Stereo visual odometry in urban environments based on detecting ground features

Abstract

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.

State of the Art in Vision-Based Localization Techniques for Autonomous Navigation Systems

“…Key design choices of VO schemes can be classified based on the used visual sensor(s) and the selected processing modules, into geometric and nongeometric approaches. In the first VO method, camera geometrical relations are identified to estimate the ego-motion such as the intensity value of image pixels (appearance-based VO [36], [37], [43], [44], [48]- [50], [128]) and the image texture (feature-based VO [64], [65], [104]- [106], [108], [109], [111], [126], [137]). This method could provide precise state estimation only if enough features within the environment are observed in good lighting conditions.…”

“…Then, the matching and tracking of these features is performed by an optimization method to reduce the geometric error. Lastly, computing the transformation matrix is performed to estimate the motion [63]- [65]. Figure 7 illustrates the main pipeline of feature-based VO approach.…”

Analysis of the Influence of Training Data on Road User Detection

“…The auto-calibration procedure proposed to obtain the transform beoverview tween the camera and the footprint frames is based on previous works developed in the LSI [66], [190], [216]. The method obtains the parameters by detecting and segmenting the ground plane in the data from the stereo system, as shown in Fig.…”

A Monocular Visual Odometry Method Based on Virtual-Real Hybrid Map in Low-Texture Outdoor Environment

“…For robots, visual odometry (VO) and visual Simultaneous Localization and Mapping (vSLAM) are the key technologies. With visual odometry, a robot can accurately estimate its trajectory in an unknown environment, which endows it with the ability to explore unknown environments on its own [ 5 , 6 , 7 , 8 ]. However, possible environments are highly diverse, not always textured, and there are plenty of low-texture environments, such as the streets in urban areas and artificial squares.…”