A Deep Learning Approach to the Detection and Tracking of Moving Objects in 2D Point Clouds

Simple item page
dc.contributor.advisorShan, Jinjun
dc.contributor.authorSchofield, Hunter Liam
dc.date.accessioned2022-12-14T16:35:28Z
dc.date.available2022-12-14T16:35:28Z
dc.date.copyright2022-08-05
dc.date.issued2022-12-14
dc.date.updated2022-12-14T16:35:27Z
dc.degree.disciplineEarth & Space Science
dc.degree.levelMaster's
dc.degree.nameMSc - Master of Science
dc.description.abstractThe detection and tracking of moving objects (DATMO) are crucial tasks that any autonomous vehicle must perform. Autonomous vehicles must detect and track all obstacles to ensure safety within the environment while also completing their tasks efficiently. In autonomous driving research, LiDAR is becoming increasingly popular due to its high resolution and accuracy. There are many state-of-the-art DATMO methods using LiDAR, however, most methods are designed for 3D LiDAR sensors. Methods that work for 2D LiDAR sensors are not as robust as their 3D counterparts or require too many computational resources to run efficiently on less powerful robots. This research presents two robust solutions to the DATMO problem based on deep learning techniques that can scale to meet a variety of hardware constraints. The first solution, detect while track (DWT), combines a convolutional neural network (CNN) with a multiple hypothesis tracking (MHT) approach and Kalman filter. The second solution, pixel predictions for future-oriented bounding boxes (PIXFOR), combines a CNN with a recurrent network architecture to solve both detection and tracking problems in a single forward pass. Both methods are experimentally validated on an unmanned ground vehicle (UGV) operating on an intersection scenario and a highway scenario using 2D point clouds collected from simulation and hardware environments. The run-time performance of both methods is also validated different hardware platforms to show that the methods can scale to meet different hardware constraints. When compared to state-of-the-art DATMO methods, the newly proposed methods outperform in the object detection and tracking tasks, while operating at a faster run time on equivalent hardware.
dc.identifier.urihttp://hdl.handle.net/10315/40717
dc.languageen
dc.rightsAuthor owns copyright, except where explicitly noted. Please contact the author directly with licensing requests.
dc.subjectComputer science
dc.subjectArtificial intelligence
dc.subjectEngineering
dc.subject.keywordsComputer vision
dc.subject.keywordsLiDAR
dc.subject.keywordsArtificial Intelligence
dc.subject.keywordsDeep learning
dc.subject.keywordsMachine learning
dc.subject.keywordsObject detection
dc.subject.keywordsObject tracking
dc.subject.keywordsConvolutional network
dc.subject.keywordsRecurrent network
dc.subject.keywordsKalman filter
dc.titleA Deep Learning Approach to the Detection and Tracking of Moving Objects in 2D Point Clouds
dc.typeElectronic Thesis or Dissertation

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Schofield_Hunter_L_2022_Masters.pdf
Size:
44.68 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
license.txt
Size:
1.87 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
YorkU_ETDlicense.txt
Size:
3.39 KB
Format:
Plain Text
Description:
Download

Collections

Earth & Space Science

All items in the YorkSpace institutional repository are protected by copyright, with all rights reserved except where explicitly noted.