Monash Machine Vision Group receives first place in TRECVID 2019 ActEV challenge

3 October 2019

Sponsored by the National Institute of Standards and Technology (NIST) and the Intelligence Advanced Research Projects Activity (IARPA), the TRECVID 2019 ActEV challenge hosted a number of university research teams to develop techniques around activity detection in surveillance videos.

The Monash Machine Vision Group (MMVG), led by Dr Xiaojun Chang, achieved first place in the annual challenge which aims to accelerate the development of robust, multi-camera, automatic activity detection algorithms for forensic and real-time alerting applications.

With the support of eResearch centre members Dr. Zongyuan Ge and Prof. Paul Bonnington, the MMVG modelled real-world surveillance camera situations.

The techniques developed by MMVG in the TRECVID 2019 ActEV challenge can be readily applied to safeguard various industries including, mining and quarrying, public safety and disaster management.

Activity detection technologies process extended video streams, such as those from an IP camera, and automatically detects all instances of the activity by identifying the type of activity, producing a confidence score indicating the presence of instance, temporally localising the instance by indicating the begin and end times, and detecting the objects involved in the activity.

Well done to Dr Xiaojun Chang the MMVG team on this fantastic result.


Information Technology


Data Science, AI, TRECVID, ActEV, Machine Learning