Darshan Bhanushali - Academia.edu (original) (raw)

Papers by Darshan Bhanushali

The performance of autonomous agents in both commercial and consumer applications increases along... more The performance of autonomous agents in both commercial and consumer applications increases along with their situational awareness. Tasks such as obstacle avoidance, agent to agent interaction, and path planning are directly dependent upon their ability to convert sensor readings into scene understanding. Central to this is the ability to detect and recognize objects. Many object detection methodologies operate on a single modality such as vision or LiDAR. Camera-based object detection models benefit from an abundance of feature-rich information for classifying different types of objects. LiDAR-based object detection models use sparse point clouds, where each point contains accurate 3D position of object surfaces. Camera-based methods lack accurate object to lens distance measurements, while LiDAR-based methods lack dense feature-rich details. By utilizing information from both camera and LiDAR sensors, advanced object detection and identification is possible. In this work, we introduce a deep learning framework for fusing these modalities and produce a robust real-time 3D bounding box object detection network. We demonstrate qualitative and quantitative analysis of the proposed fusion model on the popular KITTI dataset.

electronic imaging, 2020

Modern warehouses utilize fleets of robots for inventory management. To ensure efficient and safe... more Modern warehouses utilize fleets of robots for inventory management. To ensure efficient and safe operation, real-time localization of each agent is essential. Most robots follow metal tracks buried in the floor and use a grid of precisely mounted RFID tags for localization. As robotic agents in warehouses and manufacturing plants become ubiquitous, it would be advantageous to eliminate the need for these metal wires and RFID tags. Not only do they suffer from significant installation costs, the removal of wires would allow agents to travel to any area inside the building. Sensors including cameras and LiDAR have provided meaningful localization information for many different positioning system implementations. Fusing localization features from multiple sensor sources is a challenging task especially when the target localization task’s dataset is small. We propose a deep-learning based localization system which fuses features from an omnidirectional camera image and a 3D LiDAR point...

for being on my thesis committee. I would also like to thank my parents, my sister Bhakti and my ... more for being on my thesis committee. I would also like to thank my parents, my sister Bhakti and my friends; without their support this journey would not have been as joyful as it was. I would like to thank Dr. Michael Kuhl and my friend Samrat Patel for their advice and suggestions. I am indebted to the iMHS team for all the support and discussion sessions.

SSRN Electronic Journal

e-Education has developed as one of the most encouraging territories. The Indian Government is in... more e-Education has developed as one of the most encouraging territories. The Indian Government is investing all amounts of energy to improve education among the residents of the nation. School and graduate understudies are focused on, however the stage is being created for all the residents seeking to learn. Without a doubt, the objective is to build the quantity of literates with advanced education. To accomplish the equivalent, propels in Data and Correspondence innovation are being utilized in the education division, which has cleared route for e-Training in India as well. To help educators in concentrating more on more current viewpoints, their excess work can be disposed of utilizing Machine Learning (ML). Difference to programming, ML deals with information and answers to create rules. In the event that Machine Learning is tackled effectively, it can setup the training division and contribute essentially to the development of the country. Hence, the work presented in this paper fortifiews e-Education in India utilizing Machine Learning. For the most part, three concerns are focused to be tended to: Personalized recommendation of course and Customized teaching methodology. The work proposes utilizing developmental methodology of hereditary calculations for improving conventional procedures. Implementation and experiments presented in the paper verify the viability of proposed calculations.

Electronic Imaging, 2020

The performance of autonomous agents in both commercial and consumer applications increases along... more The performance of autonomous agents in both commercial and consumer applications increases along with their situational awareness. Tasks such as obstacle avoidance, agent to agent interaction, and path planning are directly dependent upon their ability to convert sensor readings into scene understanding. Central to this is the ability to detect and recognize objects. Many object detection methodologies operate on a single modality such as vision or LiDAR. Camera-based object detection models benefit from an abundance of feature-rich information for classifying different types of objects. LiDAR-based object detection models use sparse point clouds, where each point contains accurate 3D position of object surfaces. Camera-based methods lack accurate object to lens distance measurements, while LiDAR-based methods lack dense feature-rich details. By utilizing information from both camera and LiDAR sensors, advanced object detection and identification is possible. In this work, we introduce a deep learning framework for fusing these modalities and produce a robust real-time 3D bounding box object detection network. We demonstrate qualitative and quantitative analysis of the proposed fusion model on the popular KITTI dataset.

