Kushal Kusram

I am an engineer with formal education in computer science, masters from the University of Colorado, and bachelors from Visvesvaraya Technological University.

My area of research are computer vision, machine learning, software development, and large-scale deployment.

I currently am advancing sensing and large-scale deployment of the revolutionary next-gen parking system at Metropolis as a Senior Machine Learning Application Engineer.

news

May 24, 2022	Roadway Contextual Risk Assessment Using Dynamic Traffic Conditions Data Obtained from Autonomous Vehicles is published and available online.
May 22, 2022	Attended ICRA 2022, Philadelphia, PA, USA on behalf of Metropolis Machine Learning Team.
Sep 19, 2021	Attended ICIP 2021, Anchorage, AK, USA to present Two-Phase Multimodal Image Fusion Using Convolutional Neural Networks.
May 20, 2021	Two-Phase Multimodal Image Fusion Using Convolutional Neural Networks is accepted at IEEE ICIP 2021, Anchorage, AK, USA.

selected publications

ICIP 2021

Two-Phase Multimodal Image Fusion Using Convolutional Neural Networks

Kusram, K., Transue, S., and Choi, M.

2021 IEEE International Conference on Image Processing Sep 2021

Abs HTML PDF

The fusion of multiple imaging modalities presents an important contribution to machine vision, but remains an ongoing challenge due to the limitations in traditional calibration methods that perform a single, global alignment. For depth and thermal imaging devices, sensor and lens intrinsics (FOV, resolution, etc.) may vary considerably, making per-pixel fusion accuracy difficult. In this paper, we present AccuFusion, a two-phase non-linear registration method to fuse multimodal images at a per-pixel level to obtain an efficient and accurate image registration. The two phases: the Coarse Fusion Network (CFN) and Refining Fusion Network (RFN), are designed to learn a robust image-space fusion that provides a non-linear mapping for accurate alignment. By employing the refinement process, we obtain per-pixel displacements to minimize local alignment errors and observe an increase of 18% in average accuracy over global registration.
ASCE 2021

Roadway Contextual Risk Assessment Using Dynamic Traffic Conditions Data Obtained from Autonomous Vehicles

Bendigeri, V G., Zou, F., Ogle, J H., and Kusram, K.

2021 ASCE International Conference on Computing in Civil Engineering Sep 2021

Abs HTML PDF

Traditional road safety assessment methodologies do not recognize the driving environment’s fast-changing dynamics that influence the contextual complexity and, ultimately, its risk. This paper proposes a method to use diverse open-source sensor data (LiDAR) collected by Waymo autonomous vehicles to estimate the road environment’s complexity considering dynamic traffic conditions. The proposed contextual risk factor (CRF) model estimates the driving scene’s complexity using the density and proximity of the objects around the vehicle. The data was analyzed frame-by-frame, and contextual risk categories of high, medium, and low were assigned. The results revealed the objects in the scene well represent the contextual complexity. However, what the driver sees in front of them and within their forward reaction space is not directly representative of the complexity of the scene and vice versa.