GCRIS

Now showing 1 - 2 of 2

Classification of Maneuvers of Vehicles in Front for Driver Assistance Systems
(01. Izmir Institute of Technology, 2023) Nalçakan, Yağız; Baştanlar, Yalın
Predicting vehicle maneuvers is a critical task for developing autonomous driving. These maneuvers have been identified as leading causes of fatal accidents, underscoring the need for robust and reliable detection systems. This thesis addresses this critical issue by developing and evaluating novel methodologies for classifying maneuvers, especially lane change and cut-in maneuvers in front of the vehicle. Two specific methods are proposed in this thesis work, and their effectiveness is evaluated on two datasets: the Prevention Lane Change Prediction dataset and the BDD-100K Cut-in/Lane-pass Classification Subset. The first method is a model that utilizes features extracted from the bounding boxes of the target vehicle, feeding them into a single-layer LSTM network for cut-in/lane-pass classification. The second method involves training a 3-dimensional residual neural network in a self-supervised manner using contrastive video representation learning. For the self-supervised training phase, a novel scene representation is proposed to highlight vehicle motions. Afterward, the same model is fine-tuned using labeled video data. Lastly, an ensemble learning approach is introduced, which combines the predictive capabilities of the proposed LSTM-based and self-supervised contrastive video representation learning models, leveraging the strengths of both methods to enhance the overall maneuver classification performance. The proposed methods made significant contributions to the field. The LSTM-based model achieved high classification accuracies compared to other studies in the literature. The self-supervised video representation learning model represents the first application of contrastive learning in maneuver classification. The ensemble learning approach has shown a significant improvement in the performance of the maneuver detection system.
Planar Geometry Estimation With Deep Learning
(Izmir Institute of Technology, 2022) Uzyıldırım, Furkan Eren; Özuysal, Mustafa
Understanding the geometric structure of any scene is one of the oldest problems in Computer Vision. Most scenes include planar regions that provide information about the geometric structure and their automatic detection and segmentation plays an important role in many computer vision applications. In recent years, convolutional neural network architectures have been introduced for piece-wise planar segmentation. They outperform the traditional approaches that generate plane candidates with 3D segmentation methods from the explicitly reconstructed 3D point cloud. However, most of the convolutional neural network architectures are not designed and trained for outdoor scenes, because they require manual annotation, which is a time-consuming task that results in a lack of training data. In this thesis,we propose and develop a deep learning based framework for piece-wise plane detection and segmentation of outdoor scenes without requiring manually annotated training data. We exploit a network trained on imagery with annotated targets and an automatically reconstructed point cloud from either Structure from Motion-Multi View Stereo pipeline or monocular depth estimation network to estimate the training ground truth on the outdoor images in an iterative energy minimization framework. We show that the resulting ground truth estimate of various sets of images in the outdoor domain is good enough to improve network weights of different architectures trained on ground truth annotated images. Moreover, we demonstrate that this transfer learning scheme can be repeated multiple times iteratively to further improve the accuracy of plane detection and segmentation on monocular images of outdoor scenes.

Phd Degree / Doktora

Browse

Filters

Settings

Sort By

Results per page

Search Results