Adapting a real-time monocular visual SLAM from conventional to omnidirectional cameras (original) (raw)

Visual SLAM with an Omnidirectional Camera

2010 20th International Conference on Pattern Recognition, 2010

In this work we integrate the Spherical Camera Model for catadioptric systems in a Visual-SLAM application. The Spherical Camera Model is a projection model that unifies central catadioptric and conventional cameras. To integrate this model into the Extended Kalman Filter-based SLAM we require to linearize the direct and the inverse projection. We have performed an initial experimentation with omnidirectional and conventional real sequences including challenging trajectories. The results confirm that the omnidirectional camera gives much better orientation accuracy improving the estimated camera trajectory.

Spherical image processing for accurate visual odometry with omnidirectional cameras

Due to their omnidirectional view, the use of catadioptric cameras is of great interest for robot localization and visual servoing. For simplicity, most vision-based algorithms use image processing tools (e.g. image smoothing) that were designed for perspective cameras. This can be a good approximation when the camera displacement is small with respect to the distance to the observed environment. Otherwise, perspective image processing tools are unable to accurately handle the signal distortion that is induced by the specific geometry of omnidirectional cameras. In this paper, we propose an appropriate spherical image processing for increasing the accuracy of visual odometry estimation. The omnidirectional images are mapped onto a unit sphere and treated in the spherical spectral domain. The spherical image processing take into account the specific geometry of omnidirectional cameras. For example we can design, a more accurate and more repeatable Harris interest point detector. The interest points can be matched between two images with a large baseline in order to accurately estimate the camera motion. We demonstrate with a real experiment the accuracy of the visual odometry obtained using the spherical image processing and the improvement with respect to the use of a standard perspective image processing.

Monocular visual odometry in urban environments using an omnidirectional camera

2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2008

We present a system for Monocular Simultaneous Localization and Mapping (Mono-SLAM) relying solely on video input. Our algorithm makes it possible to precisely estimate the camera trajectory without relying on any motion model. The estimation is fully incremental: at a given time frame, only the current location is estimated while the previous camera positions are never modified. In particular, we do not perform any simultaneous iterative optimization of the camera positions and estimated 3D structure (local bundle adjustment). The key aspects of the system is a fast and simple pose estimation algorithm that uses information not only from the estimated 3D map, but also from the epipolar constraint. We show that the latter leads to a much more stable estimation of the camera trajectory than the conventional approach. We perform high precision camera trajectory estimation in urban scenes with a large amount of clutter. Using an omnidirectional camera placed on a vehicle, we cover the longest distance ever reported, up to 2.5 kilometers.

Full scaled 3D visual odometry from a single wearable omnidirectional camera

2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2012

In the last years monocular SLAM has been widely used to obtain highly accurate maps and trajectory estimations of a moving camera. However, one of the issues of this approach is that, due to the impossibility of the depth being measured in a single image, global scale is not observable and scene and camera motion can only be recovered up to scale. This problem gets aggravated as we deal with larger scenes since it is more likely that scale drift arises between different map portions and their corresponding motion estimates. To compute the absolute scale we need to know some kind of dimension of the scene (e.g., actual size of an element of the scene, velocity of the camera or baseline between two frames) and somehow integrate it in the SLAM estimation. In this paper, we present a method to recover the scale of the scene using an omnidirectional camera mounted on a helmet. The high precision of visual SLAM allows the head vertical oscillation during walking to be perceived in the trajectory estimation. By performing a spectral analysis on the camera vertical displacement, we can measure the step frequency. We relate the step frequency to the speed of the camera by an empirical formula based on biomedical experiments on human walking. This speed measurement is integrated in a particle filter to estimate the current scale factor and the 3D motion estimation with its true scale. We evaluated our approach using image sequences acquired while a person walks. Our experiments show that the proposed approach is able to cope with scale drift.

