A Novel Georeferenced Dataset for Stereo Visual Odometry (original) (raw)

Stereo camera visual odometry for moving urban environments

Integrated Computer-Aided Engineering, 2019

This work proposes a system designed to estimate the egomotion of a synchronized calibrated stereo camera in scenes containing a moderate number of moving objects. This is particularly useful in busy road scenes and populated urban areas. The key novelty of the proposed approach is that it estimates the motion of clusters of pixels between stereo frames, which allows it to explicitly reject clusters in motion. This is in contrast to current state-of-the-art algorithms, that tend to treat moving elements as outliers, which are removed using strategies such as RANSAC or M-estimators. Unfortunately treating moving pixels as outliers can give poor performance when the motion represents a significant portion of pixels. The proposed approach overcomes this, if the motion is due to many independently moving objects (such as people or cars). Our experiments show promising results in a variety of urban environments.

Implementation of Stereo Visual Odometry Estimation for Ground Vehicles

Keeping track of vehicles location is a challenging aspect in recent days. Visual Odometry (VO) is the process of estimating the orientation and position of a vehicle or a robot by analyzing the associated camera's input. In this paper a stereo camera based visual odometry system is presented in which stereo cameras have been rigidly attached to the vehicle and motion of the vehicle is estimated using only the input coming from these stereo cameras. No other sensors are needed. The corner features are extracted in both left and right images using Harris corner detector algorithm, descriptor for each feature is extracted using Scale Invariant Feature Transform (SIFT) algorithm, feature descriptors are matched between left and right images using K-nearest neighbor match. Those matched feature correspondences are triangulated to get 3-D points. Two sets of 3-D points are obtained at time steps 't' and 't+1'. Then, the motion is estimated using least squares fitting of these two 3-D point sets.

Large scale visual odometry using stereo vision

2011

This paper presents a system for egomotion estimation using a stereo head camera. The camera motion estimation is based on features tracked along a video sequence. The system also estimates the tridimensional geometry of the environment by fusing the visual information from multiple views. Furthermore, the paper presents comparisons between two different algorithms. The first one is by applying triangulation to 3D points. Motion estimation using 3D points suffers from the problem of nonisotropic noise due to the large uncertainty in depth estimation. To deal with this problem we present results with a second approach that works directly in the disparity space. Experimental results using a mobile platform are presented. The experiments cover long distances in urban-like environments with the presence of dynamic objects. The system presented is part of a bigger project involving autonomous navigation using vision only.

Visual Odometry using Stereo Vision

Conventional non-vision based navigation systems relying on purely Global Positioning System (GPS) or inertial sensors can provide the 3D position or orientation of the user. However GPS is often not available in forested regions and cannot be used indoors. Visual odometry provides an independent method to estimate position and orientation of the user/system based on the images captured by the moving user accurately. Vision based systems also provide information (e.g. images, 3D location of landmarks, detection of scene objects) about the scene that the user is looking at. In this project, a set of techniques are used for the accurate pose and position estimation of the moving vehicle for autonomous navigation using the images obtained from two cameras placed at two different locations of the same area on the top of the vehicle. These cases are referred to as stereo vision. Stereo vision provides a method for the 3D reconstruction of the environment which is required for pose and position estimation. Firstly, a set of images are captured. The Harris corner detector is utilized to automatically extract a set of feature points from the images and then feature matching is done using correlation based matching. Triangulation is applied on feature points to find the 3D coordinates. Next, a new set of images is captured. Then repeat the same technique for the new set of images too. Finally, by using the 3D feature points, obtained from the first set of images and the new set of images, the pose and position estimation of moving vehicle is done using QUEST algorithm.

Stereo visual odometry in urban environments based on detecting ground features

Robotics and Autonomous Systems, 2016

Autonomous vehicles rely on the accurate estimation of their pose, speed and direction of travel to perform basic navigation tasks. Although GPSs are very useful, they have some drawbacks in urban applications that affect their accuracy. Visual odometry is an alternative or complementary method because provides the ego motion of the vehicle with enough accuracy and uses a sensor already available in some vehicles for other tasks, so no extra sensor is needed. In this paper, a new method is proposed that detects and tracks features available on the surface of the ground, due to the texture of the road or street and road markings. This way it is assured only static points are taking into account in order to obtain the relative movement between images. A Kalman filter improves the estimations and the Ackermann steering restriction is applied so the vehicle follows a constrained trajectory, which improves the camera displacement estimation obtain from a PnP algorithm. Some results in real urban environments are shown in order to demonstrate the good performance of the algorithm. They show the method is able to estimate the linear and angular speeds of the vehicle with high accuracy as well as its ability to follow the real trajectory drove by the vehicle along long paths within a minimum error.

