Image Processing

Wireless video sensor networks which integrate image processing, computer vision and networking tasks will help develop a new, exciting and challenging scientific research area at the intersection of video and network technologies. One of the major outcomes of the research apart from the technology transfer to the industry is the setting up of an outdoor visual sensor network laboratory. Such a facility will enable ISSNIP to be at the forefront of visual sensor network research.


A few applications where the developed common framework could be used are as follows:          

A1.Surveillance: This is one of the obvious and most widely used applications of a camera network. These networks are used in a variety of ways such as tracking a person, suspicious activities, left luggage detection and unauthorised access. If a high definition camera is used, the system can be used for specific recognition as well added to the event detection mentioned above.

A2.Healthcare: This is a grand application required for aging nations. Lots of money is being spent on carers of the elderly. One potential scenario would be detection of visual gait of the subject in order to assess the risk of falling. Another scenario is to use heterogeneous sensors which could combine traditional sensors along with camera network for monitoring fall risk and activities of people with dementia. Apart from this, this network of cameras can be effectively used for infrastructure monitoring like restricted hallways, access control and patient movement.

A3.Business Intelligence: Analysis of customer behaviour is critical in restructuring business based on purchasing pattern. This is achieved by analysing customer emotions with the help of facial expression recognition. Current video analytics concentrate on understanding behaviour patterns when the customers are with and without children. Video analytics can also be used to ensure procedure compliance by staff by efficient tracking algorithms.

A4.Government: Governmental agencies can use video analytics in various ways including person verification & access control in restricted venues; crowd behaviour in peak hours and real time first response systems to help the public in case of calamities.

A5.Smoke detection and bush fire detection: The intelligent camera network can be used for smoke detection in challenging environment centralised decision making and in-network decision making. The advantage of low cost in-network processing over the traditional centralised processing will enable in using better intelligent algorithms and reducing load on central computers.

Previous | Next 1
top of page