This is an automatic means based on unsupervised machine learning, neural network computing, and computer vision techniques to analyse video content filmed inside underground stormwater drains to help find out any structural and functional related anomalies.

To ensure slope safety and prevent from landslides is important for the densely populated hillside areas in Hong Kong. This system adopted the use of deep learning methods to vectorise video imagery of underground stormwater drains for further cluster analysis. The resulting image clusters will then be visualised 
for identifying which groups have damage-related issues and then compute the severity of the defective drains to determine the priority of remedial works.

▍ Use deep learning methods to extract image features for vectorising video imagery of underground stormwater drains
▍ Cluster all vectorised images into various groups
▍ Visualise resulting clusters to identify which groups have damage-related issues
▍ Compute the severity of the defective drains to determine the priority of remedial works

▍ This video analytics technology and application for recognising damages, defects, and general anomalies inside underground stormwater drains enable a systematic, consistent, and reliable means to ensure the massively constructed stormwater drainage infrastructure under slopes is in a well maintained condition. 
▍ Reduce the chance of landslide caused by frequent heavy rainfall in Hong Kong.

2024

Technology licensing

Underground Stormwater Drains Survey and Management