A Spherical Model Based Keypoint Descriptor and Matching Algorithm for Omnidirectional Images

International Journal of Advanced Robotic Systems

et al. 2018

A fish-eye lens achieves a large field of view at the cost of image distortion, and underwater imaging by a fish-eye lens introduces refraction when light passes through the different medium. To obtain three-dimensional information, under these circumstances, a stereo matching algorithm is proposed that analyzes the geometric characteristics of an underwater fish-eye image, taking into account distortion and refraction. First, the underwater imaging model of a stereo fisheye camera is established, and the epipolar curve of the underwater fish-eye image is calculated. Then, in the matching step, an adaptive window based on mean-shift segmentation is proposed to further alleviate the impact of distortion. Experiments are performed on synthetic images and natural scene images. The results show that the proposed model and the calculated epipolar curve are effective and that the adaptive window method could improve the precision of stereo matching on underwater fish-eye images.

Section: Experimental Results and Analysismentioning

confidence: 99%

Epipolar geometry and stereo matching algorithm for underwater fish-eye images

International Journal of Advanced Robotic Systems

et al. 2018

“…The SIFT Repeat from Process 1, until end algorithm based on perspective projection is generally used on computer vision tasks such as target tracking, image retrieval, and 3D reconstruction. 28 The fusion of point-based recognition and localization with those of point-based monocular vSLAM can identify and recover the 3D geometry of objects. The coverage range of the matching keypoints is wider, including the distorted peripheral areas.…”

Section: Mobilerobot Platform For Sar Slam Simulationsmentioning

confidence: 99%

A perception-driven exploration hierarchical simultaneous localization and mapping for mobile robots adapted to search and rescue environments

Wang

Advances in Mechanical Engineering

Song

et al. 2018

Perception-driven hierarchical simultaneous localization and mapping approach is proposed based on a distributed particle of percolator model adapted to search and rescue post-disaster environment. The proposed hierarchical analysis reduced the complexity; it can only highlight the interesting three-dimensional objects marked on the two-dimensional map, which adapted to urgent search and rescue post-disaster scenarios. Object identification, area coverage, and loop closure are the key issues that simultaneous localization and mapping faces when mobile robots detect and reach survivors in search and rescue collapsed environments. We developed hierarchical analysis using iterative extended Kalman filter method to improve the localization accuracy in simultaneous localization and mapping of mobile robots with an iteration process. An analytic hierarchical map-building mechanism efficiently constructs a globally consistent topological map using graph-based nodes and data association. An improved iterative extended Kalman filter procedure is used to estimate positions and the covariance matrix. The proposed algorithm incorporates a prediction step and a measurement update step, which performs the state vector time update in constant time interval and the correction of the state vector based on the new sensor measurement. The hierarchical mapping process is divided into three levels. The bottom level perceives the surroundings and collects input. The middle level receives and processes data from the bottom level. The upper level organizes the feature information from the previous levels to form a global, topologically consistent map. Simulations and experiments using the mobileRobot platform, Pioneer LX robot, and a crawler mobile robot validate the efficiency of this hierarchical simultaneous localization and mapping approach adapting to search and rescue post-disaster scenarios.

“…In 2012, Lourenço and Barreto have proposed an improved SIFT algorithm to improve detection and matching in the radial distortion effects repeatability, while preserving the original scale and rotation invariant [10]. In 2014, matching algorithm by Guofeng Tong and Xue Chen, the matching algorithm is to avoid the omnidirectional image distortion [11].…”

Section: Introductionmentioning

confidence: 99%

Research on image matching technology for the spherical stereo vision

2015 IEEE International Conference on Mechatronics and Automation (ICMA)

Liu

Jiao

et al. 2015

The technique of stereo matching is an important research goal of spherical stereo vision system, which is widely used in visual navigation, motion analysis and panoramic surveillance areas. Fisheye lens can get view images of large field, this paper uses two fisheye lens whose optical axis are perpendicular to construct spherical stereo vision system and does research in stereo matching of spherical stereo vision system. As the image that fish eye lens collected has lager distortion, this paper does stereo matching with the images the system collected without distortion correction using matching algorithm based on maximally stable extremal regions (MSER) and affine scale invariant feature transform (ASIFT) to reduce the correction error generated in the process. The experiment results show that the algorithm can be applied in stereo matching of fish eye image without distortion, and the results meets the need of 3D reconstruction. 2402 978-1-4799-7098-8/15/$31.00 Index Terms -Matching, Spherical stereo vision, Maximally Stable Extremal Regions (MSER), Affine Scale Invariant Feature Transform (ASIFT)