Streaming video analytics using deep learning on large scale surveillance data @ Fractal Analytics
Submitted by abhineet verma (@averma) on Tuesday, 25 April 2017
Full talk for data engineering track
Video surveillance systems are increasingly becoming vital tools for protecting people and property. The increasing availability and lower cost of high-quality video cameras has increased the reach and the effectiveness of deploying and efficiently using video analytics systems. Even though video data often provides a very high amount of information, this data has not been efficiently used by analytical systems due to the challenges and complexities in processing video data. We have built a system to help address these challenges by leveraging cutting-edge image-processing and deep-learning based methodologies, combined with best-in-class data engineering practices to build video analytics systems. The system is built to read multiple streaming feeds from cameras as well as other sensor systems. The streaming data is analysed using machine learning methods (including deep learning methods) to perform various tasks – eg: face recognition on scaled streaming data.
In this talk, we will share our recent effort in joining multiple streams of data (video + other sensor), capturing the image at event/time and realising on how to implement algorithms like deep learning algorithms for face recognition at scale among others.
Video Analytics for enhanced security
Discussion on how to join multiple streams of Data(video+sensor data)using OpenCV & Spark.
Implementation of various ML techniques on sensors data to enhance security.
Discussion on Convolution Neural Networks
CNN Model training and challenges
Face Recognition at scale
Video Processing and Ad-Hoc Video Content Search
Abhineet Verma is Lead Data Engineer at Fractal Analytics Pvt Ltd , Bangalore and has over five years of experience in large scale data processing.Currently, he is leading the capability development at Fractal and responsible for solution development for analytical problems across multiple business domains at large scale. Prior to this, he worked as Senior Big Data Developer in building a real-time processing platform at Amadeus Software Labs, Bangalore.He works closely with Kafka, Spark,Cassandra, Hadoop,Machine Learning, Deep Learning, Computer Vision and Real-time streaming.