Home
Project Motivation
Hospitals and nursing homes are experiencing a simultaneous increase in injuries due to falls and a decrease in qualified staff hires. In countries like England, falls account for 32.3% of reported patient safety incidents in hospitals. Solving the problem involves implementing preventative measures that will minimize incidents leading to injury without necessitating a larger staff. It is difficult to stop falls from ever occurring, but decreasing the number of injuries would lessen the dilemma.
Proposed Product
The fall detection system employed in this project deals with both of these problems and can be implemented on a large-scale level. During hours when there is a smaller on-call staff, such as at night, the system activates itself and begins to detect motion in a room. It uses a strategically positioned camera to record any movement. A feed of the images is continuously transmitted to a computer, where the data is analyzed and processed to determine if a fall has occurred and whether it necessitates immediate medical assistance. The computer can differentiate between sudden movements and motion that is actually a fall. If help is necessary, an alarm or alert is sent to a station in order to direct staff to action. Read more about the Project in the project tab.
Project
Problem
Falls are a leading cause of accidental death in the US.There are 1.8 million emergency room visits and over 400,000 bed-fall related hospital admissions that involve patients over the age of 65. If the nursing staff could be informed of this potential fall situation, the patient could get care in time.
Competition
There are existing solutions like a wearable button that will send out an alert when
a fall is detected. These systems use accelerometers and push buttons to detect how fast
the person is falling and is prone to false positives due to the daily activities of the patient
in a home environment. This solution depends on the patient’s capability and
willingness to raise alarm.
One of the products in the market using this technique is iLife™
Solution
Computer vision systems offer a new automatic solution to overcome these limitations. Another advantage of such a system is that a camera gives more information on the motion of a person and his/her actions than an accelerometer. Thus, we can imagine a computer vision system providing information on falls, but also, checking some daily behaviors (medication intake, meal and sleep time and duration, etc.).We aim to use Advanced Signal Processing techniques to achieve this goal and successfully detect falls.
Deliverables
Technical Review Papers
- Web Camera Image Detection - Abhishek Chandrasekhar (PDF) (DOC)
- Video/Image Recognition Software - Akshay Patel (PDF) (DOC)
- Applications of Fall Detection - Hahnming Lee (PDF) (DOC)
- Fall Detection Algorithms - Nicholas Chan (PDF) (DOC)
Project Proposal
Draft Summaries
PDR Presentation
Final Deliverables
Status
This section contains an archive of the weekly reports required for class:
- Week One
- Week Two
- Week Three
- Week Four
- Week Five
- Week Six
- Week Seven
- Week Eight
- Week Nine
- Spring Break
- Week Eleven
- Week Twelve
- Week Thirteen
- Week Fourteen
- Week Fifteen
View Gantt Chart
Media
Photos and Videos coming soon!!
Team
We are a group of motivated individuals at the Georgia Tech ECE department who are working towards making a solution to help the elderly in countless hospitals and healthcare facilities across the world. Our mentor Dr. Arthur Koblasz is helping us make this project possible
Our team consists of the following members:
- Abhishek Chandrasekhar : abhishek@gatech.edu
- Akshay Patel - Webmaster : akshayp@gatech.edu
- Hahnming Lee : hahnming.lee@gatech.edu
- Nicholas Chan - Team Leader: channy@gatech.edu
Abhishek Chandrasekhar Akshay Patel Hahnming Lee Nicholas Chan
Matlab Master Web Wizard Writing Guru DSP Factotum