Vision-aided Navigation System Research Articles

The long-acting walking control of a cockroach bio-bot for vision-aided pipeline navigation.

Many small bionic crawling robots have been invented for search and rescue missions in narrow spaces. However, their locomotion capability is far from that of insects of the same size. Transforming a cockroach into a bio-bot has been a hot topic in the past decade. Herein, we modified this insect to perform surveillance work in dark confined environments. The synergistic electrical stimulation for turning control was proposed by alternating electrical stimulation of the cerci and antennae every 5 trials. The result showed that this method was able to control cockroaches turning steadily 117 times. An electronic backpack was designed, which was capable of transmitting images in real time, and a light emitting diode (LED) was installed on the backpack providing a light source for the camera. Thus, a vision-aided navigation system was formed for dark confined environments, e.g. pipelines. With a host computer software, the operator controlled the bio-bot to pass through a completely dark and closed pipeline. The electronic backpack and the host computer were connected via transmission control protocol (TCP), which allows the operator to manipulate the bio-robot remotely. This technology can be applied in pipeline surveillance in the future.

Application of vision aided strapdown integrated navigation in lane vehicles

The application of global navigation satellite system (GNSS) is extensive in lane applications with the development of science and technology. Vision aided strapdown integrated navigation is an effective aided-navigation method in the case of GNSS failure in lane vehicles, which plays an important role in realising high-precision navigation of lane navigation system. A vision-aided navigation system based on GNSS positioning is constructed using the electrical powered platform as the research object. The hardware platform of vision navigation system is presented and digital image processing is used to segment the collected lane image. The image pre-processing operation, including denoising filtering and greyscale processing, is carried out to complete the segmentation and get the effective navigation area. According to the effective area of navigation, a navigation datum line is extracted by the least squares linear fitting and Hough transform. According to the camera imaging model and the camera's internal and external parameters, the navigation datum line in the image coordinates is transformed into the world coordinates, and the heading angle is calculated. Kalman filter algorithm is used to fuse the navigation parameters of the vision navigation module and the GNSS positioning module, and the integrated navigation model is established.

Application of vision aided strapdown integrated navigation in lane vehicles

The application of global navigation satellite system (GNSS) is extensive in lane applications with the development of science and technology. Vision aided strapdown integrated navigation is an effective aided-navigation method in the case of GNSS failure in lane vehicles, which plays an important role in realising high-precision navigation of lane navigation system. A vision-aided navigation system based on GNSS positioning is constructed using the electrical powered platform as the research object. The hardware platform of vision navigation system is presented and digital image processing is used to segment the collected lane image. The image pre-processing operation, including denoising filtering and greyscale processing, is carried out to complete the segmentation and get the effective navigation area. According to the effective area of navigation, a navigation datum line is extracted by the least squares linear fitting and Hough transform. According to the camera imaging model and the camera's internal and external parameters, the navigation datum line in the image coordinates is transformed into the world coordinates, and the heading angle is calculated. Kalman filter algorithm is used to fuse the navigation parameters of the vision navigation module and the GNSS positioning module, and the integrated navigation model is established.

Database construction for vision aided navigation in planetary landing

In this paper, a novel database construction method for passive-image based navigation system within the planetary precise pin-point landing (PPL) background is presented. The key concept is selecting qualified visual features to construct the visual database by examining their contribution to the navigation system. We first define a metric named feature exploitability to evaluate the visual feature's distinctiveness and its spatial imagery distribution. After that, a greedy selection method is employed to construct the database by selecting features with high feature-exploitability scores. Then, a hierarchical feature retrieval method is proposed to achieve the adaptation of image-scale variation during landing and improve the efficiency of feature retrieval. To evaluate our proposed approach, the Monte Carlo simulation and an experimental test are conducted, simulation results show the advantage of the feature exploitability driven database construction method over other database construction methods and the necessity of proper database construction in a vision-aided navigation system for PPL mission.

Conservative Uncertainty Estimation in Map-Based Vision-Aided Navigation

In a vision-aided autonomous system, it is crucial to have a consistent covariance matrix of the navigation solution. Overconfidence in covariance could lead to significant deviation of the navigation solution and failures of autonomous missions, especially in a global positioning system-denied environment. Consistency of a map-based vision-aided navigation system is investigated in this paper. As has been shown in numerous previous works, the traditional extended Kalman filter (EKF) approach to navigation produces significantly inconsistent (overconfident) covariance estimates. Covariance intersection and adjusted EKF approaches can both help to resolve the overconfidence problem. We present both simulation-based and real-world results of each of these approaches and investigate the consistency of their solutions.

