We present an integrated system to localize a mobile robot in rough outdoor terrain using visual odometry. Our previous work [1] presented a visual odometry solution that estimates frame-to-frame motion from stereo cameras and integrated this incremental motion with a low cost GPS. We extend that work through the use of bundle adjustment over multiple frames. Bundle adjustment helps to reduce t...

The accuracy of agricultural unmanned ground vehicles’ localization directly affects the their navigation. However, due to changeable environment and fewer features in scene, it is challenging for these vehicles localize precisely global positioning system-denied areas with a single sensor. In this article, we present an efficient adaptive sensor-fusion odometry framework based on simultaneous ...

Stairs are one of the most common structures present in human-made scenarios, but also one of the most dangerous for those with vision problems. In this work we propose a complete method to detect, locate and parametrise stairs with a wearable RGB-D camera. Our algorithm uses the depth data to determine if the horizontal planes in the scene are valid steps of a staircase judging their dimension...

We propose to use a state-of-the-art visual odometry technique for the purpose of head pose estimation. We demonstrate that with small adaptation this algorithm allows to achieve more accurate head pose estimation from an RGBD sensor than all the methods published to date. We also propose a novel methodology to automatically assess the accuracy of a tracking algorithm without the need to manual...

Tracking objects moving around a person is one of the key steps in human visual augmentation: we could estimate their locations when they are out of our field of view, know their position, distance or velocity just to name a few possibilities. This is no easy task: in this paper, we show how current state-ofthe-art visual tracking algorithms fail if challenged with a first-person sequence recor...

This technical report retrospectively collects the final reports of the undergraduate Computer Science majors from the Qatar Campus of Carnegie Mellon University who elected to complete a senior research thesis in the academic year 2008–09 as part of their degree. These projects have spanned the students’ entire senior year, during which they have worked closely with their faculty advisors to p...

In this paper, we propose an RGB-D visual odometry method that both minimizes the photometric error and aligns the edges between frames. The combination of the direct photometric information [1] and the edge features leads to higher tracking accuracy and enables the approach to deal with challenging texture-less scenes. In contrast to traditional line feature based methods [2], we involve all e...

We report a new error-aware monocular visual odometry method that only uses vertical lines, such as vertical edges of buildings and poles in urban areas as landmarks. Since vertical lines are easy to extract, insensitive to lighting conditions/shadows, and sensitive to robot movements on the ground plane, they are robust features if compared with regular point features or line features. We deri...

We present a novel Visual Odometry algorithm entitled Circular FREAK-ORB (CFORB). This algorithm detects features using the well-known ORB algorithm [12] and computes feature descriptors using the FREAK algorithm [14]. CFORB is invariant to both rotation and scale changes, and is suitable for use in environments with uneven terrain. Two visual geometric constraints have been utilized in order t...

Visual-Inertial Odometry (VIO) utilizes an Inertial Measurement Unit (IMU) to overcome the limitations of Visual Odometry (VO). However, the VIO for vehicles in large-scale outdoor environments still has some difficulties in estimating forward motion with distant features. To solve these difficulties, we propose a robust VIO method based on the analysis of feature confidence in forward motion e...