I am a Perception engineer, with a passion to solve challenging problems in automated driving. My interest lies in object detection (2D / 3D) with multi sensor setup. As a part time researcher, my curiosity is piqued by exploring unsupervised learning and its applicability to detection problems. In my free time I like to read books, go for cycling and I have recently started bouldering.
Feb 2020 - Nov 2020, Aachen, NRW
2013-2017 B.Tech. Mechanical EngineeringCGPA: 1,4 out of 4Extracurricular Activities
| ||
A pipeline to generate adverse weather data via text guided diffusion models.
A tool for collecting and evaluating sythetic data and real data for effective training of Perception DNNs.
Integrating world knowledge in DNN to improve Vurlnerable Road User detections.
Open CV based rebar counting, tested and deployed in a steel mill.
In this paper, we propose a neural network for object detection and heading forecasting based on radar by fusing three raw radar channels with a cross-attention mechanism. We also introduce an improved ground truth augmentation method based on Bivariate norm, which represents the object labels in a more realistic form for radar measurements. Our results show 5% better mAP compared to state-of-the-art methods.
This course helps to understand the ML key concepts such as foundation of NN, Hyperparameter tuning, ML Pipleline structuring, CNN models, Transformers and sequence models. Each of the modules comes with muliple assignments and projects.
This course provides a broad introduction to exploratory data analysis (EDA), automated machine learning (AutoML), and text classification algorithms.
This course provides a through understanding of docker images and compose, along with CI-CD deployment with github actions and Travis CI. These are further augmented with multiple projects in Kubernetes and AWS hosting .
