Hybrid Bird’s-Eye Edge Based Semantic Visual SLAM for Automated Valet Parking

Xiang, Zhenzhen; Bao, Anbo; Su, Jianbo

doi:10.1109/icra48506.2021.9560900

Cited by 12 publications

(13 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…X. Shao [23] establishes tightly-coupled semantic SLAM with visual, inertial, and surround-view sensors. Z. Xiang [24] utilizes hybrid edge information from bird's-eye view images to enhance semantic SLAM, while C. Zhang [25] leverages HD vector map directories for parking lot localization. These studies offer valuable insights for future research.…”

Section: Semantic Visual Slam For Avpmentioning

confidence: 99%

“…The world distances were measured using a high-precision laser rangefinder, while the map distances were computed from the respective 3D point coordinates. absolute error, maximum error, and root mean square error (RMSE) between these map distances and world distances, and attaches experimental data from the AVP-SLAM [22] and BEV Edge SLAM [24] for comparison. It should be noted that the authors of these two methods have not opensourced them, so the data in the table are derived from the literature.…”

Section: B Robustness and Accuracy Of Mappingmentioning

confidence: 99%

See 1 more Smart Citation

A Semantic Slam System Based on Visual-Inertial Information and around View Images for Underground Parking Lot

Xiao

et al. 2021

SAE Technical Paper Series

View full text Add to dashboard Cite

Automated Valet Parking (AVP) requires precise localization in challenging garage conditions, including poor lighting, sparse textures, repetitive structures, dynamic scenes, and the absence of Global Positioning System (GPS) signals, which often pose problems for conventional localization methods. To address these adversities, we present AVM-SLAM, a semantic visual SLAM framework with multi-sensor fusion in a Bird's Eye View (BEV). Our framework integrates four fisheye cameras, four wheel encoders, and an Inertial Measurement Unit (IMU). The fisheye cameras form an Around View Monitor (AVM) subsystem, generating BEV images. Convolutional Neural Networks (CNNs) extract semantic features from these images, aiding in mapping and localization tasks. These semantic features provide long-term stability and perspective invariance, effectively mitigating environmental challenges. Additionally, data fusion from wheel encoders and IMU enhances system robustness by improving motion estimation and reducing drift. To validate AVM-SLAM's efficacy and robustness, we provide a large-scale, high-resolution underground garage dataset, available at https://github.com/yale-cv/avm-slam. This dataset enables researchers to further explore and assess AVM-SLAM in similar environments.

show abstract

Section: Semantic Visual Slam For Avpmentioning

confidence: 99%

Section: B Robustness and Accuracy Of Mappingmentioning

confidence: 99%

A Semantic Slam System Based on Visual-Inertial Information and around View Images for Underground Parking Lot

Xiao

et al. 2021

SAE Technical Paper Series

View full text Add to dashboard Cite

show abstract

“…AVM provides a bird’s eye view image using cameras facing in four different directions. Many studies [ 5 , 6 , 7 ] have applied AVM-based visual SLAM to parking scenarios by taking advantage of wide FOV and no motion bias. These studies have used road-marking information as semantic features to avoid the deformation caused by Inverse Perspective Mapping (IPM).…”

Section: Introductionmentioning

confidence: 99%

“…Alternatively, in [ 5 , 6 ], they avoided the influence of distortion errors by utilizing an additional Inertial Measurement Unit (IMU) sensor based on a pre-built map or leveraging an externally provided High Definition (HD) vector map. The approach of [ 7 ] attempted to create an accurate map in real-time using the sliding window fusion technique without additional information, but it exhibited insufficient accuracy in pose estimation for autonomous parking.…”

Section: Introductionmentioning

confidence: 99%

“…In contrast to conventional data creation methods which entail human effort in manually annotating ground truth data for each raw data, the proposed data creation framework automatically generates data by utilizing three-dimensional (3D) Light Detection and Ranging (LiDAR) SLAM. By employing parking line points with varying weights based on the degree of distortion error, the proposed SLAM has shown an improved localization performance with an average reduction of 39% in error compared with the modified approach of Hybrid Bird’s-Eye Edge-Based Semantic Visual SLAM [ 7 ] when implemented in various real-world parking lots.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Accurate Visual Simultaneous Localization and Mapping (SLAM) against Around View Monitor (AVM) Distortion Error Using Weighted Generalized Iterative Closest Point (GICP)

Lee,

Kim,

Ahn

et al. 2023

Sensors

View full text Add to dashboard Cite

Accurately estimating the pose of a vehicle is important for autonomous parking. The study of around view monitor (AVM)-based visual Simultaneous Localization and Mapping (SLAM) has gained attention due to its affordability, commercial availability, and suitability for parking scenarios characterized by rapid rotations and back-and-forth movements of the vehicle. In real-world environments, however, the performance of AVM-based visual SLAM is degraded by AVM distortion errors resulting from an inaccurate camera calibration. Therefore, this paper presents an AVM-based visual SLAM for autonomous parking which is robust against AVM distortion errors. A deep learning network is employed to assign weights to parking line features based on the extent of the AVM distortion error. To obtain training data while minimizing human effort, three-dimensional (3D) Light Detection and Ranging (LiDAR) data and official parking lot guidelines are utilized. The output of the trained network model is incorporated into weighted Generalized Iterative Closest Point (GICP) for vehicle localization under distortion error conditions. The experimental results demonstrate that the proposed method reduces localization errors by an average of 39% compared with previous AVM-based visual SLAM approaches.

show abstract

Multi-camera Visual-Inertial Simultaneous Localization and Mapping for Autonomous Valet Parking

Abate,

Schwartz,

Wong

et al. 2024

Springer Proceedings in Advanced Robotics

View full text Add to dashboard Cite

Hybrid Bird’s-Eye Edge Based Semantic Visual SLAM for Automated Valet Parking

Cited by 12 publications

References 29 publications

A Semantic Slam System Based on Visual-Inertial Information and around View Images for Underground Parking Lot

A Semantic Slam System Based on Visual-Inertial Information and around View Images for Underground Parking Lot

Accurate Visual Simultaneous Localization and Mapping (SLAM) against Around View Monitor (AVM) Distortion Error Using Weighted Generalized Iterative Closest Point (GICP)

Multi-camera Visual-Inertial Simultaneous Localization and Mapping for Autonomous Valet Parking

Contact Info

Product

Resources

About