Three-Point Direct Stereo Visual Odometry

Procedings of the British Machine Vision Conference 2016, 2016

Stereo visual odometry estimates the ego-motion of a stereo camera given an image sequence. Previous methods generally estimate the ego-motion using a set of inlier features while filtering out outlier features. However, since the perfect classification of inlier and outlier features is practically impossible, the motion estimate is often contaminated by erroneous inliers. In this paper, we propose a novel three-point direct method for stereo visual odometry, which is more accurate and robust to outliers. To improve both accuracy and robustness, we consider two key points: sampling a minimum number of features, i.e., 3 points, and minimizing photometric errors in order to maximally reduce measurement errors. In addition, we utilize temporal information of features, i.e., feature tracks. Local features are updated by the feature tracks and the updated feature points improve the performance of the proposed pose estimation. We compare the proposed method with other state-of-the-art methods and demonstrate the superiority of the proposed method through experiments on the KITTI benchmark.

Improving the Accuracy of Stereo Visual Odometry Using Visual Illumination Estimation

In the absence of reliable and accurate GPS, visual odome-try (VO) has emerged as an effective means of estimating the egomotion of robotic vehicles. Like any dead-reckoning technique, VO suffers from unbounded accumulation of drift error over time, but this accumulation can be limited by incorporating absolute orientation information from, for example, a sun sensor. In this paper, we leverage recent work on visual outdoor illumination estimation to show that estimation error in a stereo VO pipeline can be reduced by inferring the sun position from the same image stream used to compute VO, thereby gaining the benefits of sun sensing without requiring a dedicated sun sensor or the sun to be visible to the camera. We compare sun estimation methods based on hand-crafted visual cues and Convolutional Neural Networks (CNNs) and demonstrate our approach on a combined 7.8 km of urban driving from the popular KITTI dataset, achieving up to a 43% reduction in translational average root mean squared error (ARMSE) and a 59% reduction in final translational drift error compared to pure VO alone. In the absence of reliable and accurate GPS, visual odometry (VO) has emerged as an effective means of estimating the egomotion of robotic vehicles as they navigate through their environment. While VO is generally less prone to drift than other dead-reckoning techniques such as wheel odometry, any dead-reckoning algorithm will inevitably accumulate drift over time due to the compounding of small estimation errors. Indeed, VO suffers from superlinear growth of drift error with distance travelled, mainly due to error in the orientation estimates [14]. Fortunately, the addition of absolute orientation information from, for example, a sun sensor can restrict this growth to be linear [14]. The sun is an appealing source of absolute orientation information since it is readily detectable and its apparent motion through the sky is well characterized in ephemeris tables. The benefits of deriving orientation information from a sun sensor have been successfully demonstrated in planetary analogue environments [6,11] as well as on board the Mars Exploration Rovers (MERs) [3,13].

Joint Forward-Backward Visual Odometry for Stereo Cameras

2019

Visual odometry is a widely used technique in the field of robotics and automation to keep a track on the location of a robot using visual cues alone. In this paper, we propose a joint forward-backward visual odometry framework by combining both, the forward motion and backward motion estimated from stereo cameras. The basic framework of LIBVIOS2 is used here for pose estimation as it can run in real-time on standard CPUs. The complementary nature of errors in the forward and backward mode of visual odometry helps in providing a refined motion estimation upon combining these individual estimates. In addition, two reliability measures, that is, forward-backward relative pose error and forward-backward absolute pose error have been proposed for evaluating visual odometry frameworks on its own without the requirement of any ground truth data. The proposed scheme is evaluated on the KITTI visual odometry dataset. The experimental results demonstrate improved accuracy of the proposed sch...

Comparison of Three Off-the-Shelf Visual Odometry Systems

Robotics, 2020

Positioning is an essential aspect of robot navigation, and visual odometry an important technique for continuous updating the internal information about robot position, especially indoors without GPS (Global Positioning System). Visual odometry is using one or more cameras to find visual clues and estimate robot movements in 3D relatively. Recent progress has been made, especially with fully integrated systems such as the RealSense T265 from Intel, which is the focus of this article. We compare between each other three visual odometry systems (and one wheel odometry, as a known baseline), on a ground robot. We do so in eight scenarios, varying the speed, the number of visual features, and with or without humans walking in the field of view. We continuously measure the position error in translation and rotation thanks to a ground truth positioning system. Our result shows that all odometry systems are challenged, but in different ways. The RealSense T265 and the ZED Mini have compar...

Stereo-based Visual Odometry for Autonomous Robot Navigation

International Journal of Advanced Robotic Systems, 2016

Mobile robots should possess accurate self-localization capabilities in order to be successfully deployed in their environment. A solution to this challenge may be derived from visual odometry (VO), which is responsible for estimating the robot's pose by analysing a sequence of images. The present paper proposes an accurate, computationally-efficient VO algorithm relying solely on stereo vision images as inputs. The contribution of this work is twofold. Firstly, it suggests a non-iterative outlier detection technique capable of efficiently discarding the outliers of matched features. Secondly, it introduces a hierarchical motion estimation approach that produces refinements to the global position and orientation for each successive step. Moreover, for each subordinate module of the proposed VO algorithm, custom non-iterative solutions have been adopted. The accuracy of the proposed system has been evaluated and compared with competent VO methods along DGPS-assessed benchmark routes. Experimental results of relevance to rough terrain routes, including both simulated and real outdoors data, exhibit remarkable accuracy, with positioning errors lower than 2%.