Unusual Human Activity in Real Time Environment
Our system proposed is consisted of following parts Research and Literature review Training Testing and Validations In the first part, the system is trained using training technique and algorithms. Afterwards this trained model distinguishes the susp
2025-06-28 16:36:31 - Adil Khan
Unusual Human Activity in Real Time Environment
Project Area of Specialization Artificial IntelligenceProject Summary- Due to exponential increase in crime rate, surveillance systems are being put up in malls, stations, schools, airports etc.
- With the videos being captured 24x7 from these cameras, it is difficult to manually monitor them to detect suspicious activities. So, there is a great demand for intelligent surveillance system.
- The proposed work automatically detects multiple suspicious activities in videos.
- Detecting the suspicious activities from videos is very challenging due to environment conditions, illumination conditions and working status of capturing cameras.
- Propose an automated system for efficient unusual human activities detection in real-time.
- Make this useful for smart city environment.
- Multiple suspicious detection in real-time.
- Make this useful for outdoor and indoor environment.
Our system proposed is consisted of following parts
- Research and Literature review
- Training
- Testing and Validations
In the first part, the system is trained using training technique and algorithms. Afterwards this trained model distinguishes the suspicious activity from the given video. After that it will make a decision that this is activity suspicious or any other. On the basis of that decision and display it on screen and turns on the alarm.
Benefits of the ProjectThis project provide the following benefits
- Reduces crime rate in malls, stations, schools, airports etc.
- Effective Surveillance can help prevent shoplifting & theft.
- An increased Sense of Security.
- Actually what we have done and planned to submitt on the given time is that first we have collect the data set which we are made.
- Than we use pre-trained model to train our imagesĀ on the Machine.
- After training the images then we move toward the videos and check the accuracy. The accuraccy must be above 80%.
- Then we made graphical user interface(GUI).
| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 34300 | |||
| IP Camera | Equipment | 2 | 3500 | 7000 |
| Standee for open Hous | Miscellaneous | 1 | 750 | 750 |
| Poster of FYP for Standee | Miscellaneous | 1 | 300 | 300 |
| Project Report | Miscellaneous | 3 | 750 | 2250 |
| Additional GPU | Equipment | 1 | 18000 | 18000 |
| Paper Publication Fee | Miscellaneous | 1 | 6000 | 6000 |