up to finish up the slides for the presentation on Monday, and have given it to Cindy for feedback. We will be reading over her comments and fixing it today The device works really well and we have tested it against our metrics, which meets our expectations.

Everything is on track for our project and we are so happy that everything is working as expected! We will be doing the final report and demo video in the upcoming days.

 

Tasks Accomplished

• Final Enclosure:

We cut out the enclosure using the laser cutter and assembled it to see what our final product looks like. Here are the images of the model and the actual printed product.

 

• Fixed buggy RFID scanner behavior:

We used to have a bug where a byte gets lost in transmission when the Nucleo board sends the unique ID to the Nano. We were able to fix this on Nucleo’s side by always sending two sets of ID in case one of the bytes get lost. The nano is now able to detect if some bytes were lost and recover those bytes by reading the duplicated string.

• Connected the red/green LED for RFID:

We wired the red and green LED to blink when invalid and valid ID’s are scanned, respectively. We also had to adjust the resistor values to make sure the green LED wasn’t blinking when the system is off, as the green LED has a lower turn-on threshold voltage.

• Optimized Facial Detection FrameRate:

Initially, we were obtaining an fps of ~4. Now, we are achieving an fps of ~7.

• Integration:

We integrated the logic for scanning RFID, flashing LED, measuring temperature, detecting a face, and sending the information to the cloud. We had to handle some edge cases, such as when a user moves away during the temperature measurement. Now our system has a fully integrated functionality.

To-Do:

• Create a mock database functionality for users to be able to import their own RFID database and check against the scanned ID.
• Add code to display temperature results on the screen.
• IoT app development (front-end & back-end).
• Organize the content inside our enclosure and paint it!

 

This week, we all went to Techspark to meet with someone who could help us CAD an enclosure for our various components. We got measurements and drew out a design, and we have a Techspark student worker (Brian Lee) who will be aiding us in CADing the model for it. The picture of our vision is attached. Tomorrow, all 3 of us will be meeting together to get the LED working and a basic IOT framework up and running.

We are on schedule with our various components, and are staying on track with our goals.

This week we worked on hardware integration of the Nucleo and Jetson Nano for our Demo. We also met on Thursday with TechSpark to discuss how to make an enclosing for our hardware. We thought about just getting different enclosing for each component, but we feel that having everything in one thing would be best. We also made a purchase of a display monitor so that it can be embedded within our enclosing and be used as the display for user interface. The most significant risks that could jeopardize the success of the project is the accuracy of the temperature sensor since we don’t have a good way of testing human subjects with fevers. Although we did and will be testing various temperatures of objects to meet our past stated metrics. We changed our cloud implementation to be Python based instead of using Node.js since we are more familiar with Python even though there are more IOT stack examples using Node.js

This week we spent a lot of time debugging our system in preparation for the demo. During the process of getting the IR sensor to work with the Nano, we noticed that the Nano’s I2C bus has some issues detecting connections from the sensor and the Nucleo board as well. We were able to confirm that the Nano is able to read bytes from the sensor’s I2C connection. However, we’re still in the process of debugging the I2C connection between the Nano and the Nucleo board. If we are unable to resolve this issue, we will consider using an alternative communication protocol that is supported by the Nano and the board such as UART or SPI.

After figuring out the I2C connection between the Nano and the IR sensor, we were able to execute a program that reads and outputs temperature data from the IR sensor every 0.5 seconds. We can simply integrate this script with the other script that was sending hard-coded data to the cloud gateway to finish up the temperature sensing functionality. Here’s a quick video of the temperature sensor working:

We also modified our work schedule. We noticed that the complexity of deploying the face/mask detection algorithm on the Nano is a lot more than we expected. So Iris and Minji will work on Nano’s face/mask detection algorithm and temperature sensing process together. After those functionalities are up and running, we will implement the web application together toward the second half of the remaining weeks. We came to this conclusion because we decided that our priority should be on fully implementing the system’s functionalities.

