Visual SLAM and structure from motion in dynamic environments: A survey

MRU Saputra, A Markham, N Trigoni - ACM Computing Surveys (CSUR), 2018‏ - dl.acm.org
In the last few decades, Structure from Motion (SfM) and visual Simultaneous Localization
and Map** (visual SLAM) techniques have gained significant interest from both the …

Detect-SLAM: Making object detection and SLAM mutually beneficial

F Zhong, S Wang, Z Zhang… - 2018 IEEE winter …, 2018‏ - ieeexplore.ieee.org
Although significant progress has been made in SLAM and object detection in recent years,
there are still a series of challenges for both tasks, eg, SLAM in dynamic environments and …

Mono3d++: Monocular 3d vehicle detection with two-scale 3d hypotheses and task priors

T He, S Soatto - Proceedings of the AAAI Conference on Artificial …, 2019‏ - ojs.aaai.org
We present a method to infer 3D pose and shape of vehicles from a single image. To tackle
this ill-posed problem, we optimize two-scale projection consistency between the generated …

Carfusion: Combining point tracking and part detection for dynamic 3d reconstruction of vehicles

ND Reddy, M Vo… - Proceedings of the IEEE …, 2018‏ - openaccess.thecvf.com
Despite significant research in the area, reconstruction of multiple dynamic rigid objects (eg.
vehicles) observed from wide-baseline, uncalibrated and unsynchronized cameras, remains …

A real-time dynamic object segmentation framework for SLAM system in dynamic scenes

J Chang, N Dong, D Li - IEEE Transactions on Instrumentation …, 2021‏ - ieeexplore.ieee.org
To accurately detect dynamic objects in dynamic scenes (DSs), a detection framework
equipped with visual-based measurement methods has been proposed in this article. First …

WALT3D: Generating realistic training data from time-lapse imagery for reconstructing dynamic objects under occlusion

K Vuong, ND Reddy, R Tamburo… - Proceedings of the …, 2024‏ - openaccess.thecvf.com
Current methods for 2D and 3D object understanding struggle with severe occlusions in
busy urban environments partly due to the lack of large-scale labeled ground-truth …

Reconstructing vehicles from a single image: Shape priors for road scene understanding

JK Murthy, GVS Krishna, F Chhaya… - … on Robotics and …, 2017‏ - ieeexplore.ieee.org
We present an approach for reconstructing vehicles from a single (RGB) image, in the
context of autonomous driving. Though the problem appears to be ill-posed, we demonstrate …

Semantic map** for view-invariant relocalization

J Li, D Meger, G Dudek - 2019 International Conference on …, 2019‏ - ieeexplore.ieee.org
We propose a system for visual simultaneous localization and map** (SLAM) that
combines traditional local appearance-based features with semantically meaningful object …

Real-time dense monocular SLAM with online adapted depth prediction network

H Luo, Y Gao, Y Wu, C Liao, X Yang… - IEEE Transactions on …, 2018‏ - ieeexplore.ieee.org
Considerable advances have been achieved in estimating the depth map from a single
image via convolutional neural networks (CNNs) during the past few years. Combining …

Visual-inertial-semantic scene representation for 3D object detection

J Dong, X Fei, S Soatto - Proceedings of the IEEE …, 2017‏ - openaccess.thecvf.com
We describe a system to detect objects in three-dimensional space using video and inertial
sensors (accelerometer and gyrometer), ubiquitous in modern mobile platforms from phones …