SegMap: Segment-based mapping and localization using data-driven descriptors

Dubé, Renaud; Cramariuc, Andrei; Dugas, Daniel; Sommer, Hannes; Dymczyk, Marcin; Nieto, Juan; Siegwart, Roland; Cadena, César

doi:10.1177/0278364919863090

Cited by 173 publications

(100 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SegMap aims to extract meaningful features for global retrieval while the semantic class types were limited to vehicles, buildings, and others. The performance of SegMap is further improved in [ 110 ].…”

Section: Role Of Deep Learning In Loop Closure Detectionmentioning

confidence: 99%

Role of Deep Learning in Loop Closure Detection for Visual and Lidar SLAM: A Survey

Arshad

Kim

2021

Sensors

View full text Add to dashboard Cite

Loop closure detection is of vital importance in the process of simultaneous localization and mapping (SLAM), as it helps to reduce the cumulative error of the robot’s estimated pose and generate a consistent global map. Many variations of this problem have been considered in the past and the existing methods differ in the acquisition approach of query and reference views, the choice of scene representation, and associated matching strategy. Contributions of this survey are many-fold. It provides a thorough study of existing literature on loop closure detection algorithms for visual and Lidar SLAM and discusses their insight along with their limitations. It presents a taxonomy of state-of-the-art deep learning-based loop detection algorithms with detailed comparison metrics. Also, the major challenges of conventional approaches are identified. Based on those challenges, deep learning-based methods were reviewed where the identified challenges are tackled focusing on the methods providing long-term autonomy in various conditions such as changing weather, light, seasons, viewpoint, and occlusion due to the presence of mobile objects. Furthermore, open challenges and future directions were also discussed.

show abstract

Section: Role Of Deep Learning In Loop Closure Detectionmentioning

confidence: 99%

Role of Deep Learning in Loop Closure Detection for Visual and Lidar SLAM: A Survey

Arshad

Kim

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…We consider that the reserved points will meet the needs of location positioning from two aspects. Firstly, the local feature based maps are widely used for precise registration or localization [3], [10], [11]. Edges, walls or semantic objects are mainly used for robust matching in these papers.…”

Section: Map Compression Comparisonmentioning

confidence: 99%

“…In this paper, the idea is extended to the LiDAR maps by proposing an optimization strategy to approximate the solution of original programming problem within tractable time. In many other papers, geometric features or semantics can also be extracted for robust localization [3], [10], [11], so we think the geometric properties might also be correlated with the localization performance. Combing with these existing works, the second hypothesis is raised that the observation count is correlated to the geometric property of point cloud map, which makes the method possible to adapt to the new environments.…”

mentioning

confidence: 99%

3D LiDAR Map Compression for Efficient Localization on Resource Constrained Vehicles

Yin

Wang

Tang

et al. 2021

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Large scale 3D maps constructed via LiDAR sensor are widely used on intelligent vehicles for localization in outdoor scenes. However, loading, communication and processing of the original dense maps are time consuming for onboard computing platform, which calls for a more concise representation of maps to reduce the complexity but keep the performance of localization. In this paper, we propose a teacher-student learning paradigm to compress the 3D point cloud map. Specifically, we first find a subset of LiDAR points with high number of observations to preserve the localization performance, which is regarded as the teacher of map compression. An efficient optimization strategy is proposed to deal with the massive data in original map. With the supervision of compressed map, a student model is built by training a random forest model fed with geometric feature descriptors of each point. As a result, the student model is able to compress the map without referring to the expensive numerical optimization. Additionally, by incorporating the features, the innovative student model can be generalized to other new maps while no re-training is required. We conduct thorough experiments on multi-session dataset and KITTI dataset to demonstrate the effectiveness and efficiency of the proposed learning paradigm, and the comparison with other map compression methods. The final results show that the learned student model can achieve efficient map compression with comparable LiDAR based localization performance to the original map at the same time.

show abstract

“…It incrementally integrates semantic information into a dense 3-D map. Dube et al proposed SegMap [ 33 ] which is segment-based mapping using data-driven descriptors. The proposed descriptor was extracted by a neural network and the descriptor was used for mapping.…”

Section: Related Workmentioning

confidence: 99%

Semantic Point Cloud Mapping of LiDAR Based on Probabilistic Uncertainty Modeling for Autonomous Driving

Cho

Kim

Park

et al. 2020

Sensors

View full text Add to dashboard Cite

LiDAR-based Simultaneous Localization And Mapping (SLAM), which provides environmental information for autonomous vehicles by map building, is a major challenge for autonomous driving. In addition, the semantic information has been used for the LiDAR-based SLAM with the advent of deep neural network-based semantic segmentation algorithms. The semantic segmented point clouds provide a much greater range of functionality for autonomous vehicles than geometry alone, which can play an important role in the mapping step. However, due to the uncertainty of the semantic segmentation algorithms, the semantic segmented point clouds have limitations in being directly used for SLAM. In order to solve the limitations, this paper proposes a semantic segmentation-based LiDAR SLAM system considering the uncertainty of the semantic segmentation algorithms. The uncertainty is explicitly modeled by proposed probability models which are come from the data-driven approaches. Based on the probability models, this paper proposes semantic registration which calculates the transformation relationship of consecutive point clouds using semantic information with proposed probability models. Furthermore, the proposed probability models are used to determine the semantic class of the points when the multiple scans indicate different classes due to the uncertainty. The proposed framework is verified and evaluated by the KITTI dataset and outdoor environments. The experiment results show that the proposed semantic mapping framework reduces the errors of the mapping poses and eliminates the ambiguity of the semantic information of the generated semantic map.

show abstract

SegMap: Segment-based mapping and localization using data-driven descriptors

Cited by 173 publications

References 52 publications

Role of Deep Learning in Loop Closure Detection for Visual and Lidar SLAM: A Survey

Role of Deep Learning in Loop Closure Detection for Visual and Lidar SLAM: A Survey

3D LiDAR Map Compression for Efficient Localization on Resource Constrained Vehicles

Semantic Point Cloud Mapping of LiDAR Based on Probabilistic Uncertainty Modeling for Autonomous Driving

Contact Info

Product

Resources

About