Simultaneous Localization, Mapping and Moving Object Tracking

By Chieh-Chih Bob Wang, C. Thorpe, Sebastian Thrun, Martial Hebert, H. F. Durrant-Whyte. Int. J. Robotics Res., 2007

695 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Artificial Intelligence, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/f712798e03e4acae700739aa10f1ac43efeb3336

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Artificial Intelligence

In Electrical and Electronic Engineering

Citations in the corpus

Kimera: From SLAM to spatial perception with 3D dynamic scene graphs (2021, methodology): “…et al. 2007) or as SLAM and Detection And Tracking of Moving Objects, DATMO (Azim and Aycard 2012)) has been extensively investigated in robotics (Wang et al. 2007), while more recent work focuses on joint visual-inertial odometry and target pose estimation (Qiu et al. 2019; Eckenhoff et al.…”
Visual Place Recognition: A Survey (2016, background): “Elements of a scene that are moving when the robot observes them must be detected and may also be removed [229], [230].”
MaskFusion: Real-Time Recognition, Tracking and Reconstruction of Multiple Moving Objects (2018, neutral): “In the first case, a deformable world is assumed [12, 32, 53] and as-rigid-as-possible registration is performed, while in the second, rigid object instances are identified [40, 46] and tracked sparsely [48, 54] or densely [39].”
Detection, classification and tracking of moving objects in a 3D environment (2012, methodology): “Most of these use the grid maps, specially a well-established mapping technique of occupancy grid algorithm [2], to represent the environment.”
Robust Multiperson Tracking from a Mobile Platform (2009, background): “In robotics, various approaches for SLAM in dynamic environments exist [5], [22], [55], related to the above, but mostly focusing on range data.”
Multimodal information fusion for urban scene understanding (2016, background): “LiDARs are often used to detect static structures [29] and also moving objects [31].”
Visual simultaneous localization and mapping: a survey (2012, background): “However, the addition of sensors increases the cost, weight and power requirements of a system; therefore, it is important to investigate how an entity may locate itself and create a map with only cameras.”
A perception‐driven autonomous urban vehicle (2008, background): “A single process is responsible for maintaining and broadcasting the vehicle’s pose in the local frame (position, velocity, acceleration, orientation, and turning rates) as well as the most recent local-to-GPS transformation.”
Multiple Sensor Fusion and Classification for Moving Object Detection and Tracking (2016, methodology): “Whilst Vu [1] and Wang [3] use an almost deterministic approach to perform the association in tracking, we use an evidential approach based on mass distributions over the set of different class hypotheses.”
TerraMax™: Team Oshkosh urban robot (2008, methodology): “A notable detection and tracking system for urban traffic from LIDAR data was developed by Wang (2004) , who incorporated dynamic object tracking in a 3-D simultaneous localization and mapping (SLAM) system.”
Visual SLAM and Structure from Motion in Dynamic Environments (2018, methodology): “To this end, [169] and [170] employed a laser scanner to track moving objects using a Bayesian approach and created in a system called SLAMMOT (Simultaneous Localization, Mapping, and Moving Object Tracking).”
Stereo-Camera-Based Urban Environment Perception Using Occupancy Grid and Object Tracking (2012, methodology): “Compared with the approaches in [5] and [8], we achieved good results using a sensor other than a laser scanner, namely, a stereo camera.”
Model based vehicle detection and tracking for autonomous urban driving (2009, methodology): “In vehicle tracking literature it is common to use a constant velocity model (Dellaert and Thorpe, 1998), a constant acceleration model (Dietmayer et al, 2001), or a switching dynamics model (Wang, 2004; Darms et al, 2008).”
3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humans (2020, background): “SLAM and moving object tracking (sometimes referred to as SLAMMOT [102] or as SLAM and Detection And Tracking of Moving Objects, DATMO [6]) has been extensively investigated in robotics [102], while more recent work focuses on joint visualinertial odometry and target pose estimation [23, 29, 81].”
DynaSLAM II: Tightly-Coupled Multi-Object Tracking and SLAM (2020, methodology): “The idea of simultaneously estimating camera motion and multiple moving objects motion originated from the SLAM-MOT work [20].”