Marco Fanfani

Robust Selective Stereo SLAM without Loop Closure and Bundle Adjustment

This paper presents a novel stereo SLAM framework, where a robust loop chain matching scheme for tracking keypoints is combined with an effective frame selection strategy. The proposed approach, referred to as selective SLAM (SSLAM), relies on the observation that the error in the pose estimation propagates from the uncertainty of the three-dimensional points. This is higher for distant points, corresponding to matches with low temporal flow disparity in the images. Comparative results based on the reference KITTI evaluation framework show that SSLAM is effective and can be implemented efficiently, as it does not require any loop closure or bundle adjustment.

Thesaurus project: design of new autonomous underwater vehicles for documentation and protection of underwater archaeological sites

The Thesaurus Project, funded by the Regione Toscana, combines humanistic and technological research aiming at developing a new generation of cooperating Autonomous Underwater Vehicles and at documenting ancient and modern Tuscany shipwrecks. Technological research will allow performing an archaeological exploration mission through the use of a swarm of autonomous, smart and self-organizing underwater vehicles. Using acoustic communications, these vehicles will be able to exchange each other data related to the state of the exploration and then to adapt their behavior to improve the survey. The archival research and archaeological survey aim at collecting all reports related to the underwater evidences and the events of sinking occurred in the sea of Tuscany. The collected data will be organized in a specific database suitably modeled.

Selective visual odometry for accurate AUV localization

In this paper we present a stereo visual odometry system developed for autonomous underwater vehicle localization tasks. The main idea is to make use of only highly reliable data in the estimation process, employing a robust keypoint tracking approach and an effective keyframe selection strategy, so that camera movements are estimated with high accuracy even for long paths. Furthermore, in order to limit the drift error, camera pose estimation is referred to the last keyframe, selected by analyzing the feature temporal flow. The proposed system was tested on the KITTI evaluation framework and on the New Tsukuba stereo dataset to assess its effectiveness on long tracks and different illumination conditions. Results of a live archaeological campaign in the Mediterranean Sea, on an AUV equipped with a stereo camera pair, show that our solution can effectively work in underwater environments.

Accurate keyframe selection and keypoint tracking for robust visual odometry

This paper presents a novel stereo visual odometry (VO) framework based on structure from motion, where a robust keypoint tracking and matching is combined with an effective keyframe selection strategy. In order to track and find correct feature correspondences a robust loop chain matching scheme on two consecutive stereo pairs is introduced. Keyframe selection is based on the proportion of features with high temporal disparity. This criterion relies on the observation that the error in the pose estimation propagates from the uncertainty of 3D points—higher for distant points, that have low 2D motion. Comparative results based on three VO datasets show that the proposed solution is remarkably effective and robust even for very long path lengths.

SAMSLAM: Simulated Annealing Monocular SLAM

This paper proposes a novel monocular SLAM approach. For a triplet of successive keyframes, the approach inteleaves the registration of the three 3D maps associated to each image pair in the triplet and the refinement of the corresponding poses, by progressively limiting the allowable reprojection error according to a simulated annealing scheme. This approach computes only local overlapping maps of almost constant size, thus avoiding problems of 3D map growth. It does not require global optimization, loop closure and back-correction of the poses.

Reliability assessment of principal point estimates for forensic applications

Abstract Although quite recent as a forensic research domain, computer vision analysis of scenes is likely to become more and more important in the near future, thanks to its robustness to image alterations at the signal level, such as image compression and filtering. However, the experimental assessment of vision-based forensic algorithms is a particularly critical task, since they cannot be tested on massive amounts of data, and their performance can heavily depend on user skill. In this paper we investigate on the accuracy and reliability of a vision-based, user-supervised method for the estimation of the camera principal point, to be used in cropping and splicing detection. Results of an extensive experimental evaluation show how the estimation accuracy depends on perspective conditions as well as on the selected image features. Such evidence led us to define a novel visual feature, referred to as Minimum Vanishing Angle, which can be used to assess the reliability of the method.

LaserGun: a tool for hybrid 3D reconstruction

We present a tool for the acquisition of 3D textured models of objects of desktop size using an hybrid computer vision framework. This framework combines active laser-based triangulation with passive motion estimation. The 3D models are obtained by motion-based alignment (with respect to a fixed world frame) of imaged laser profiles backprojected onto time-varying camera frames. Two distinct techniques for estimating camera displacements are described and evaluated. The first is based on a Simultaneous Localization and Mapping (SLAM) approach, while the second exploits a planar pattern in the scene and recovers motion by homography decomposition. Results obtained with a custom laser-camera stereo setup -- implemented with off-the-shelf hardware -- show that a trade-off exists between the greater operational flexibility of SLAM and the higher model accuracy of the homography-based approach.

Smartphone-Based Obstacle Detection for the Visually Impaired

One of the main problems that visually impaired people have to deal with is moving autonomously in an unknown environment. Currently, the most used autonomous walking aid is still the white can. Though in the last few years more technological devices have been introduced, referred to as electronic travel aids (ETAs). In this paper, we present a novel ETA based on computer vision. Exploiting the hardware and software facilities of a standard smartphone, our system is able to extract a 3D representation of the scene and detect possible obstacles. To achieve such a result, images are captured by the smartphone camera and processed with a modified Structure from Motion algorithm that takes as input also information from the built-in gyroscope. Then the system estimates the ground-plane and labels as obstacles all the structures above it. Results on indoor and outdoor test sequences show the effectiveness of the proposed method.

Fast Adaptive Frame Preprocessing for 3D Reconstruction

Abstract: This paper presents a new online preprocessing strategy to detect and discard ongoing bad frames in video sequences. These include frames where an accurate localization between corresponding points is difficult, such as for blurred frames, or which do not provide relevant information with respect to the previous frames in terms of texture, image contrast and non-flat areas. Unlike keyframe selectors and deblurring methods, the proposed approach is a fast preprocessing working on a simple gradient statistic, that does not require to compute complex time-consuming image processing, such as the computation of image feature keypoints, previous poses and 3D structure, or to know a priori the input sequence. The presented method provides a fast and useful frame pre-analysis which can be used to improve further image analysis tasks, including also the keyframe selection or the blur detection, or to directly filter the video sequence as shown in the paper, improving the final 3D reconstruction by discarding noisy frames and decreasing the final computation time by removing some redundant frames. This scheme is adaptive, fast and works at runtime by exploiting the image gradient statistic of the last few frames of the video sequence. Experimental results show that the proposed frame selection strategy is robust and improves the final 3D reconstruction both in terms of number of obtained 3D points and reprojection error, also reducing the computational time.