Tracking an Object in 3D Space

Implemented an obstacle detection pipeline using 3D lidar point cloud data by using RANSAC based plane segmentation, KD-Tree and Eucledian Clustering Algorithms.

Learn more

Lidar Obstacle Detection

Developed a pipeline to match 3D objects over time by using key point correspondences and also computed time to collision based on Lidar measurements. Projected lidar points backward onto a camera image in order to fuse sensor modalities. Used YOLO framework on the fused data for detecting and classifying objects and track vehicles.

Learn more

SFM Learner

Currently estimating depth and pose (or ego-motion) from a sequence of images using unsupervised learning. Using multiple image sequences from KITTI dataset and learning rotation and translation from the sequence.

Learn more

DepthSegNet - Monocular Depth estimation and Semantic Segmentation

This project addresses the two most important task in computer vision of depth estimation and semantic segmentation. We have considered the idea of integrating both the task together in the same framework as they may benefit each other in improving the accuracy.

Learn more

Traffic Sign Classification

Detected traffic signs from a video using MSER, Histogram of Gradients (HOG) features and trained a linear-Support Vector Machine (SVM) for classification purposes. Created bounding boxes around the detected sign and pasted the appropriate sign next to it for verification.

Learn more

Lane line detection

Created a traffic lane segmentation pipeline using HSL & LAB color spaces by identifying peak histograms. Used sliding window poly-fitting to determine radius of curvature of the road and distance between center of image and lane to calculate vehicle offset.

Learn more

Visual Odometry

Built an image processing pipeline to plot the route of a car taken from a dash-cam monocular camera. Calculated fundamental and essential matrices using RANSAC based 8-point algorithm and Zhang’s estimation

Learn more