Information-based view initialization in visual SLAM with a single omnidirectional camera

Robotics and Autonomous Systems, 2015

This paper presents a novel mechanism to initiate new views within the map building process for an EKF-based visual SLAM (Simultaneous Localization and Mapping) approach using omnidirectional images. In presence of non-linearities, the EKF is very likely to compromise the final estimation. Particularly, the omnidirectional observation model is induces non-linear errors, thus it becomes a potential source of uncertainty. To deal with this issue we propose a novel mechanism for view initialization which accounts for information gain and losses more efficiently. The main outcome of this contribution is the reduction of the map uncertainty and thus the higher consistency of the final estimation. Its basis relies on a Gaussian Process to infer an information distribution model from sensor data. This model represents feature points existence probabilities and their information content analysis leads to the proposed view initialization scheme. To demonstrate the suitability and effectiveness of the approach we present a series of real data experiments conducted with a robot equipped with a camera sensor and map model solely based on omnidirectional views. The results reveal a beneficial reduction on the uncertainty but also on the error in the pose and the map estimate.

On-line SLAM using clustered landmarks with omnidirectional vision

Journal of the Brazilian Society of Mechanical Sciences and Engineering, 2010

The problem of SLAM (simultaneous localization and mapping) is a fundamental problem in autonomous robotics. It arises when a robot must create a map of the regions it has navigated while localizing itself on it, using results from one step to increase precision in another by eliminating errors inherent to the sensors. One common solution consists of establishing landmarks in the environment which are used as reference points for absolute localization estimates and form a sparse map that is iteratively refined as more information is obtained. This paper introduces a method of landmark selection and clustering in omnidirectional images for on-line SLAM, using the SIFT algorithm for initial feature extraction and assuming no prior knowledge of the environment. Visual sensors are an attractive way of collecting information from the environment, but tend to create an excessive amount of landmarks that are individually prone to false matches due to image noise and object similarities. By clustering several features in single objects, our approach eliminates landmarks that do not consistently represent the environment, decreasing computational cost and increasing the reliability of information incorporated. Tests conducted in real navigational situations show a significant improvement in performance without loss of quality.

Visual Odometry Based on Omnidirectional Images

We propose a method for visual odometry using optical flow with a single omnidirectional (catadioptric) camera. We show how omnidirectional images can be used to perform optical flow, discussing the basis of optical flow and some restrictions needed to it and how unwarp these images. In special we describe how to unwarp omnidirectional images to Bird's eye view, that correspond to scaled orthographic views of the ground plane. Catadioptric images facilitate landmark based odometry, since landmarks remain visible for longer time, as opposed to a small field-of-view standard camera. Also, providing adequate representations to support visual odometry with a fast processing time. We perform tests to measure robustness and performance of our approach with analysis of the data acquired.

Visual odometry from an omnidirectional vision system

2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422)

Lecturer of the M.Sc. course "Autonomous Mobiles Robots" • Scientific Manager of the "sFly" European Project (FP7) • Project Leader of the ETH team which will participate in the European Micro Aerial Vehicle competition. We will show an autonomous micro helicopter capable of exploring an apartment using only vision for navigation. • Research activities in the field of vision based 3D mapping of urban environments and vision based navigation of micro-aerial vehicles

Selectively Using Landmarks in Online SLAM with Omnidirectional Vision

2008

The problem of SLAM (simultaneous localization and mapping), is a fundamental problem in autonomous robotics. It arises when a robot must create a map of the regions it has navigated while localizing itself on it, using results from one step to increase precision in the other by eliminating errors inherent to the sensors. One common solution consists of establishing landmarks in the environment that are used as reference points for absolute localization estimates and form a sparse map that is iteratively refined as more information is obtained. This paper introduces a method of landmark selection in omnidirectional images for online SLAM, using the SIFT algorithm for initial feature extraction and assuming no prior knowledge of the environment. Visual sensors are an attractive way of collecting information from the environment, but tend to create an excessive amount of landmarks that are individually propense to false matches due to image noise and object similarities. By clustering...

Visual Odometry through Appearance- and Feature-Based Method with Omnidirectional Images

Journal of Robotics, 2012

In the field of mobile autonomous robots, visual odometry entails the retrieval of a motion transformation between two consecutive poses of the robot by means of a camera sensor solely. A visual odometry provides an essential information for trajectory estimation in problems such as Localization and SLAM (Simultaneous Localization and Mapping). In this work we present a motion estimation based on a single omnidirectional camera. We exploited the maximized horizontal field of view provided by this camera, which allows us to encode large scene information into the same image. The estimation of the motion transformation between two poses is incrementally computed, since only the processing of two consecutive omnidirectional images is required. Particularly, we exploited the versatility of the information gathered by omnidirectional images to perform both an appearance-based and a feature-based method to obtain visual odometry results. We carried out a set of experiments in real indoor ...