|
|
|
![]() |
We present a monocular visual-inertial odometry (VIO) system that uses only planar features and their induced homographies, during both initialization and sliding-window estimation, for increased robustness and accuracy in dynamic environments. We evaluate on diverse sequences, including our own highly-dynamic simulated dataset, and show significant improvement over a state-of-the-art monocular VIO algorithm in dynamic environments. Project page |
![]() |
We propose a data-driven prior on possible user locations in a map by combining learned spatial map embeddings and temporal odometry embeddings. Our prior learns to encode which map regions are feasible locations for a user more accurately than previous hand-defined methods, and leads to a 49% improvement in inertial-only localization accuracy when used in a particle filter. Project page |
![]() |
We have developed an autoregressive model to accurately predict future trajectories of traffic participants (vehicles). We demonstrate that using semantics provides a significant boost and allows the model generalize to completely different datasets, collected across several cities, and also across countries where people drive on opposite sides of the road (left-handed vs right-handed driving). Preprint | Video |
![]() |
We developed a self-supervised deep network, CalibNet, capable of automatically estimating the 6-DoF rigid body transformation between a 3D LiDAR and a 2D camera in real-time. The network alleviates the need for any calibration targets, thereby reducing significant calibration efforts. Preprint | Video |
|
Developed a turn-by-turn assistive indoor navigation app for iOS that combined three deep models for localization in real-time -- LSTM for bluetooth-based absolute position estimation, LSTM for IMU-based relative position estimation, LSTM + U-Net for encoding floor map information. Data collected using Meta's Project Aria Glasses were used for training the models. Video demo | Presentation | Meta Connect feature |
|
![]() |
An end-to-end application with a graphical user interface for easily calibrating the extrinsics between range and visual sensors was developed during GSoC 2018. Automatic and target-less calibration algorithms based on plane-matching and line-matching were integrated into the app, allowing the calibration to be performed in any generic scene setting without the need for any specific targets. Code | Video demo | Report |
![]() |
Mentored and worked with a team in a national-level competition on a janitorial robot to autonomously navigate and clean a washroom setup. The team was selected for the simulation and on-site rounds out of of 136 teams and finished second overall. Challenge page |
|
![]() |
Estimated the camera motion between two frames by minimizing the photometric error between them. Implemented in matlab using a vanilla Levenberg-Marquardt non-linear least squares (approx.) solver. Results |
![]() |
Implemented a pipeline to estimate the rigid body pose between an IMU and a camera by applying the Kabsch algorithm to their motion estimates. Based on Zachary Taylor and Juan Nieto's work on Motion-Based Calibration of Multimodal Sensor Arrays. Report | Code |
![]() |
Developed a visual odometry module based on optic flow for the localization of a custom-built quadcopter and incorporated it into the PX4 navigation stack, enabling autonomous indoor navigation. All the computations were performed on-board, on an Odroid XU4. A stock counting module was implemented using ArUco markers. Report | Code |
![]() |
Used SimpleOpenNI to track body joint angles and mapped it to a model in blender. This was developed as a part of a body posture tracking project during my time as an intern at HTIC. Code | Video |
![]() |
Developed and evaluated a person tracking application for a drone using a CUDA accelerated monocular HOG detector, and another using disparity maps generated from a custom stereo rig. Both were tested on a Jetson TX1. This was developed during my time as an intern at Navstik Labs. |
![]() |
Developed a simple navigation stack for controlling the motion of a differential drive mobile robot using visual feed-back from an overhead camera. The stack consisted of a color based localization module and a PID controller for issuing steering commands to the motors. Code | Video |
![]() |
Built and programmed a flight controller for stabilizing a custom built quadcopter, using the ATmega328. Utilized interrupt service routines, I2C comm, PWM and PID rate control loops. Code |
![]() |
Developed an Android app that enabled students to share their course textbooks among each other easily. This app has got close to a thousand installations and has also been featured in a prominent weekly magazine, and in the top 10 of the Apps for Chennai contest. Code | Store | Press | Press |
![]() |
Ideated and developed an Android application to notify students and faculty about important events, announcements and other campus related information like bus routes and dining menus. It has close to two thousand users today and is the official app of SSN. Code | Store | Appreciation |
|
Built using Hugo and Jon's styling
|