Robust Visual SLAM for Fast Moving Platforms

Dr. Jose Martinez-Carranza

In the last years considerable progress has been achieved for what is known as visual Simultaneous localisation and Mapping (SLAM).

Visual SLAM is a technology that provides fast accurate 6D pose estimation of a moving camera and a 3D representation of the scene observed with the camera. Applications for this technology include: navigation in GPS-denied environments, virtual augmentation of objects in video footage, video-game interaction, etc.

Despite the achievements, there are still challenges to be faced. A practical one, but yet quite important, is that of using visual SLAM systems on platforms of low budget where computer power is reduced and memory is limited.

From the above, my main research focuses on the design of strategies that allow visual SLAM systems to keep working on slow budget platform without sacrificing the real-time response. This also includes maintaining robustness against loss of tracking, vibration, image blurred and strong change of light conditions.

Applications of my research are oriented to fast moving robotic platforms such as walking robots, mobile vehicles and Unmanned Aerial Vehicles (UAVs).

Full details about my ongoing research can be found here.

Robust visual SLAM using higher-order structure

Jose Martinez Carranza, Andrew Calway

We are working with the problem of simultaneous localization and mapping using a single hand-held camera as unique sensor.  Specifically, looking at how to camviewjextract a richer representation of the environment using the map generated by the system and the visual information obtained with the camera.

We have developed a method to identify planar structures from the environment using as basis the cloud of points generated by the slam system and the appearance information contained in the images captured with the camera. Our method evaluates the validity of points in the map as part of a physical plane in the world using a statistical frame work that incorporates the uncertainty of estimations for both camera and the map obtained with the typical EKF based visual slam framework. Besides of the benefits of a better visual representation fo the map, we are investigating how to exploid this structures to improve the estimation.