Search Results for author: K. Madhava Krishna

Found 37 papers, 13 papers with code

AutoLay: Benchmarking amodal layout estimation for autonomous driving

no code implementations20 Aug 2021 Kaustubh Mani, N. Sai Shankar, Krishna Murthy Jatavallabhula, K. Madhava Krishna

Given an image or a video captured from a monocular camera, amodal layout estimation is the task of predicting semantics and occupancy in bird's eye view.

Amodal Layout Estimation Autonomous Driving

RP-VIO: Robust Plane-based Visual-Inertial Odometry for Dynamic Environments

1 code implementation18 Mar 2021 Karnik Ram, Chaitanya Kharyal, Sudarshan S. Harithas, K. Madhava Krishna

We evaluate our approach on this dataset, and three diverse sequences from standard datasets including two real-world dynamic sequences and show a significant improvement in robustness and accuracy over a state-of-the-art monocular visual-inertial odometry system.

Monocular Multi-Layer Layout Estimation for Warehouse Racks

1 code implementation16 Mar 2021 Meher Shashwat Nigam, Avinash Prabhu, Anurag Sahu, Puru Gupta, Tanvi Karandikar, N. Sai Shankar, Ravi Kiran Sarvadevabhatla, K. Madhava Krishna

Given a monocular colour image of a warehouse rack, we aim to predict the bird's-eye view layout for each shelf in the rack, which we term as multi-layer layout prediction.

RoRD: Rotation-Robust Descriptors and Orthographic Views for Local Feature Matching

1 code implementation15 Mar 2021 Udit Singh Parihar, Aniket Gujarathi, Kinal Mehta, Satyajit Tourani, Sourav Garg, Michael Milford, K. Madhava Krishna

The use of local detectors and descriptors in typical computer vision pipelines work well until variations in viewpoint and appearance change become extreme.

Pose Estimation Visual Place Recognition

BirdSLAM: Monocular Multibody SLAM in Bird's-Eye View

no code implementations15 Nov 2020 Swapnil Daga, Gokul B. Nair, Anirudha Ramesh, Rahul Sajnani, Junaid Ahmed Ansari, K. Madhava Krishna

In this paper, we present BirdSLAM, a novel simultaneous localization and mapping (SLAM) system for the challenging scenario of autonomous driving platforms equipped with only a monocular camera.

Autonomous Driving Object Localization +1

Early Bird: Loop Closures from Opposing Viewpoints for Perceptually-Aliased Indoor Environments

no code implementations3 Oct 2020 Satyajit Tourani, Dhagash Desai, Udit Singh Parihar, Sourav Garg, Ravi Kiran Sarvadevabhatla, Michael Milford, K. Madhava Krishna

In particular, our integration of VPR with SLAM by leveraging the robustness of deep-learned features and our homography-based extreme viewpoint invariance significantly boosts the performance of VPR, feature correspondence, and pose graph submodules of the SLAM pipeline.

Visual Place Recognition

Cosine meets Softmax: A tough-to-beat baseline for visual grounding

1 code implementation13 Sep 2020 Nivedita Rufus, Unni Krishnan R Nair, K. Madhava Krishna, Vineet Gandhi

In this paper, we present a simple baseline for visual grounding for autonomous driving which outperforms the state of the art methods, while retaining minimal design choices.

Autonomous Driving Metric Learning +2

Understanding Dynamic Scenes using Graph Convolution Networks

1 code implementation9 May 2020 Sravan Mylavarapu, Mahtab Sandhu, Priyesh Vijayan, K. Madhava Krishna, Balaraman Ravindran, Anoop Namboodiri

We present a novel Multi-Relational Graph Convolutional Network (MRGCN) based framework to model on-road vehicle behaviors from a sequence of temporally ordered frames as grabbed by a moving monocular camera.

Motion Segmentation Semantic Segmentation +1

Reconstruct, Rasterize and Backprop: Dense shape and pose estimation from a single image

no code implementations25 Apr 2020 Aniket Pokale, Aditya Aggarwal, K. Madhava Krishna

This paper presents a new system to obtain dense object reconstructions along with 6-DoF poses from a single image.

3D Reconstruction Pose Estimation

LiDAR guided Small obstacle Segmentation

2 code implementations12 Mar 2020 Aasheesh Singh, Aditya Kamireddypalli, Vineet Gandhi, K. Madhava Krishna

In this paper, we present a method to reliably detect such obstacles through a multi-modal framework of sparse LiDAR(VLP-16) and Monocular vision.

Autonomous Driving Semantic Segmentation

DFVS: Deep Flow Guided Scene Agnostic Image Based Visual Servoing

no code implementations8 Mar 2020 Y V S Harish, Harit Pandya, Ayush Gaud, Shreya Terupally, Sai Shankar, K. Madhava Krishna

We further present an extensive benchmark in a photo-realistic 3D simulation across diverse scenes to study the convergence and generalisation of visual servoing approaches.

Optical Flow Estimation

MonoLayout: Amodal scene layout from a single image

2 code implementations19 Feb 2020 Kaustubh Mani, Swapnil Daga, Shubhika Garg, N. Sai Shankar, Krishna Murthy Jatavallabhula, K. Madhava Krishna

We dub this problem amodal scene layout estimation, which involves "hallucinating" scene layout for even parts of the world that are occluded in the image.

Amodal Layout Estimation

Topological Mapping for Manhattan-like Repetitive Environments

1 code implementation16 Feb 2020 Sai Shubodh Puligilla, Satyajit Tourani, Tushar Vaidya, Udit Singh Parihar, Ravi Kiran Sarvadevabhatla, K. Madhava Krishna

At the intermediate level, the map is represented as a Manhattan Graph where the nodes and edges are characterized by Manhattan properties and as a Pose Graph at the lower-most level of detail.