The most significant risks right now is if the facial detection algorithm is too laggy. It’s mentioned more in Iris’s status report, but we were planning on taking advantage of pre trained models that boast high accuracy numbers, but we found out that its very computation heavy and makes the Jetson Nano run very slowly. We are pivoting towards a more Haar classifier approach, but we are getting pretty low accuracy numbers so we will need to work on that more.

No changes have been made to the existing design from last week. We have updated our Gantt chart according to our progress made so far, to better reflect our goals for the demo on 11/9. All the slack time we added was really helpful because we are still fairly on track with our final goals.

After submitting the design review presentation, we got back to working on our project this week. Jiamin found out that the current NFC02 board we purchased for processing RFID tags doesn’t actually achieve the functionalities necessary for our project. This has posed a little bit of delay in our timeline, but we are hoping to be back on schedule once the new board, NFC05, arrives.

The rest of the group members continued to work on interfacing with the Jetson Nano to receive a video stream from the Raspberry Pi camera module and setting up the IoT application. On the Nano and software side, our team is on schedule and will continue to work more on it next week. In the upcoming weeks, the two of us are planning on working together to make work on the Nano to expedite the process of receiving and processing data from the two input sources, the IR sensor and camera. This will help us better overcome some of the bottlenecks in our progress which mostly consists of learning how to interact with the Nano and send data to the cloud from the Nano.

This week we worked on the design review document deliverable that is due Monday. The most significant risk right now is if we can’t read the tag UIDs from the NFC expansion board. Jiamin is going to do more research to see if libraries are available or if a new board should be purchased. The new board should work if purchased since our Nucleo board model has been tested and is a driver that is included in the demo, unlike the NFC02 we have right now. More details are mentioned in Jiamin’s status report. Everything on the software side has been going according to schedule. No changes have been made to the existing design of the system since we just finalized some of our components from working on the design review presentation and document. We did submit some more purchase requests for type 5 tags.

This week has been mostly doing the design report and presentation slides. We have been slowly figuring out how each part of our project will connect to each other and ordering the new thermal sensor and microSD card that we need.

Our most significant risk right now is having the microcontroller board being able to communicate with the Jetson. There are some driver problems right now that Jiamin is debugging, and hopefully we can get that resolved in the next week. Thankfully, she will be coming back to Pittsburgh next Saturday so we can all start working together in person, which will make work flow smoother.

No other changes have been made to the design thus far.

The most significant risks that could jeopardize the success of the project is if we fail to integrate all of our hardware components. We plan on testing out the individual hardware components prior to connecting everything together. A lot of research has been done to ensure that components are compatible. More research will be done if needed. In addition, we have to ensure that the Nucleo board will be able to turn the Jetson on/off since that is the major target in our low power goal. Jiamin did some research into this topic, but the ideas will have to be tested out once she comes back to Pittsburgh in 2 weeks. If we are unable to use the Nucleo board to wake the Jetson, then we might have to consider using some sort of physical momentary switch to activate the signal. 

After the proposal presentation we realized that the 2 degrees of error for the temperature reading from the FLIR IR camera is not good enough. We looked into cameras that could have better accuracy, but those were way out of our budget. From the TA’s suggestions, we decided that a sensor might be a better option. We decided on a sensor from the MLX90614 series. However, most sensors can only measure from a very short distance (2-5 cm). We did some more research and found that specifically the MLX90614-DCI has an accuracy of 0.5 degree of error for room temperature and 0.2 degree of error for human body temperature. It can also detect from a distance 50 cm, about 20 inches. The FLIR IR was originally around $200 and now we no longer need to buy a separate board to interface the camera with the Jetson. The sensor we chose is only $60, providing a little more breathing room in our $600 budget. 

The schedule has not been changed. Everything is still happening according to the initial Gantt chart created for the proposal presentation.