codefundo-idea

1. We are planning to build a model that can play a role in detection of human presence.

2. We can use computer vision to exploit this semi-rigid structure and extract features to quantify the human body.These features can be passed on to machine learning models that when trained can be used to detect and track humans in images and video streams. This is especially useful for the task of pedestrian detection, which is the topic we’ll be talking about. As humans can be differentiated from other objects on certain recognition basis such as facial, shape, etc.

3. Rescue people or trained dogs cannot easily enter into some places of the disaster-affected area. This may lead to loss of life of the victim or fatal injuries that paralyses them for the rest of their life which could have been saved if help was provided at the right time. According to the field of Urban Search and Rescue (USAR), the probability of saving a victim is high within the first 48 hours of the rescue operation, after that, the probability becomes nearly zero. Rescue operation team puts in a lot of effort to reach out to every person, nearly buried in the debris, but they may not always be successful.

4.The (x, y)-coordinates associated with landmarks in body and how these landmarks can be mapped to specific regions of the body.Then we will extract the regions of the body using these datasets or we can use the human. 5. We will write a code on python to detect human bodies, plus machine learning and deep learning.OpenCV to accelerate the use of machine perception with a pre-trained HOG + Linear SVM model that can be used to perform pedestrian detection in images.