Object Parsing in Sequences Using CoordConv Gated Recurrent Networks

no code implementations2 Oct 2019 Ayush Gaud, Y V S Harish, K. Madhava Krishna

We leverage the expressiveness of the popular stacked hourglass architecture and augment it by adopting memory units between intermediate layers of the network with weights shared across stages for video frames.

A Hierarchical Network for Diverse Trajectory Proposals

no code implementations9 Jun 2019 Sriram N. N., Gourav Kumar, Abhay Singh, M. Siva Karthik, Saket Saurav Brojeshwar Bhowmick, K. Madhava Krishna

In the indoor setting, we use an autonomous drone to navigate various scenarios and also a ground robot which can explore the environment using the trajectories proposed by our framework.

Integrating Objects into Monocular SLAM: Line Based Category Specific Models

no code implementations12 May 2019 Nayan Joshi, Yogesh Sharma, Parv Parkhiya, Rishabh Khawad, K. Madhava Krishna, Brojeshwar Bhowmick

The proposed parameterization associates 3D category-specific CAD model and object under consideration using a dictionary based RANSAC method that uses object Viewpoints as prior and edges detected in the respective intensity image of the scene.


DeCoILFNet: Depth Concatenation and Inter-Layer Fusion based ConvNet Accelerator

no code implementations1 Dec 2018 Akanksha Baranwal, Ishan Bansal, Roopal Nahar, K. Madhava Krishna

However, with the limited on-chip memory and computation resources of FPGA, meeting the high memory throughput requirement and exploiting the parallelism of CNNs is a major challenge.

Distributed, Parallel, and Cluster Computing

Geometric Consistency for Self-Supervised End-to-End Visual Odometry

no code implementations11 Apr 2018 Ganesh Iyer, J. Krishna Murthy, Gunshi Gupta, K. Madhava Krishna, Liam Paull

We show that using a noisy teacher, which could be a standard VO pipeline, and by designing a loss term that enforces geometric consistency of the trajectory, we can train accurate deep models for VO that do not require ground-truth labels.

Visual Odometry

CalibNet: Geometrically Supervised Extrinsic Calibration using 3D Spatial Transformer Networks

1 code implementation22 Mar 2018 Ganesh Iyer, R. Karnik Ram., J. Krishna Murthy, K. Madhava Krishna

During training, the network only takes as input a LiDAR point cloud, the corresponding monocular image, and the camera calibration matrix K. At train time, we do not impose direct supervision (i. e., we do not directly regress to the calibration parameters, for example).

Camera Calibration Domain Adaptation

MergeNet: A Deep Net Architecture for Small Obstacle Discovery

no code implementations17 Mar 2018 Krishnam Gupta, Syed Ashar Javed, Vineet Gandhi, K. Madhava Krishna

We present here, a novel network architecture called MergeNet for discovering small obstacles for on-road scenes in the context of autonomous driving.

Autonomous Driving

DiGrad: Multi-Task Reinforcement Learning with Shared Actions

no code implementations27 Feb 2018 Parijat Dewangan, S Phaniteja, K. Madhava Krishna, Abhishek Sarkar, Balaraman Ravindran

In this paper, we propose a new approach for simultaneous training of multiple tasks sharing a set of common actions in continuous action spaces, which we call as DiGrad (Differential Policy Gradient).

Multi-Task Learning reinforcement-learning

Constructing Category-Specific Models for Monocular Object-SLAM

no code implementations26 Feb 2018 Parv Parkhiya, Rishabh Khawad, J. Krishna Murthy, Brojeshwar Bhowmick, K. Madhava Krishna

These category models are instance-independent and aid in the design of object landmark observations that can be incorporated into a generic monocular SLAM framework.

Object SLAM

FPGA based Parallelized Architecture of Efficient Graph based Image Segmentation Algorithm

no code implementations6 Oct 2017 Roopal Nahar, Akanksha Baranwal, K. Madhava Krishna

Efficient and real time segmentation of color images has a variety of importance in many fields of computer vision such as image compression, medical imaging, mapping and autonomous navigation.

Autonomous Navigation Image Compression +1

Exploring Convolutional Networks for End-to-End Visual Servoing

no code implementations10 Jun 2017 Aseem Saxena, Harit Pandya, Gourav Kumar, Ayush Gaud, K. Madhava Krishna

In this paper, we present an end-to-end learning based approach for visual servoing in diverse scenes where the knowledge of camera parameters and scene geometry is not available a priori.

Joint Semantic and Motion Segmentation for dynamic scenes using Deep Convolutional Networks

no code implementations18 Apr 2017 Nazrul Haque, N. Dinesh Reddy, K. Madhava Krishna

This paper proposes an approach to fuse semantic features and motion clues using CNNs, to address the problem of monocular semantic motion segmentation.

Motion Segmentation Optical Flow Estimation +1

Reconstructing Vechicles from a Single Image: Shape Priors for Road Scene Understanding

no code implementations29 Sep 2016 J. Krishna Murthy, G. V. Sai Krishna, Falak Chhaya, K. Madhava Krishna

We then formulate a shape-aware adjustment problem that uses the learnt shape priors to recover the 3D pose and shape of a query object from an image.

Autonomous Driving road scene understanding

Dynamic Body VSLAM with Semantic Constraints

no code implementations27 Apr 2015 N. Dinesh Reddy, Prateek Singhal, Visesh Chari, K. Madhava Krishna

We show results on the challenging KITTI urban dataset for accuracy of motion segmentation and reconstruction of the trajectory and shape of moving objects relative to ground truth.

Autonomous Navigation Motion Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.