Hi there. Welcome to our IOT group project group uh 45. And we designed a security camera which detects humans. So the title of a project is object detection security camera and it does fall into the domain of security. The IOT we developed uh is a security camera. We used the camera module from Raspberry Pi. We did take inspiration from surveillance cameras, home cameras, home security that are used by governments companies, personal use, et cetera. Our camera, when it sees an object, it tries to figure out if it is a person or not. If it is, then it draws an outline on the object and also displays a percentage I think is right. If they, if the threshold is passed, then the camera will detect that it is a person. We use Python with a computer vision library to achieve this, it streams the camera output to a website for which we use flask. Our motive was to create a security camera that displays its output somewhere and we use the web because it'd be easy to implement and wouldn't require us to design any physical equipment. And on the whole, our product fulfills the role of a security camera as it outputs itself to our website and informs the us if it detects a person. Originally, our IOT project detected all objects from a library listed here under Cocoa names. All of these objects were detectable if it pass a certain threshold. But for our project, we only wanted to detect people slash humans. So we were able to do this by setting the objects, the only person. So what this does is that whatever object is shown on the screen, if of whatever objects is shown on the screen, if a person is there, it will only highlight that person. And this is based on a feature that we couldn't use as the Raspberry Pi only has passive cooling and having all objects detected just kept it way too hot. So for the purposes of our project, we kept it to only humans. And this IOT does in fact detect, detect multiple people. This does cause the frame rate of the camera to be a lot lower than usual. We were not able to achieve at least 30 frames because it's just too stress heavy. And uh we decided just to keep it as plain as possible and as efficient as possible not to cause any issues in the future. Um When it comes to similarities to our product uh in the market today, there are products that exist which are similar to the security camera that we developed. A notable example is the NNNCMIQ indoor similar to our product. The nest cam also has advanced computer vision capabilities. The NSCA MA I uses algorithms in order to detect and identify people and then also has the ability to send an alert to user smartphone. When a person is detected in front of the camera, it will outline the shape of the detected person like ours and will then also provide confidence score like our threshold which through the help of computer vision determines the likelihood of accuracy of the detection, which is very similar to ours. There is the option for continuous stream to the app which allows for remote viewing of a human's home by the user which there is more information on their website. Another good example is also the Arlo Ultra two, which is a wireless security camera system with advanced motion detection features and four KHDR video. It may not provide a clear outline of items as identified or objects or people, but it does provide customizable motion zones and notifications for certain activities such as human detection. It also sends live video to the Arlo app so that it can be viewed and monitored remotely more information on their website. Our code does in fact use flash server so it's a local host. It also uses open CV to achieve the detection. And this code as I mentioned is taken not uh it isn't entirely developed. We did take some inspiration from a youtuber that did a tutorial on this. Um, but their code, as I said previously was purely on object detection. This had to be changed for only people. So, yeah.