In this paper we present a technique for visual odometry on the ground plane, based on a single, uncalibrated fixed camera mounted on a mobile robot. The odometric estimate is based on the observation of features (e.g., salient points) on the floor by means of the camera mounted on the mobile robot. The presented odometric technique produces an estimate of the transformation between the ground ...

This paper introduces an extremely computationally inexpensive method for estimating monocular, feature-based, heading-only visual odometry a visual compass. The method is shown to reduce the odometric uncertainty of an uncalibrated humanoid robot by 73%, while remaining robust to the presence of independently moving objects. High efficiency is achieved by exploiting the planar motion assumptio...

Visual odometry has been used in many fields, especially in robotics and intelligent vehicles. Since local descriptors are robust to background clutter, occlusion and other content variations, they have been receiving more and more attention in the application of the detector-descriptor based visual odometry. To our knowledge, however, there is no extensive, comparative evaluation investigating...

We present a self-supervised approach to ignoring “distractors” in camera images for the purposes of robustly estimating vehicle motion in cluttered urban environments. We leverage offline multi-session mapping approaches to automatically generate a per-pixel ephemerality mask and depth map for each input image, which we use to train a deep convolutional network. At run-time we use the predicte...

Robotic systems can achieve real-time visual odometry by extracting a fixed number of invariant keypoints from the current camera frame, matching them against keypoints from a previous frame, and calculating camera motion from matching pairs. If keypoints are selected by response only they can become concentrated in a small image region. This decreases the chance for keypoints to match between ...

This paper introduces a system applicable to autonomous planetary exploration rovers that provides localization in the inevitable absence of a Global Positioning System (GPS). Given a terrain elevation map previously constructed from satellite imagery, the proposed method determines rover pose using new imagery from an onboard stereo camera system by combining visual odometry, 3D terrain matchi...

Most mobile robots use a combination of absolute and relative sensing techniques for position estimation. Relative positioning techniques are generally known as dead-reckoning. Many systems use odometry as their only deadreckoning means. However, in recent years fiber optic gyroscopes have become more affordable and are being used on many platforms to supplement odometry, especially in indoor a...

This work analyzes the performances of different feature detectors/descriptors in the context of incremental path estimation from passive stereo vision (Visual Odometry). Several state-of-the-art approaches have been tested, including a fast Hessian-based feature detector/descriptor developed at INRIM. Tests on both synthetic image sequences and real data show that in this particular applicatio...

This paper presents a novel method for visual-inertial odometry. The method is based on an information fusion framework employing low-cost IMU sensors and the monocular camera in a standard smartphone. We formulate a sequential inference scheme, where the IMU drives the dynamical model and the camera frames are used in coupling trailing sequences of augmented poses. The novelty in the model is ...

Estimating the optical flow robustly in real-time is still a challenging issue as revealed by current KITTI benchmarks. We propose an original two-step method for fast and performant optical flow estimation from stereo vision. The first step is the prediction of the flow due to the ego-motion, efficiently conducted by stereo-matching and visual odometry. The correction step estimates the motion...