Visual odometry (VO) is a prevalent way to deal with the relative localization problem, which
is becoming increasingly mature and accurate, but it tends to be fragile under challenging …

Camera localization involves the estimation of the camera pose of an image from a random
scene. We used a single image or sequence of images or videos as the input. The output …

Over the last two decades, deep learning has transformed the field of computer vision. Deep
convolutional networks were successfully applied to learn different vision tasks such as …

Event cameras exhibit remarkable attributes such as high dynamic range asynchronicity and
low latency making them highly suitable for vision tasks that involve high-speed motion in …

In this paper, we propose a deep learning based assistive system to improve the
environment perception experience of visually impaired (VI). The system is composed of a …

Accurate and robust camera pose estimation is essential for high-level applications such as
augmented reality and autonomous driving. Despite the development of global feature …

Camera, and associated with its objects within the field of view, localization could benefit
many computer vision fields, such as autonomous driving, robot navigation, and augmented …

This paper presents a domain adaptation strategy to efficiently train network architectures for
estimating the relative camera pose in multi-view scenarios. The network architectures are …

Estimating depth, ego-motion, and optical flow from consecutive frames is a critical task in
robot navigation and has received significant attention in recent years. In this study, we …

Visual Odometry (VO) accumulates a positional drift in long-term robot navigation tasks.
Although Convolutional Neural Networks (CNNs) improve VO in various aspects, VO still …