Real-Time Monocular Object-Model Aware Sparse SLAM

Hosseinzadeh, Mehdi; Li, Kejie; Latif, Yasir; Reid, Ian

doi:10.1109/icra.2019.8793728

Cited by 65 publications

(41 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The algorithm requires the object’s surface to have apparent texture and known object size prior, which limits the application range. Hosseinzadeh et al [ 34 ] proposed to use a CNN model to recover the three-dimensional object point cloud from a single-frame image. However, the proposed network model requires a large amount of training data, and the generalization ability in the real environment needs further verification.…”

Section: Related Workmentioning

confidence: 99%

RGB-D Object SLAM Using Quadrics for Indoor Environments

Liao

Wang

et al. 2020

Sensors

View full text Add to dashboard Cite

Indoor service robots need to build an object-centric semantic map to understand and execute human instructions. Conventional visual simultaneous localization and mapping (SLAM) systems build a map using geometric features such as points, lines, and planes as landmarks. However, they lack a semantic understanding of the environment. This paper proposes an object-level semantic SLAM algorithm based on RGB-D data, which uses a quadric surface as an object model to compactly represent the object’s position, orientation, and shape. This paper proposes and derives two types of RGB-D camera-quadric observation models: a complete model and a partial model. The complete model combines object detection and point cloud data to estimate a complete ellipsoid in a single RGB-D frame. The partial model is activated when the depth data is severely missing because of illuminations or occlusions, which uses bounding boxes from object detection to constrain objects. Compared with the state-of-the-art quadric SLAM algorithms that use a monocular observation model, the RGB-D observation model reduces the requirements of the observation number and viewing angle changes, which helps improve the accuracy and robustness. This paper introduces a nonparametric pose graph to solve data associations in the back end, and innovatively applies it to the quadric surface model. We thoroughly evaluated the algorithm on two public datasets and an author-collected mobile robot dataset in a home-like environment. We obtained obvious improvements on the localization accuracy and mapping effects compared with two state-of-the-art object SLAM algorithms.

show abstract

Section: Related Workmentioning

confidence: 99%

RGB-D Object SLAM Using Quadrics for Indoor Environments

Liao

Wang

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Object detection at the instance level was performed to build a map with object models as central entities, which was one level higher than semantic mapping based on pure semantic segmentation. In [40], by using the CNN-based object detector and the CNN-based plane detector, the semantic object and plane structure are included in BA. The proposed method can enrich the reconstruction map semantically and improve the positioning (pose estimation) of the camera significantly.…”

Section: Semantic Mapping and Semantic Slammentioning

confidence: 99%

Coarse Semantic-Based Motion Removal for Robust Mapping in Dynamic Environments

Wang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

SLAM in dynamic environments is still a severe challenge for most feature-based SLAM systems. Moving objects will lead to terrible errors in the calculation of frame tracking and local mapping. We propose a novel method for keypoints selection to lower the negative effect brought by moving objects during map construction. To address this challenge, we concentrate on the combination of coarse semantic information and a feature-based SLAM system. In this article, a modified CenterNet object detector is proposed as the moving object detection thread for providing coarse semantic information and 2D location. The modified CenterNet can provide a faster and more accurate prediction. For each frame in a sequence, objects in a scenario will be classified into two motion states, non-static and static, according to the category prediction from the moving object detection thread. Then important processing called semantic data association is presented for motion removal in frame tracking thread and local mapping thread. In this way, the keypoints on the non-static objects will not be chosen for calculation. Finally, on this basis, a modified real-time SLAM system is presented. Experimental results in TUM indoor dataset show that the proposed SLAM system outperforms the state-of-the-art ORB-SLAM2 in dynamic environments. Besides that, our method has a better speed-accuracy trade-off than other deep learning-based SLAM systems in dynamic environments. INDEX TERMS Simultaneous localization and mapping, motion removal, dynamic environments, object detection.

show abstract

“…As a low-cost solution, V-SLAM technology has lower requirements on its hardware system. 1 –6 Therefore, it has preliminary applications in many fields, such as robot industry, virtual reality, and autonomous driving. 7,8 However, the state-of-the-art V-SLAMs are usually sensitive to the sparse landmarks in the environment and large view transformation of camera motion.…”

Section: Introductionmentioning

confidence: 99%

A visual simultaneous localization and mapping approach based on scene segmentation and incremental optimization

Zhang

Liu

Zheng

et al. 2020

International Journal of Advanced Robotic Systems

View full text Add to dashboard Cite

Existing visual simultaneous localization and mapping (V-SLAM) algorithms are usually sensitive to the situation with sparse landmarks in the environment and large view transformation of camera motion, and they are liable to generate large pose errors that lead to track failures due to the decrease of the matching rate of feature points. Aiming at the above problems, this article proposes an improved V-SLAM method based on scene segmentation and incremental optimization strategy. In the front end, this article proposes a scene segmentation algorithm considering camera motion direction and angle. By segmenting the trajectory and adding camera motion direction to the tracking thread, an effective prediction model of camera motion in the scene with sparse landmarks and large view transformation is realized. In the back end, this article proposes an incremental optimization method combining segmentation information and an optimization method for tracking prediction model. By incrementally adding the state parameters and reusing the computed results, high-precision results of the camera trajectory and feature points are obtained with satisfactory computing speed. The performance of our algorithm is evaluated by two well-known datasets: TUM RGB-D and NYUDv2 RGB-D. The experimental results demonstrate that our method improves the computational efficiency by 10.2% compared with state-of-the-art V-SLAMs on the desktop platform and by 22.4% on the embedded platform, respectively. Meanwhile, the robustness of our method is better than that of ORB-SLAM2 on the TUM RGB-D dataset.

show abstract

Real-Time Monocular Object-Model Aware Sparse SLAM

Cited by 65 publications

References 39 publications

RGB-D Object SLAM Using Quadrics for Indoor Environments

RGB-D Object SLAM Using Quadrics for Indoor Environments

Coarse Semantic-Based Motion Removal for Robust Mapping in Dynamic Environments

A visual simultaneous localization and mapping approach based on scene segmentation and incremental optimization

Contact Info

Product

Resources

About