Improving a Background Model for Tracking and Classification of Objects in LiDAR 3D Point Clouds
(2022) In Master's Theses in Mathematical Sciences FMAM05 20221Mathematics (Faculty of Engineering)
- Abstract
- This thesis studied methods of improving a background model for a data processing
pipeline of LiDAR point clouds. For this, two main approaches were
evaluated. The first was to implement and compare three different models for
detecting ground in a point cloud. These were based on more classical modeling
approaches. The second was to use Deep Learning for semantic segmentation of
point clouds and to use this information in a background filtering model with the
hope of achieving better filtering of dynamic background. These methods were
combined in a pipeline as an example of a possible application. The performance
of the ground models was primarily evaluated based on their ability of classifying
points as ground or non-ground.... (More) - This thesis studied methods of improving a background model for a data processing
pipeline of LiDAR point clouds. For this, two main approaches were
evaluated. The first was to implement and compare three different models for
detecting ground in a point cloud. These were based on more classical modeling
approaches. The second was to use Deep Learning for semantic segmentation of
point clouds and to use this information in a background filtering model with the
hope of achieving better filtering of dynamic background. These methods were
combined in a pipeline as an example of a possible application. The performance
of the ground models was primarily evaluated based on their ability of classifying
points as ground or non-ground. However, well performing ground models
have further uses. Of the three models studied, the Hybrid model achieved most
promising results. For semantic segmentation, RandLA-NET was used for its
ability to process large scale point clouds at high speeds. Variations of the
network was trained on simulated data for which all networks achieved similar
good performance for classes ground, vegetation and other. When testing domain
transfer to point clouds produced by a Real Physical LiDAR, mixed results
were achieved with variations on a per-point-cloud basis. On a lot of instances
however, very promising results could be seen. A background subtraction model
based on a 3D Density Static Filter was extended to include semantic information
from the neural network. For this filter, voxels classified as vegetation and
their neighbours, heavily filtered out points. This was to avoid issues of false
detections caused by wind. The model was tested on parts of two LiDAR recordings
and compared to the standard filter. Based on this, the extended model
was found to better filter out vegetation in windy conditions. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/9090366
- author
- Doyle, Seamus LU and Nilsson, Gustav
- supervisor
- organization
- alternative title
- Förbättring av en bakgrundsmodell för följning och klassificering av objekt i LiDAR-genererade 3D punktmoln
- course
- FMAM05 20221
- year
- 2022
- type
- H2 - Master's Degree (Two Years)
- subject
- keywords
- LiDAR, Semantic Segmentation, Neural Networks, RandLA-NET, 3D Point Cloud, Gaussian Process Regression, Robust Locally Weighted Regression, CARLA, Ground Model
- publication/series
- Master's Theses in Mathematical Sciences
- report number
- LUTFMA-3472-2022
- ISSN
- 1404-6342
- other publication id
- 2022:E23
- language
- English
- id
- 9090366
- date added to LUP
- 2022-06-29 13:56:32
- date last changed
- 2022-06-30 14:47:34
@misc{9090366, abstract = {{This thesis studied methods of improving a background model for a data processing pipeline of LiDAR point clouds. For this, two main approaches were evaluated. The first was to implement and compare three different models for detecting ground in a point cloud. These were based on more classical modeling approaches. The second was to use Deep Learning for semantic segmentation of point clouds and to use this information in a background filtering model with the hope of achieving better filtering of dynamic background. These methods were combined in a pipeline as an example of a possible application. The performance of the ground models was primarily evaluated based on their ability of classifying points as ground or non-ground. However, well performing ground models have further uses. Of the three models studied, the Hybrid model achieved most promising results. For semantic segmentation, RandLA-NET was used for its ability to process large scale point clouds at high speeds. Variations of the network was trained on simulated data for which all networks achieved similar good performance for classes ground, vegetation and other. When testing domain transfer to point clouds produced by a Real Physical LiDAR, mixed results were achieved with variations on a per-point-cloud basis. On a lot of instances however, very promising results could be seen. A background subtraction model based on a 3D Density Static Filter was extended to include semantic information from the neural network. For this filter, voxels classified as vegetation and their neighbours, heavily filtered out points. This was to avoid issues of false detections caused by wind. The model was tested on parts of two LiDAR recordings and compared to the standard filter. Based on this, the extended model was found to better filter out vegetation in windy conditions.}}, author = {{Doyle, Seamus and Nilsson, Gustav}}, issn = {{1404-6342}}, language = {{eng}}, note = {{Student Paper}}, series = {{Master's Theses in Mathematical Sciences}}, title = {{Improving a Background Model for Tracking and Classification of Objects in LiDAR 3D Point Clouds}}, year = {{2022}}, }