https://scholarsmine.mst.edu/cgi/viewcontent.cgi?article=4594&context=ele_comeng_facwork

Deep Learning Nuclei Detection in Digitized Histology Images by Superpixels.

Simultaneous localization and mapping (SLAM) is a fundamental problem for various applications. For indoor environments, planes are predominant features that are less affected by measurement noise. In this paper, we propose a novel point-plane SLAM system using RGB-D cameras. First, we extract feature points from RGB images and planes from depth images. Then plane correspondences in the global map can be found using their contours. Considering the limited size of real planes, we exploit constraints of plane edges. In general, a plane edge is an intersecting line of two perpendicular planes. Therefore, instead of line-based constraints, we calculate and generate supposed perpendicular planes from edge lines, resulting in more plane observations and constraints to reduce estimation errors. To exploit the orthogonal structure in indoor environments, we also add structural (parallel or perpendicular) constraints of planes. Finally, we construct a factor graph using all of these features. The cost functions are minimized to estimate camera poses and global map. We test our proposed system on public RGB-D benchmarks, demonstrating its robust and accurate pose estimation results, compared with other state-of-the-art SLAM systems.

Point-Plane SLAM Using Supposed Planes for Indoor Environments.

Overlapping cells segmentation is one of the challenging topics in medical image processing. In this paper, we propose to approximately represent the cell contour as a set of sparse contour points, which can be further partitioned into two parts: the strong contour points and the weak contour points. We consider the cell contour extraction as a contour points locating problem and propose an effective and robust framework for segmentation of partially overlapping cells in cervical smear images. First, the cell nucleus and the background are extracted by a morphological filtering-based K-means clustering algorithm. Second, a gradient decomposition-based edge enhancement method is developed for enhancing the true edges belonging to the center cell. Then, a dynamic sparse contour searching algorithm is proposed to gradually locate the weak contour points in the cell overlapping regions based on the strong contour points. This algorithm involves the least squares estimation and a dynamic searching principle, and is thus effective to cope with the cell overlapping problem. Using the located contour points, the Gradient Vector Flow Snake model is finally employed to extract the accurate cell contour. Experiments have been performed on two cervical smear image datasets containing both single cells and partially overlapping cells. The high accuracy of the cell contour extraction result validates the effectiveness of the proposed method.

Accurate Segmentation of Partially Overlapping Cervical Cells Based on Dynamic Sparse Contour Searching and GVF Snake Model

A non-contact measurement method of ship block using image-based 3D reconstruction technology

This paper proposed a new vehicle geo-localization method in urban environment integrating a new source of information that is a virtual 3D city model. This 3D model provides a realistic representation of the navigation environment of the vehicle. To optimize the performance of vehicle geo-localization system, several sources of information are integrated for their complementarity and redundancy: a GPS receiver, proprioceptive sensors (odometers and gyrometer), a video camera and a virtual 3D city model. The pose estimation algorithm used to fuse the different sensors data is an IMM-UKF (Interacting Multiple Model - Unscented Kalman Filter). The proprioceptive sensors allow to continuously estimating the dead-reckoning position and orientation of the vehicle. This dead-reckoning estimation of the pose is corrected by GPS measurements. Moreover, a 3D model/camera based observation of the vehicle pose is constructed to compensate the drift of the dead-reckoning localization when GPS measurements are unavailable for a long time. This pose observation is based on the matching between the virtual image extracted from the 3D city model and the real image acquired by the camera. The observation construction is composed of two major parts. The first part consists in detecting and matching the feature points of the real and virtual images. Three features are compared: Harris corner, SIFT (Scale Invariant Feature Transform) and SURF (Speed Up Robust Features). The second part is the pose computation using POSIT algorithm and the previously matched features set. The developed approach has been tested on a real sequence and the obtained results proved the feasibility and robustness of the approach.

Harris, SIFT and SURF features comparison for vehicle localization based on virtual 3D model and camera

This paper presents a new 3D reconstruction method using feature points extracted by the SIFT and Harris corner detector. Since the SIFT feature points can be detected stably and relatively accurately, the proposed algorithm first uses the SIFT matching points to calculate the fundamental matrix. On the other hand many of the feature points detected by the SIFT are not what we need for reconstruction, so by combining the SIFT feature points with the Harris corners it is possible to obtain more vivid and detailed 3D information. Experiments have been conducted to validate the proposed method.

