Rishan Sanjay

Data Scientist, Kushagramati Analytics

Data Scientist. Sports and music enthusiast.

Past sessions

Surveillance feed has essentially been monitored manually until recent years. Video analytics as a technology has made great strides and leverages video surveillance networks to derive searchable, actionable, and quantifiable intelligence from live or recorded video content. 

Driven by artificial intelligence and deep learning, video intelligence solutions detect and extract objects in a video. These solutions identify target objects based on trained Deep Neural Networks and then classify each object to enable intelligent video analysis, including search & filtering, alerting, data aggregation and visualization.

In our session, we will:

  • Discuss the current state of surveillance and      popular Python libraries used in video analytics 
  • Elucidate various approaches deployed, using a      myriad of pre-trained models from MobileNet SSD to the state-of-the-art Yolo Model. 
  • Describe the many pre-processing techniques we have used, such as the generation of a time-averaged frame, erosion, dilation, and many others 

With the basics covered, it's LIGHTS! CAMERA! ACTION ....Let us show you how this works. We will be presenting a live demo that will explain the performance-computing trade-offs between the use of different models, techniques, and their limitations. 

What you can expect to take away from our session:

  • Gain a deeper understanding of advanced Video Analytics techniques 
  • Understand how to utilize pre-trained models      for video analytics solutions 
  • Learn more about the hardware requirements,      limitations and challenges posed while devising a video analytics solution      
  • Benefit from the lessons learnt upon deployment in a real-life scenario 
  • The future direction and possibilities of the  solution we have developed
In this session watch:
Vinamre Dhar, Data Scientist, Kushagramati Analytics
Rishan Sanjay, Data Scientist, Kushagramati Analytics