Visual Place Recognition (VPR) is a challenging problem due to environmental changes, which means that the appearance of places can vary over time. It is one of the most essential and challenging problems in the field of robotics and computer vision. In the past few years, enormous improvements in visual sensing capabilities, an increasing concentration on long-term mobile robot autonomy, and the ability to conduct state-of-the-art research have all contributed to significant advances in VPR systems. Long-term robot autonomy has revealed that changing conditions can be a significant factor in its failure. Therefore, it is crucial to come up with more advanced solutions which considers a variety of changes within the environment, including the seasons, weather, illumination, and occlusion. Compared to traditional machine learning approaches, deep learning methods are currently among the most widespread and successful research topics in several disciplines, including computer vision and robotics.
To reach the goals, Alijani first compared the performance of deep CNN architectures coupled with BatchNorm layers using architectures primarily trained for image classification and object detection as holistic feature descriptors for VPR.
Secondly, he investigated the performance of learned global features when trained using three different loss functions in an end-to-end manner for learning the parameters of the architectures in terms of a fraction of the correct matches during deployment.
Next, he evaluated two state-of-the-art deep metric learning methods for VPR using vision and LiDAR sensor modalities along with ablation studies on the crucial parameters of deep architectures.
Finally, he investigated the topic of deep long-term VPR as a systematic approach to propose an experimental benchmark using deep CNN architectures in order to obtain the discriminative feature representation.
This PhD dissertation has been completed at the Doctoral School of Industry Innovations (DSII) at the Faculty of Information Technology and Communication Sciences, Tampere University, and was sponsored by Sandvik Oy.
Public defence on Friday 22 September
The doctoral dissertation of MSc (Tech) Farid Alijani in the field of deep learning and computer vision titled Long-term Visual Place Recognition Under Varying Conditions will be publicly examined at the Faculty of Information Technology and Communication Sciences at Tampere University at noon on Friday, September 22, 2023, in lecture hall TB109 of the Tietotalo building on the Hervanta campus. The Opponent will be Dr. Bertil Grelsson from Saab AB, Sweden, and DSc (Tech) Juho Vihonen from Hiab/Cargotech Oy, Finland. The Custos will be Professor Esa Rahtu from the Faculty of Information Technology and Communication Sciences at Tampere University.
The doctoral dissertation is available online.
The public defence can be followed via a remote connection.
Photograph: Annelise Rainer