A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Point-cloud-based place recognition using CNN feature extraction
[article]
2018
arXiv
pre-print
Preserved Fulltext
This paper proposes a novel point-cloud-based place recognition system that adopts a deep learning approach for feature extraction. ...
Apart from the system itself, we also bring to the community a new place recognition dataset containing both point cloud and grayscale images covering a full 360^∘ environmental view. ...
Our focus in this work is point-cloud-based feature extraction using a CNN. ...
arXiv:1810.09631v1
fatcat:sguqdmc5yrccnmav3xkegxvmje
3D Recognition Based on Sensor Modalities for Robotic Systems: A Survey
2021
Sensors
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Instigated by the recognition capability of social robots, we present the analysis of data representation methods based on sensor modalities for 3D object and place recognition using deep learning models ...
This survey is intended to show how recent developments in 3D visual recognition based on sensor modalities using deep-learning-based approaches can lay the groundwork to inspire further research and serves ...
features LiDAR Point Cloud based extraction with CNN Large scale place recognition Lpd-net [83] Outdoor scenario with feature extraction using global LiDAR Point Cloud based descriptors Oriented recognition ...
doi:10.3390/s21217120
pmid:34770429
pmcid:PMC8587961
fatcat:qqoqlkaycbc4xk24j7j2nzqabe
CNN-BASED PLACE RECOGNITION TECHNIQUE FOR LIDAR SLAM
2020
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
To mitigate this problem, state-of-art Convolutional Neural Networks (CNNs)-based 3D descriptors may be directly applied to 3D point clouds. ...
Place recognition in 3D point clouds is a challenging task which is traditionally handled with the aid of other sensors, such as camera and GPS. ...
CNN-based classifier, NN and RF by using the same set of global feature descriptors extracted from testing datasets. ...
doi:10.5194/isprs-archives-xliv-m-2-2020-117-2020
fatcat:6wzdco6wcvcrdaooyvctmvh2bq
Learning 3D Segment Descriptors for Place Recognition
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this work we leverage a segment extraction and matching approach to achieve place recognition in Light Detection and Ranging (LiDAR) based 3D point cloud maps. ...
Most place recognition methods rely on images, point clouds, or a combination of both. ...
Particularly, this work focuses on the SegMatch method for performing place recognition in 3D point clouds, which is based on comparing segments extracted from a point cloud with previously observed segments ...
arXiv:1804.09270v1
fatcat:vulys5bk7vc45oqc6solus6cvy
CNN-Based Classification for Point Cloud Object With Bearing Angle Image
2021
IEEE Sensors Journal
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
The main contribution of this paper is proposing an efficient recognition method that uses the information from point clouds only. ...
Those individual point cloud objects are converted to bearing angle (BA) images. Then, a well-trained CNN is used to classify objects with BA images. ...
While the local feature-based methods use the 3D features derived by a point and its neighbors, the global feature-based approaches use the features extracted from the whole objects for recognition, e.g ...
doi:10.1109/jsen.2021.3130268
fatcat:4n2wpu3ykbdexmv6jcaph33lim
LPD-Net: 3D Point Cloud Learning for Large-Scale Place Recognition and Environment Analysis
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2018 pre-print arXiv:1812.07050v1 fatcat:zynhi2qxvrcy3montmqxl7z7lq
Point cloud based place recognition is still an open issue due to the difficulty in extracting local features from the raw 3D point cloud and generating the global descriptor, and it's even harder in the ...
We implement the proposed global descriptor in solving point cloud based retrieval tasks to achieve the large-scale place recognition. ...
Current solutions for environment analysis and place recognition mainly fall into two categories, image-based and 3D point cloud-based. ...
arXiv:1812.07050v2
fatcat:wryxaqevtjh4po4hk2rvb4wn5a
Activity Recognition Based on Millimeter-Wave Radar by Fusing Point Cloud and Range–Doppler Information
2022
Signals
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
We adopt a CNN–LSTM model to extract the time-serial features from point clouds and a CNN model to obtain the features from range–Doppler. ...
In previous studies, researchers mostly analyzed either 2D (3D) point cloud or range–Doppler information from radar echo to extract activity features. ...
For example, in [10] , the experimenters converted the obtained point cloud data into micro-Doppler features and used CNN to extract the features to classify actions. ...
doi:10.3390/signals3020017
fatcat:nrelwuklyraknmyhsiqnyuhlza
PIC-Net: Point Cloud and Image Collaboration Network for Large-Scale Place Recognition
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Place recognition is one of the hot research fields in automation technology and is still an open issue, Camera and Lidar are two mainstream sensors used in this task, Camera-based methods are easily affected ...
to fuse the features of image and point cloud, and mine the complementary information between the two. ...
