LO-Net: Deep Real-Time Lidar Odometry

Li, Qing; Chen, Shaoyang; Wang, Cheng; Li, Xin; Wen, Chenglu; Cheng, Ming; Li, Jonathan

doi:10.1109/cvpr.2019.00867

Cited by 201 publications

(223 citation statements)

References 43 publications

(73 reference statements)

Supporting

Mentioning

200

Contrasting

Unclassified

Order By: Relevance

“…We compared our method with the ground truth trajectory and several LiDAR odometry estimation methods: ICP-point2point(ICP-po2po), ICP-point2plane (ICP-po2pl), GICP [26], CLS [29], LOAM [38], Velas et al [30], LO-Net [12]. Table 1 shows the evaluation results of the mentioned methods on the KITTI dataset.…”

Section: Discussionmentioning

confidence: 99%

“…CAE-LO [36] did not provide the results on KITTI Seq 00-10. LO-Net [12] is one of the best deep learning methods for LiDAR based odometry estimation. From Table 1, The Seq 07 and 08 are not used to train LodoNet.…”

Section: Discussionmentioning

confidence: 99%

“…Lyu et al [17,18] and RangeNet++ [19] improve the projection scheme by replacing the target plane with a sphere surface, in which LiDAR points are nearly uniformly distributed. SqueezeSeg V1 [33], V2 [34], and LO-Net [12] also employ this projection scheme and result in a good performance in LiDAR point semantic segmentation. In our work, we follow the projection scheme of RangeNet++ to generate a 2D LiDAR feature map for each LiDAR frame.…”

Section: Related Workmentioning

confidence: 99%

“…L3-Net [16] proposes a learning-based LiDAR localization system by comparing the network-based feature vector between the current LiDAR frame and pre-build point cloud map followed by a recurrent neural network based smoothness module. LO-Net [12] is another learning-based odometry estimator. Different from L3-Net that only extracts point-wise features, LO-Net projects the points onto a sphere surface and builds an image-like feature map for each LiDAR frame.…”

Section: Deep Learning-based Vehicle Odometry Estimationmentioning

confidence: 99%

“…Δ and Δ are the angular resolutions in the horizontal and vertical directions, respectively. The element at ( , ) of the spherical image is set to be the range value = 2 + 2 + 2 of the LiDAR point ( , , ) [12]. A matrix of size × × can be obtained by applying this projection.…”

Section: Data Prepossessingmentioning

confidence: 99%

See 4 more Smart Citations

LodoNet

Zheng

Lyu

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Deep learning based LiDAR odometry (LO) estimation attracts increasing research interests in the field of autonomous driving and robotics. Existing works feed consecutive LiDAR frames into neural networks as point clouds and match pairs in the learned feature space. In contrast, motivated by the success of image based feature extractors, we propose to transfer the LiDAR frames to image space and reformulate the problem as image feature extraction. With the help of scale-invariant feature transform (SIFT) for feature extraction, we are able to generate matched keypoint pairs (MKPs) that can be precisely returned to the 3D space. A convolutional neural network pipeline is designed for LiDAR odometry estimation by extracted MKPs. The proposed scheme, namely LodoNet, is then evaluated in the KITTI odometry estimation benchmark, achieving on par with or even better results than the state-of-the-art.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Deep Learning-based Vehicle Odometry Estimationmentioning

confidence: 99%

Section: Data Prepossessingmentioning

confidence: 99%

See 3 more Smart Citations

LodoNet

Zheng

Lyu

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

LiDAR‐based object detection for agricultural robots

Stronzek‐Pfeifer,

Chemmadan,

Patel

et al. 2023

Proc Appl Math and Mech

View full text Add to dashboard Cite

Light detection and ranging (LiDAR) sensors have proven to be a valuable tool to gather spatial information about the environment and are a crucial component in perception of autonomous systems. In the agricultural domain, state‐of‐the‐art algorithms for detection, classification, and tracking often utilize a combination of LiDAR and camera by fusing both semantic and spatial information. This is in part due to the availability of fast algorithms specifically optimized to make use of the convenient 2D data structure of RGB images. Still, there are limitations relying on cameras in agriculture because they highly depend on favorable lighting conditions and generally lack explicit geometric information, whereas LiDAR is especially advantageous in that regard as well as regarding range. This makes LiDAR particularly valuable for perception applications such as self‐localization, mapping, or object detection. The unstructured nature of 3D LiDAR point clouds, however, coupled with their possibly large size and density, presents a significant hurdle in terms of real‐time capability for these kinds of tasks. Object detection on 3D LiDAR sensor data is therefore challenging and solutions in agriculture usually are tied to very narrow use cases or rigorous down sampling to ensure real‐time applicability. Here, we present an algorithm featuring 2.5D map representations to avoid the computational drawbacks and ensure real‐time capability. We utilize established algorithms to project the 3D LiDAR data into two distinct maps and then apply object detection algorithms on each of those maps individually and to subsequently combine the information into a joint estimate. From the information stored in the 2.5D map, axis‐aligned bounding boxes for each object are computed containing information about position and dimensions. We present a proof of concept and assess the real‐time capability for a domain‐specific use case.

show abstract