2020 IEEE International Conference on Consumer Electronics (ICCE)

The performance of autonomous agents in both commercial and consumer applications increases along... more The performance of autonomous agents in both commercial and consumer applications increases along with their situational awareness. Tasks such as obstacle avoidance, agent to agent interaction, and path planning are directly dependent upon their ability to convert sensor readings into scene understanding. Central to this is the ability to detect and recognize objects. Many object detection methodologies operate on a single modality such as vision or LiDAR. Camera-based object detection models benefit from an abundance of feature-rich information for classifying different types of objects. LiDAR-based object detection models use sparse point clouds, where each point contains accurate 3D position of object surfaces. Camera-based methods lack accurate object to lens distance measurements, while LiDAR-based methods lack dense feature-rich details. By utilizing information from both camera and LiDAR sensors, advanced object detection and identification is possible. In this work, we introduce a deep learning framework for fusing these modalities and produce a robust real-time 3D bounding box object detection network. We demonstrate qualitative and quantitative analysis of the proposed fusion model on the popular KITTI dataset.

electronic imaging, 2020

Modern warehouses utilize fleets of robots for inventory management. To ensure efficient and safe... more Modern warehouses utilize fleets of robots for inventory management. To ensure efficient and safe operation, real-time localization of each agent is essential. Most robots follow metal tracks buried in the floor and use a grid of precisely mounted RFID tags for localization. As robotic agents in warehouses and manufacturing plants become ubiquitous, it would be advantageous to eliminate the need for these metal wires and RFID tags. Not only do they suffer from significant installation costs, the removal of wires would allow agents to travel to any area inside the building. Sensors including cameras and LiDAR have provided meaningful localization information for many different positioning system implementations. Fusing localization features from multiple sensor sources is a challenging task especially when the target localization task’s dataset is small. We propose a deep-learning based localization system which fuses features from an omnidirectional camera image and a 3D LiDAR point...

for being on my thesis committee. I would also like to thank my parents, my sister Bhakti and my ... more for being on my thesis committee. I would also like to thank my parents, my sister Bhakti and my friends; without their support this journey would not have been as joyful as it was. I would like to thank Dr. Michael Kuhl and my friend Samrat Patel for their advice and suggestions. I am indebted to the iMHS team for all the support and discussion sessions.

SSRN Electronic Journal

e-Education has developed as one of the most encouraging territories. The Indian Government is in... more e-Education has developed as one of the most encouraging territories. The Indian Government is investing all amounts of energy to improve education among the residents of the nation. School and graduate understudies are focused on, however the stage is being created for all the residents seeking to learn. Without a doubt, the objective is to build the quantity of literates with advanced education. To accomplish the equivalent, propels in Data and Correspondence innovation are being utilized in the education division, which has cleared route for e-Training in India as well. To help educators in concentrating more on more current viewpoints, their excess work can be disposed of utilizing Machine Learning (ML). Difference to programming, ML deals with information and answers to create rules. In the event that Machine Learning is tackled effectively, it can setup the training division and contribute essentially to the development of the country. Hence, the work presented in this paper fortifiews e-Education in India utilizing Machine Learning. For the most part, three concerns are focused to be tended to: Personalized recommendation of course and Customized teaching methodology. The work proposes utilizing developmental methodology of hereditary calculations for improving conventional procedures. Implementation and experiments presented in the paper verify the viability of proposed calculations.

Electronic Imaging, 2020

The performance of autonomous agents in both commercial and consumer applications increases along... more The performance of autonomous agents in both commercial and consumer applications increases along with their situational awareness. Tasks such as obstacle avoidance, agent to agent interaction, and path planning are directly dependent upon their ability to convert sensor readings into scene understanding. Central to this is the ability to detect and recognize objects. Many object detection methodologies operate on a single modality such as vision or LiDAR. Camera-based object detection models benefit from an abundance of feature-rich information for classifying different types of objects. LiDAR-based object detection models use sparse point clouds, where each point contains accurate 3D position of object surfaces. Camera-based methods lack accurate object to lens distance measurements, while LiDAR-based methods lack dense feature-rich details. By utilizing information from both camera and LiDAR sensors, advanced object detection and identification is possible. In this work, we introduce a deep learning framework for fusing these modalities and produce a robust real-time 3D bounding box object detection network. We demonstrate qualitative and quantitative analysis of the proposed fusion model on the popular KITTI dataset.

2020 IEEE International Conference on Consumer Electronics (ICCE)