Agency for Science, Technology and Research

Singapore Health Services Pte Ltd

How Lung Eng

Wei Yun Yau

Beng Hai Lee

Junxian Wang

That Mon Htwe

Siew Wah Alvin Harvey Kam

Boon Fong Chew

Wei Shih Derrick Chan

Wiriyanto Darsono

Ee Sin Ng

Suryanti Yunita Anggrelly

There is provided a hypermotor activity detection system, including: a video capture device configured to monitor a patient and obtain a video input; and a processing system configured to process the video input. The processing system includes: an optical flow module configured to carry out an optical flow analysis on a video input region determined from the video input, and further determine a flow field magnitude of the video input region; and a local motion reference module configured to obtain a local motion reference value. The local reference module includes: a division module; a sub-window flow module; a local motion magnitude module; and a local motion comparison module. Further, a corresponding method for detecting hypermotor activity is provided.

Hypermotor activity detection system and method therefrom

A system and system for monitoring water quality. The system comprises a container for receiving a flow of water to be monitored, the container containing a plurality of fish and configured such that a substantially 3-dimensional group behavior of the fish is accommodated; a first imaging device disposed above the container for obtaining top view video data of the fish; and means for identifying individual fish based on foreground object detection.

Fish activity monitoring system for early warning of water contamination

A background image is generated based on a captured image. A data cluster is formed in pixel blocks of the background image using at least one feature of pixels in the pixel blocks. A data cluster formed in each pixel block includes a data distribution having a mean value and a standard deviation from the mean value. After generating the background image, each pixel of a subsequent captured image is compared with the data cluster of a pixel block of the background image to generate a first discrepancy value. A pixel of a subsequent image is compared with a data distribution of another adjacent pixel block of the background image to generate a second discrepancy value. Based on the discrepancy values, the pixels of the subsequent image are regarded as background or foreground pixels in a binary map, in which connected foreground pixels are marked to form a foreground object.

Method for detecting desired objects in a highly dynamic environment by a monitoring system

Growing community of inventors

Singapore, Singapore

How Lung Eng