Tracking 3-D Motion of Dynamic Objects Using Monocular Visual-Inertial Sensing

Qiu, Kejie; Qin, Tong; Gao, Wenliang; Shen, Shaojie

doi:10.1109/tro.2019.2909085

Cited by 53 publications

(41 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, a pose graph was designed to maintain cyclic consistencies and solve the problem of relative scale ambiguity. Another approach to solving this problem was proposed by Qiu et al [ 52 ] based on the fact that camera motion and object motion are independent. They quantified the correlation between camera motion and object motion, and formulated an objective function based on the quantification results to recover the scale factor of each tracking object.…”

Section: Low-level-feature-based Dynamic Slammentioning

confidence: 99%

“…Qiu et al [ 52 ] leveraged a NN to detect [ 54 ] and associate [ 53 ] high-level features. Next, 3D object motion was recovered from 2D object regions using region-based BA, which represents the relative motion between two dynamic frames (object frame and camera frame), as discussed in Dynamic feature reconstruction and 3D object tracking section.…”

Section: Using High-level Features In Dynamic Slammentioning

confidence: 99%

See 1 more Smart Citation

A survey: which features are required for dynamic visual simultaneous localization and mapping?

Zheng

2021

Vis. Comput. Ind. Biomed. Art

View full text Add to dashboard Cite

In recent years, simultaneous localization and mapping in dynamic environments (dynamic SLAM) has attracted significant attention from both academia and industry. Some pioneering work on this technique has expanded the potential of robotic applications. Compared to standard SLAM under the static world assumption, dynamic SLAM divides features into static and dynamic categories and leverages each type of feature properly. Therefore, dynamic SLAM can provide more robust localization for intelligent robots that operate in complex dynamic environments. Additionally, to meet the demands of some high-level tasks, dynamic SLAM can be integrated with multiple object tracking. This article presents a survey on dynamic SLAM from the perspective of feature choices. A discussion of the advantages and disadvantages of different visual features is provided in this article.

show abstract

Section: Low-level-feature-based Dynamic Slammentioning

confidence: 99%

Section: Using High-level Features In Dynamic Slammentioning

confidence: 99%

A survey: which features are required for dynamic visual simultaneous localization and mapping?

Zheng

2021

Vis. Comput. Ind. Biomed. Art

View full text Add to dashboard Cite

show abstract

“…Furthermore, ref. [17] proposed a framework achieving simultaneous localization, mapping and object tracking that estimates both the camera ego-motion and 3D semantic objects, where the correlation analysis between camera motion and object motion is applied to calculate the scale factor. Ref.…”

Section: Related Workmentioning

confidence: 99%

A robust visual SLAM system in dynamic man-made environments

Liu

Meng

You

2020

Sci. China Technol. Sci.

View full text Add to dashboard Cite

This paper presents a robust visual simultaneous localization and mapping (SLAM) system that leverages point and structural line features in dynamic man-made environments. Manhanttan world assumption is considered and the structural line features in such man-made environments provide rich geometric constraint, e.g., parallelism. Such a geometric constraint can be therefore used to rectify 3D maplines after initialization. To cope with dynamic scenarios, the proposed system are divided into four main threads including 2D dynamic object tracking, visual odometry, local mapping and loop closing. The 2D tracker is responsible to track the object and capture the moving object in bounding boxes. In such a case, the dynamic background can be excluded and the outlier point and line features can be effectively removed. To parameterize 3D lines, we use Plücker line coordinates in initialization and projection processes, and utilize the orthonormal representation in unconstrained graph optimization process. The proposed system has been evaluated in both benchmark datasets and real-world scenarios, which reveals a more robust performance in most of the experiments compared with the existing state-of-the-art methods.

show abstract

“…Technologies for delivering ILEs might be physically robust and able to operate the required software and controls (Thomson, 2018). Fortunately, evidence suggests that many mobile technologies are feasible for basic AR and VR purposes (e.g., Qiu et al, 2019). There is no current universal standard for tablet or smartphone design, resulting in a range of features, interfaces, operating systems, and networks.…”

Section: Technical Points Of Entrymentioning

confidence: 99%

Immersive Learning Environments at Scale: Constraints and Opportunities

Siegle

Roscoe

Schroeder

et al. 2020

Proceedings of the Human Factors and Ergonomics Society Annual

View full text Add to dashboard Cite

The expansion of online education into massive open online courses (MOOCs) and equipment have created a unique opportunity for delivering immersive learning experiences at scale. However, although the inclusivity of the MOOC ecosystem can be commended, many online courses lack key benefits associated with traditional classroom environments: immersive, engaging, and team-driven learning opportunities. Immersive learning environments (ILEs) address these educational gaps but has not been able to operate at the broad scale that MOOCs offer. Importantly, ILEs address opportunities missing from MOOC systems, they add unique learning opportunities that would also be missing in a traditional classroom. The inclusion of this virtual reality technology is pivotal topic for educational research. This theoretical paper will briefly define immersive learning environments and the potential benefits of incorporating immersive learning environments into scalable educational systems. We will also consider developers constraints on creating these online ecosystem and suggested strategies for overcoming them.

show abstract

Tracking 3-D Motion of Dynamic Objects Using Monocular Visual-Inertial Sensing

Cited by 53 publications

References 32 publications

A survey: which features are required for dynamic visual simultaneous localization and mapping?

A survey: which features are required for dynamic visual simultaneous localization and mapping?

A robust visual SLAM system in dynamic man-made environments

Immersive Learning Environments at Scale: Constraints and Opportunities

Contact Info

Product

Resources

About