Global ETD Search

21	Through the Blur with Deep Learning : A Comparative Study Assessing Robustness in Visual Odometry Techniques Berglund, Alexander January 2023 (has links) In this thesis, the robustness of deep learning techniques in the field of visual odometry is investigated, with a specific focus on the impact of motion blur. A comparative study is conducted, evaluating the performance of state-of-the-art deep convolutional neural network methods, namely DF-VO and DytanVO, against ORB-SLAM3, a well-established non-deep-learning technique for visual simultaneous localization and mapping. The objective is to quantitatively assess the performance of these models as a function of motion blur. The evaluation is carried out on a custom synthetic dataset, which simulates a camera navigating through a forest environment. The dataset includes trajectories with varying degrees of motion blur, caused by camera translation, and optionally, pitch and yaw rotational noise. The results demonstrate that deep learning-based methods maintained robust performance despite the challenging conditions presented in the test data, while excessive blur lead to tracking failures in the geometric model. This suggests that the ability of deep neural network architectures to automatically learn hierarchical feature representations and capture complex, abstract features may enhance the robustness of deep learning-based visual odometry techniques in challenging conditions, compared to their geometric counterparts. artificial intelligence AI machine learning ML deep learning DL computer vision neural networks NN convolutional neural networks CNN visual odometry VO robustness motion blur AirForestry localization navigation ego-motion pose estimation SLAM DF-VO DytanVO ORB-SLAM3 artificiell intelligens maskininlärning datorseende Computer Sciences Datavetenskap (datalogi)

Search results

Through the Blur with Deep Learning : A Comparative Study Assessing Robustness in Visual Odometry Techniques