MSDPN: Monocular Depth Prediction with Partial Laser Observation using Multi-stage Neural Networks

Lim, Hyungtae; Gil, Hyeonjae; Myung, Hyun

doi:10.1109/iros45743.2020.9340767

Cited by 6 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dong-hoon Kwak et al [9] attempted to improve the accuracy by incorporating segmentation images, into the training of the CycleGAN model. H. Lim et al [10] and Y. Liao et al [11] attempted to incorporate depth information. They obtained depth information from partial laser scanning.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Monocular Depth Estimation Using a Deep Learning Model with Pre-Depth Estimation based on Size Perspective

Asano,

Yasumura

2023

Artificial Intelligence and Applications

View full text Add to dashboard Cite

In this paper, For the task of the depth map of a scene given a single RGB image. We present an estimation method using a deep learning model that incorporates size perspective (size constancy cues). By utilizing a size perspective, the proposed method aims to address the difficulty of depth estimation tasks which stems from the limited correlation between the information inherent to objects in RGB images (such as shape and color) and their corresponding depths. The proposed method consists of two deep learning models, a size perspective model and a depth estimation model, The size-perspective model plays a role like that of the size perspective and estimates approximate depths for each object in the image based on the size of the object's bounding box and its actual size. Based on these rough depth estimation (pre-depth estimation) results, A depth image representing through depths of each object (pre-depth image) is generated and this image is input with the RGB image into the depth estimation model. The pre-depth image is used as a hint for depth estimation and improves the performance of the depth estimation model. With the proposed method, it becomes possible to obtain depth inputs for the depth estimation model without using any devices other than a monocular camera be forehand. The proposed method contributes to the improvement in accuracy when there are objects present in the image that can be detected by the object detection model. In the experiments using an original indoor scene dataset, the proposed method demonstrated improvement in accuracy compared to the method without pre-depth images.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Optimizer : Adam (The initial learning rate was set to lr=0.001, and a scheduler was used to perform a learning rate decay of 0.8 at the epochs [5,10,15,20,22]. ), Loss Function：Inverse Huber loss (referring to the study by I. Laina et al [1]).…”

Section: Loss Function：mselossmentioning

confidence: 99%

Monocular Depth Estimation Using a Deep Learning Model with Pre-Depth Estimation based on Size Perspective

Asano,

Yasumura

2023

Artificial Intelligence and Applications

View full text Add to dashboard Cite

show abstract

“…3D LiDAR sensors are relatively expensive compared with other sensors but they can acquire long-range measurements, as well as provide centimeter-level accuracy. These advantages allow LiDAR sensors to be used for various tasks, for instance, localization [11], point cloud registration [12]- [14], mapping [15], [16], and so forth.…”

Section: Introductionmentioning

confidence: 99%

PaGO-LOAM: Robust Ground-Optimized LiDAR Odometry

Seo¹,

Lim²,

Lee³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Numerous researchers have conducted studies to achieve fast and robust ground-optimized LiDAR odometry methods for terrestrial mobile platforms. In particular, groundoptimized LiDAR odometry usually employs ground segmentation as a preprocessing method. This is because most of the points in a 3D point cloud captured by a 3D LiDAR sensor on a terrestrial platform are from the ground. However, the effect of the performance of ground segmentation on LiDAR odometry is still not closely examined. In this paper, a robust ground-optimized LiDAR odometry framework is proposed to facilitate the study to check the effect of ground segmentation on LiDAR SLAM based on the state-of-the-art (SOTA) method. By using our proposed odometry framework, it is easy and straightforward to test whether ground segmentation algorithms help extract well-described features and thus improve SLAM performance. In addition, by leveraging the SOTA ground segmentation method called Patchwork, which shows robust ground segmentation even in complex and uneven urban environments with little performance perturbation, a novel ground-optimized LiDAR odometry is proposed, called PaGO-LOAM. The methods were tested using the KITTI odometry dataset. PaGO-LOAM shows robust and accurate performance compared with the baseline method. Our code is available at https://github.com/url-kaist/AlterGround-LeGO-LOAM

show abstract

What if there was no revisit? Large-scale graph-based SLAM with traffic sign detection in an HD map using LiDAR inertial odometry

Sung

Jeon

Lim

et al. 2021

Intel Serv Robotics

View full text Add to dashboard Cite

MSDPN: Monocular Depth Prediction with Partial Laser Observation using Multi-stage Neural Networks

Cited by 6 publications

References 28 publications

Monocular Depth Estimation Using a Deep Learning Model with Pre-Depth Estimation based on Size Perspective

Monocular Depth Estimation Using a Deep Learning Model with Pre-Depth Estimation based on Size Perspective

PaGO-LOAM: Robust Ground-Optimized LiDAR Odometry

What if there was no revisit? Large-scale graph-based SLAM with traffic sign detection in an HD map using LiDAR inertial odometry

Contact Info

Product

Resources

About