3D reconstruction based on SIFT and Harris feature points

Pose estimation and map reconstruction are basic requirements for robotic autonomous behavior. In this paper, we propose a point-plane-based method to simultaneously estimate the robot's poses and reconstruct the current environment's map using RGB-D cameras. First, we detect and track the point and plane features from color and depth images, and reliable constraints are obtained, even for low-texture scenes. Then, we construct cost functions from these features, and we utilize the plane's minimal representation to minimize these functions for pose estimation and local map optimization. Furthermore, we extract the Manhattan World (MW) axes on the basis of the plane normals and vanishing directions of parallel lines for the MW scenes, and we add the MW constraint to the point-plane-based cost functions for more accurate pose estimation. The results of experiments on public RGB-D datasets demonstrate the robustness and accuracy of the proposed algorithm for pose estimation and map reconstruction, and we show its advantages compared with alternative methods.

RGB-D SLAM Using Point-Plane Constraints for Indoor Environments.

Orientation estimation is a crucial part of robotics tasks such as motion control, autonomous navigation, and 3D mapping. In this paper, we propose a robust visual-based method to estimate robots’ drift-free orientation with RGB-D cameras. First, we detect and track hybrid features (i.e., plane, line, and point) from color and depth images, which provides reliable constraints even in uncharacteristic environments with low texture or no consistent lines. Then, we construct a cost function based on these features and, by minimizing this function, we obtain the accurate rotation matrix of each captured frame with respect to its reference keyframe. Furthermore, we present a vanishing direction-estimation method to extract the Manhattan World (MW) axes; by aligning the current MW axes with the global MW axes, we refine the aforementioned rotation matrix of each keyframe and achieve drift-free orientation. Experiments on public RGB-D datasets demonstrate the robustness and accuracy of the proposed algorithm for orientation estimation. In addition, we have applied our proposed visual compass to pose estimation, and the evaluation on public sequences shows improved accuracy.

Robust Visual Compass Using Hybrid Features for Indoor Environments

In this study, we present a novel, robust, and accurate method to register multiple images captured by an unmanned aerial vehicle (UAV) with modified camera matrixes, and then stitch UAV images to a seamless one. Firstly, the camera parameters, camera poses and sparse 3D points are solved using feature correspondence and SFM. Secondly, all images are registered using sparse 3D point cloud and modified camera matrixes. Thirdly, the stitching plane is determined by performing a view selection. At last, all images are stitched using multi-band blending based on graph-cut. Experiments and comparisons demonstrate the accuracy and feasibility of our approach.

Seamless stitching of large area UAV images using modified camera matrix

Conventional initialization algorithms for feature-based monocular visual simultaneous localization and mapping (V-SLAM)/visual odometry (VO) systems used point-based matrix decomposition. However, line segments are common in urban scenes and provide valuable information about scene structure. In this paper, we propose incorporating line segments for initializing, which allows obtaining accurate initial camera poses and generate reliable 3D line segment landmarks as well as point landmarks. The proposed algorithm, denoted as PLSfSM (point and line structure from small motion), employs both point and Pl $\ddot {u}$ cker line reprojection constraints to recover structure from small motion. In particular, we propose a closed-form solution to estimate rotation and optimize rotation with line segment correspondences, which provides good initial guesses for rotation and line directions. Mathematically proven criteria are introduced to detect degeneracy of line reconstruction. The algorithm is evaluated on synthetic indoor dataset and simulation data. The qualitative experiments on both indoor and outdoor scenes are conducted to verify the robustness. The experimental results validate that the proposed algorithm, which combines both points and line segments for initialization, outperforms the state-of-the-art methods which only use points for initialization.

/pdf/monocular-visual-odometry-initialization-with-points-and-2xtre60fke.pdf

Keju Peng

Papers

3D reconstruction based on SIFT and Harris feature points

RGB-D SLAM Using Point-Plane Constraints for Indoor Environments.

Robust Visual Compass Using Hybrid Features for Indoor Environments

Seamless stitching of large area UAV images using modified camera matrix

Monocular Visual Odometry Initialization With Points and Line Segments