Download Project Document/Synopsis
Detecting human beings accurately is very crucial for diverse application areas including abnormal event detection, congestion analysis, person identification, and gender classification. The object classification methods could be divided into three categories: shape-based, motion-based and texture-based.
Human detection is a difficult task from a machine vision perspective as it is influenced by a wide range of possible appearances due to changing articulated pose, clothing, lighting and background, but prior knowledge of these limitations can improve the detection performance. This system implements algorithms such as the HOG Descriptor algorithm and Support Vector Machine algorithm.
In this system, the user has to upload an image or video for detecting humans. To detect humans in real-time, a webcam can be used. Then, the number of people counted will be displayed while detecting.
The front-end involves Html, CSS, and JavaScript and the back-end involves Python. Here, the IDE used is Android Studio. The framework used is Django and the database is MySQL.
Here, we focus on detecting humans and do not consider recognition of their activities.
Advantages
- It’s easy to maintain.
- It’s user-friendly.
- Humans can be detected from any given image, video or from webcam.