Search Results for author:
Found 42 papers, 13 papers with code
Semantic Motion Segmentation Using Dense CRF Formulation
We pro- pose an algorithm that jointly infers the semantic class and motion labels of an object.
Dynamic Body VSLAM with Semantic Constraints
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.
Reconstructing Vechicles from a Single Image: Shape Priors for Road Scene Understanding
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.
Joint Semantic and Motion Segmentation for dynamic scenes using Deep Convolutional Networks
This paper proposes an approach to fuse semantic features and motion clues using CNNs, to address the problem of monocular semantic motion segmentation.
Exploring Convolutional Networks for End-to-End Visual Servoing
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.
FPGA based Parallelized Architecture of Efficient Graph based Image Segmentation Algorithm
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.
Beyond Pixels: Leveraging Geometry and Shape Cues for Online Multi-Object Tracking
This paper introduces geometry and object shape and pose costs for multi-object tracking in urban driving scenarios.
Ranked #2 on
3D Multi-Object Tracking
on KITTI
Constructing Category-Specific Models for Monocular Object-SLAM
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.
DiGrad: Multi-Task Reinforcement Learning with Shared Actions
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).
The Earth ain't Flat: Monocular Reconstruction of Vehicles on Steep and Graded Roads from a Moving Camera
The proposed approach significantly improves the state-of-the-art for monocular object localization on arbitrarily-shaped roads.
MergeNet: A Deep Net Architecture for Small Obstacle Discovery
We present here, a novel network architecture called MergeNet for discovering small obstacles for on-road scenes in the context of autonomous driving.
CalibNet: Geometrically Supervised Extrinsic Calibration using 3D Spatial Transformer Networks
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).
Geometric Consistency for Self-Supervised End-to-End Visual Odometry
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.
Parameter Sharing Reinforcement Learning Architecture for Multi Agent Driving Behaviors
This paper proposes a novel architecture to learn multiple driving behaviors in a traffic scenario.
DeCoILFNet: Depth Concatenation and Inter-Layer Fusion based ConvNet Accelerator
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
Learning to Prevent Monocular SLAM Failure using Reinforcement Learning
Monocular SLAM refers to using a single camera to estimate robot ego motion while building a map of the environment.
Robotics
Integrating Objects into Monocular SLAM: Line Based Category Specific Models
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.
Robotics
A Hierarchical Network for Diverse Trajectory Proposals
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.
Object Parsing in Sequences Using CoordConv Gated Recurrent Networks
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.
Towards Accurate Vehicle Behaviour Classification With Multi-Relational Graph Convolutional Networks
Understanding on-road vehicle behaviour from a temporal sequence of sensor data is gaining in popularity.
Multi-object Monocular SLAM for Dynamic Environments
In this paper, we tackle the problem of multibody SLAM from a monocular camera.
Topological Mapping for Manhattan-like Repetitive Environments
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.
MonoLayout: Amodal scene layout from a single image
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.
DFVS: Deep Flow Guided Scene Agnostic Image Based Visual Servoing
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.
LiDAR guided Small obstacle Segmentation
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.
Reconstruct, Rasterize and Backprop: Dense shape and pose estimation from a single image
This paper presents a new system to obtain dense object reconstructions along with 6-DoF poses from a single image.
Understanding Dynamic Scenes using Graph Convolution Networks
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.
Ranked #1 on
Test results
on KITTI
Cosine meets Softmax: A tough-to-beat baseline for visual grounding
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.
Ranked #6 on
Referring Expression Comprehension
on Talk2Car
Early Bird: Loop Closures from Opposing Viewpoints for Perceptually-Aliased Indoor Environments
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.
BirdSLAM: Monocular Multibody SLAM in Bird's-Eye View
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.
DRACO: Weakly Supervised Dense Reconstruction And Canonicalization of Objects
We present DRACO, a method for Dense Reconstruction And Canonicalization of Object shape from one or more RGB images.
RoRD: Rotation-Robust Descriptors and Orthographic Views for Local Feature Matching
The use of local detectors and descriptors in typical computer vision pipelines work well until variations in viewpoint and appearance change become extreme.
Monocular Multi-Layer Layout Estimation for Warehouse Racks
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.
RP-VIO: Robust Plane-based Visual-Inertial Odometry for Dynamic Environments
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.
AutoLay: Benchmarking amodal layout estimation for autonomous driving
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.
ReF -- Rotation Equivariant Features for Local Feature Matching
Sparse local feature matching is pivotal for many computer vision and robotics tasks.
Ground then Navigate: Language-guided Navigation in Dynamic Scenes
We investigate the Vision-and-Language Navigation (VLN) problem in the context of autonomous driving in outdoor settings.
UAV-based Visual Remote Sensing for Automated Building Inspection
Unmanned Aerial Vehicle (UAV) based remote sensing system incorporated with computer vision has demonstrated potential for assisting building construction and in disaster management like damage assessment during earthquakes.
MVRackLay: Monocular Multi-View Layout Estimation for Warehouse Racks and Shelves
To the best of our knowledge, this is the first such work to portray a 3D rendering of a warehouse scene in terms of its semantic components - Racks, Shelves and Objects - all from a single monocular camera.
Talk2BEV: Language-enhanced Bird's-eye View Maps for Autonomous Driving
Talk2BEV is a large vision-language model (LVLM) interface for bird's-eye view (BEV) maps in autonomous driving contexts.
Automated Detection and Counting of Windows using UAV Imagery based Remote Sensing
Despite the technological advancements in the construction and surveying sector, the inspection of salient features like windows in an under-construction or existing building is predominantly a manual process.
