Monocular Object and Plane SLAM in Structured Environments

Yang, Shichao; Scherer, Sebastian

doi:10.1109/lra.2019.2924848

Cited by 90 publications

(35 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To discuss the performance of the improved ORB-based visual SLAM algorithm (I-ORB), a comparative experiment with the general ORB-based visual SLAM algorithm (G-ORB) is conducted. And, the widely used data set TUM is selected to test the performance of the two algorithms [38,39]. ree subsets of TUM (fre1_desk1,…”

Section: Discussionmentioning

confidence: 99%

An Improved Deep Residual Network-Based Semantic Simultaneous Localization and Mapping Method for Monocular Vision Robot

Gong

et al. 2020

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The robot simultaneous localization and mapping (SLAM) is a very important and useful technology in the robotic field. However, the environmental map constructed by the traditional visual SLAM method contains little semantic information, which cannot satisfy the needs of complex applications. The semantic map can deal with this problem efficiently, which has become a research hot spot. This paper proposed an improved deep residual network- (ResNet-) based semantic SLAM method for monocular vision robots. In the proposed approach, an improved image matching algorithm based on feature points is presented, to enhance the anti-interference ability of the algorithm. Then, the robust feature point extraction method is adopted in the front-end module of the SLAM system, which can effectively reduce the probability of camera tracking loss. In addition, the improved key frame insertion method is introduced in the visual SLAM system to enhance the stability of the system during the turning and moving of the robot. Furthermore, an improved ResNet model is proposed to extract the semantic information of the environment to complete the construction of the semantic map of the environment. Finally, various experiments are conducted and the results show that the proposed method is effective.

show abstract

Section: Discussionmentioning

confidence: 99%

An Improved Deep Residual Network-Based Semantic Simultaneous Localization and Mapping Method for Monocular Vision Robot

Gong

et al. 2020

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Recently, SLAM techniques combining both geometric as well as semantic information have gained popularity and significant relevance [9]. It is now widely recognized that the incorporation of object-level information for accurate data associations and loop closures can increase the quality, robustness and interpretability of the solutions [10]- [12].…”

Section: Related Workmentioning

confidence: 99%

VPS-SLAM: Visual Planar Semantic SLAM for Aerial Robotic Systems

et al. 2020

View full text Add to dashboard Cite

Indoor environments have abundant presence of high-level semantic information which can provide a better understanding of the environment for robots to improve the uncertainty in their pose estimate. Although semantic information has proved to be useful, there are several challenges faced by the research community to accurately perceive, extract and utilize such semantic information from the environment. In order to address these challenges, in this paper we present a lightweight and real-time visual semantic SLAM framework running on board aerial robotic platforms. This novel method combines low-level visual/visual-inertial odometry (VO/VIO) along with geometrical information corresponding to planar surfaces extracted from detected semantic objects. Extracting the planar surfaces from selected semantic objects provides enhanced robustness and makes it possible to precisely improve the metric estimates rapidly, simultaneously generalizing to several object instances irrespective of their shape and size. Our graph-based approach can integrate several state of the art VO/VIO algorithms along with the state of the art object detectors in order to estimate the complete 6DoF pose of the robot while simultaneously creating a sparse semantic map of the environment. No prior knowledge of the objects is required, which is a significant advantage over other works. We test our approach on a standard RGB-D dataset comparing its performance with the state of the art SLAM algorithms. We also perform several challenging indoor experiments validating our approach in presence of distinct environmental conditions and furthermore test it on board an aerial robot.

show abstract

“…Differently, the work presented in [137] uses cuboids as objects' representation, where an object SLAM system is proposed. The system relies on observations from a monocular camera and exploits dynamic objects in the scene to improve localization by adding motion model constraints to the multi-view BA formulation that is used to solve the optimization problem.…”

Section: Handling Dynamics In the Scenementioning

confidence: 99%

“…In [54] and [137], SLAM systems are developed based on features from all three levels; points, planes, and objects.…”

Section: Low- Middle- and High-level Feature-based Approachesmentioning

confidence: 99%

“…Using points, planes, and objects, observed through a monocular camera, the work presented in [137] achieves improved localization, especially in absence of loop closure, compared to state-of-the-art SLAM systems. This is attributed to the long-range observability of objects and planes which facilitates more associations between old and new measurements.…”

Section: Low- Middle- and High-level Feature-based Approachesmentioning

confidence: 99%

See 1 more Smart Citation

Feature-based visual simultaneous localization and mapping: a survey

Azzam

Taha²,

Huang

et al. 2020

SN Appl. Sci.

View full text Add to dashboard Cite

Visual simultaneous localization and mapping (SLAM) has attracted high attention over the past few years. In this paper, a comprehensive survey of the state-of-the-art feature-based visual SLAM approaches is presented. The reviewed approaches are classified based on the visual features observed in the environment. Visual features can be seen at different levels; low-level features like points and edges, middle-level features like planes and blobs, and high-level features like semantically labeled objects. One of the most critical research gaps regarding visual SLAM approaches concluded from this study is the lack of generality. Some approaches exhibit a very high level of maturity, in terms of accuracy and efficiency. Yet, they are tailored to very specific environments, like feature-rich and static environments. When operating in different environments, such approaches experience severe degradation in performance. In addition, due to software and hardware limitations, guaranteeing a robust visual SLAM approach is extremely challenging. Although semantics have been heavily exploited in visual SLAM, understanding of the scene by incorporating relationships between features is not yet fully explored. A detailed discussion of such research challenges is provided throughout the paper.

show abstract

Monocular Object and Plane SLAM in Structured Environments

Cited by 90 publications

References 33 publications

An Improved Deep Residual Network-Based Semantic Simultaneous Localization and Mapping Method for Monocular Vision Robot

An Improved Deep Residual Network-Based Semantic Simultaneous Localization and Mapping Method for Monocular Vision Robot

VPS-SLAM: Visual Planar Semantic SLAM for Aerial Robotic Systems

Feature-based visual simultaneous localization and mapping: a survey

Contact Info

Product

Resources

About