Ekta Bhojwani

About Ekta Bhojwani

I am a Computer Vision Engineer at IntelliSee, a company that leverages deep learning and machine learning to provide real-time video analytics for risk detection and mitigation. My role involves developing and optimizing models for detecting and preventing threats such as weapon and fall incidents, using frameworks such as PyTorch, TensorFlow, and TensorRT. I have a MS degree in Electrical and Computer Engineering from University of North Carolina at Charlotte, where I specialized in deep learning in computer vision and high performance ML inferencing. I completed a research thesis on automating the inspection process of highway assets using a scalable AI framework, which was funded by VDOT and collaborated with Leidos team. I also learned deploying ML models on edge devices such as Google Coral TPU and NVIDIA AGX Xavier. I am passionate about applying my skills and knowledge to make the world safer and smarter.

Experience

1. Computer Vision Engineer

   Intellisee

   Jul 2021 — Present · Coralville, IA, US

   Preparing synthetic data for additional data augmentation using the Blender 3D.fbx models and writing blender python scripts for generating high quality synthetic data.Training and evaluating Deep Learning Object Detection modelConverting models to ONNX graph followed by serializing it to quantized FP16 or INT8 TensorRT engineHigh Performance ML pipeline benchmarkingProfiling the real-time GPU access and the real-time memory allocation inside the pipeline framework with NVIDIA Nsight.Developing Deep Learning and ML models for the real-time video analytics Computer Vision risk detection and risk mitigation product with a mission to make the world safer.Working on rescaling the frames parsed on video decoding to increase the spatial resolution on the frames.Optimizing the detection capability of the modelModel evaluating and testing.Fine-tuning Deep learning models

Education

• University of North Carolina at Charlotte

  Masters, Electrical and Computer Engineering

  2018 — 2020