Video Recognition using Deep Learning – Deep Dive

Deep learning-based solution for video recognition essentially involves detecting, classifying and localizing static, multi class objects in field of view and plotting the dynamic form factor, pose, orientation and location of objects over time. Most common use case is to determine the actions of human operators in the field of view. There are various solution approaches used by the deep computer vision practitioner community to improve the pipeline throughput, resource utilization (specifically in case of inference on compute constrained edge devices) and performance (accuracy, responsiveness).

Reading Time: 3 minutes
Read the article  

ABOUT THE AUTHOR

Nirupam Kulkarni

Nirupam Kulkarni works as Product Manager focused on eInfochips' IoT and AI product and solution portfolio. He has 11 years of technology experience across IT and analytics consulting, market research, product management and digital partnerships.