IPS – a vision aided navigation system

Abstract Ego localization is an important prerequisite for several scientific, commercial, and statutory tasks. Only by knowing one’s own position, can guidance be provided, inspections be executed, and autonomous vehicles be operated. Localization becomes challenging if satellite-based navigation systems are not available, or data quality is not sufficient. To overcome this problem, a team of the German Aerospace Center (DLR) developed a multi-sensor system based on the human head and its navigation sensors – the eyes and the vestibular system. This system is called integrated positioning system (IPS) and contains a stereo camera and an inertial measurement unit for determining an ego pose in six degrees of freedom in a local coordinate system. IPS is able to operate in real time and can be applied for indoor and outdoor scenarios without any external reference or prior knowledge. In this paper, the system and its key hardware and software components are introduced. The main issues during the development of such complex multi-sensor measurement systems are identified and discussed, and the performance of this technology is demonstrated. The developer team started from scratch and transfers this technology into a commercial product right now. The paper finishes with an outlook.

Visual Target Tracking and Relative Navigation for Unmanned Aerial Vehicles in a GPS-Denied Environment

We present a system for the real-time visual relative navigation of a fixed-wing unmanned aerial vehicle in a GPS-denied environment. An extended Kalman filter is used to construct a vision-aided navigation system by fusing the image processing results with barometer and inertial sensor measurements. Using a mean-shift object tracking algorithm, an onboard vision system provides pixel measurements to the navigation filter. The filter is slightly modified to deal with delayed measurements from the vision system. The image processing algorithm and the navigation filter are verified by flight tests. The results show that the proposed aerial system is able to maintain circling around a target without using GPS data.

Vision-aided terrain referenced navigation for unmanned aerial vehicles using ground features

A vision-aided terrain referenced navigation (VATRN) approach is addressed for autonomous navigation of unmanned aerial vehicles (UAVs) under GPS-denied conditions. A typical terrain referenced navigation (TRN) algorithm blends inertial navigation data with measured terrain information to estimate vehicle’s position. In this paper, a low-cost inertial navigation system (INS) for UAVs is supplemented with a monocular vision-aided navigation system and terrain height measurements. A point mass filter based on Bayesian estimation is employed as a TRN algorithm. Homograpies are established to estimate the vehicle’s relative translational motion using ground features with simple assumptions. And the error analysis in homography estimation is explored to estimate the error covariance matrix associated with the visual odometry data. The estimated error covariance is delivered to the TRN algorithm for robust estimation. Furthermore, multiple ground features tracked by image observations are utilized as multiple height measurements to improve the performance of the VATRN algorithm.

Vision-aided Navigation for Autonomous Aircraft Based on Unscented Kalman Filter

A vision-aided navigation system for autonomous aircraft is described in this paper. The vision navigation of the aircraft to the known scence is performed with a camera fixed on the aircraft. The location and pose of the aircraft are estimated with the corresponding control points which can be detected in the images captured. The control points are selected according their saliency and are tracked in sequential images based on Fourier-Melline transform. The simulation model of the aircraft dynamics and vision-aided navigation system based on Matlab/Simulink is built.The unscented Kalman filter is used to fuse the aircraft state information provided by the vision system and the inertial navigation system. Simulation results show that the vision-based navigation system provides satisfactory results of both accuracy and reliability. DOI: http://dx.doi.org/10.11591/telkomnika.v11i2.2250 Full Text: PDF

Research on Scene Matching Algorithm in the Vision-Aided Navigation System

the maching algorithm in the vision-aided navigation system must be real-time, high-precision and suitable for matching different images with some scaling and rotation. This paper proposed three algorithms based on SURF, SIFT and ASIFT features. The SURF algorithm is the better method than the SIFT and ASIFT in theory, because the use of integral image and basic Hessian-matrix approximation has greatly reduce the computational complexity. The experimental results show that the three algorithms can obtain similar detecting and matching performance, but the SIFT and ASIFT need too much time to realize real time. So, the SURF is more suitable for scene matching in the vision-aided navigation system.

Vision-Based Unmanned Aerial Vehicle Navigation Using Geo-Referenced Information

This paper investigates the possibility of augmenting an Unmanned Aerial Vehicle (UAV) navigation system with a passive video camera in order to cope with long-term GPS outages. The paper proposes a vision-based navigation architecture which combines inertial sensors, visual odometry, and registration of the on-board video to a geo-referenced aerial image. The vision-aided navigation system developed is capable of providing high-rate and drift-free state estimation for UAV autonomous navigation without the GPS system. Due to the use of image-to-map registration for absolute position calculation, drift-free position performance depends on the structural characteristics of the terrain. Experimental evaluation of the approach based on offline flight data is provided. In addition the architecture proposed has been implemented on-board an experimental UAV helicopter platform and tested during vision-based autonomous flights.