RELATED WORK In this section, we review other place recognition works, including image-based, point cloud-based and image and point cloud fusion-based place recognition methods. ...
arXiv:2008.00658v1
fatcat:ognqwld5zredrir3x2nsesdc6m
Viewpoint invariant semantic object and scene categorization with RGB-D sensors
2018
Autonomous Robots
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We address these problems and propose a generic deep learning framework based on a pre-trained convolutional neural network (CNN), as a feature extractor for both the colour and depth channels. ...
Extensive evaluations on four RGB-D object and scene recognition datasets demonstrate that our HP-CNN and HP-CNN-T consistently outperforms state-of-the-art methods for several recognition tasks by a significant ...
input encoding a) depth image and b) point cloud object-centric encoding before feature extraction. ...
doi:10.1007/s10514-018-9776-8
fatcat:spg6rdzgbrhpxpbuedqr2th2pe
Novel CE-CBCE feature extraction method for object classification using a low-density LiDAR point cloud
2021
PLoS ONE
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
To achieve reliable feature extraction from a sparse LiDAR point cloud, this paper proposes a novel Clustered Extraction and Centroid Based Clustered Extraction Method (CE-CBCE) method for feature extraction ...
The integration of the CE-CBCE and CNN methods enable us to utilize lightweight actuated LiDAR input and provides low computing means of classification while maintaining accurate detection. ...
Thus, this paper proposes an object recognition system with multiple feature extraction based on segregated clusters from LiDAR point clouds. ...
doi:10.1371/journal.pone.0256665
pmid:34432855
pmcid:PMC8386852
fatcat:b6fwtwjiknce3d5ivgtcickrqq
Place recognition survey: An update on deep learning approaches
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2106.10458v2 fatcat:hbw47qq2mjhsjhfb5t5vw4wfceOther Versions
This paper surveys recent approaches and methods used in place recognition, particularly those based on deep learning. ...
The contributions of this work are twofold: surveying recent sensors such as 3D LiDARs and RADARs, applied in place recognition; and categorizing the various DL-based place recognition works into supervised ...
[13] uses 3D point clouds to address the global localization problem, proposing a place recognition and metric pose estimation approach. ...
arXiv:2106.10458v3
fatcat:bbfv4qympffaphojhxkc4og4am
CLASSIFICATION OF POLE-LIKE OBJECTS USING POINT CLOUDS AND IMAGES CAPTURED BY MOBILE MAPPING SYSTEMS
2018
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
The first method used only point-clouds, the second used only images, and the third used both point-clouds and images. ...
The feature values of a point-cloud are calculated by point processing, and the ones of the cropped image are calculated using a convolutional neural network. ...
In our method, poles and target objects were extracted from point-clouds, and feature values were calculated using point-clouds. ...
doi:10.5194/isprs-archives-xlii-2-731-2018
fatcat:grs6ojnanbghjlrjgmzcyivcza
OREOS: Oriented Recognition of 3D Point Clouds in Outdoor Scenarios
2019
2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We introduce a novel method for oriented place recognition with 3D LiDAR scans. A Convolutional Neural Network is trained to extract compact descriptors from single 3D LiDAR scans. ...
These can be used both to retrieve near-by place candidates from a map, and to estimate the yaw discrepancy needed for bootstrapping local registration methods. ...
[11] transformed a point cloud to a range or bearing-angle based image by extracting local-invariant ORB [12] features for database matching. ...
doi:10.1109/iros40897.2019.8968094
dblp:conf/iros/SchauppBDSC19
fatcat:chckxkzkgfekvmefdb66emrai4
OREOS: Oriented Recognition of 3D Point Clouds in Outdoor Scenarios
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
We introduce a novel method for oriented place recognition with 3D LiDAR scans. A Convolutional Neural Network is trained to extract compact descriptors from single 3D LiDAR scans. ...
These can be used both to retrieve near-by place candidates from a map, and to estimate the yaw discrepancy needed for bootstrapping local registration methods. ...
[12] transformed a point cloud to a range or bearing-angle based image by extracting local-invariant ORB [13] features for database matching. ...
arXiv:1903.07918v1
fatcat:2scnozweabepziyh6cfl6vxph4
Pointwise CNN for 3D Object Classification on Point Cloud
2021
Journal of Information Processing Systems
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Three-dimensional (3D) object classification tasks using point clouds are widely used in 3D modeling, face recognition, and robotic missions. ...
Finally, based on the extracted features, fully connected layers predict the class labels of objects. We evaluated the proposed pointwise CNN structure on the ModelNet10 dataset. ...
[24] converted point clouds to a surfacecondition-feature map for feature extraction using an autoencoder. The geometric features extracted work well even with extremely noisy data. Su et al. ...
doi:10.3745/jips.02.0160
dblp:journals/jips/SongLTF21
fatcat:jeq2oyvb4rhupgcqzuntygrg4u
« Previous
Showing results 1 — 15 out of 8,064 results