New Method For Automatic Registration Research Articles

Image-to-Image Subpixel Registration Based on Template Matching of Road Network Extracted by Deep Learning

The vast digital archives collected by optical remote sensing observations over a long period of time can be used to determine changes in the land surface and this information can be very useful in a variety of applications. However, accurate change extraction requires highly accurate image-to-image registration, which is especially true when the target is urban areas in high-resolution remote sensing images. In this paper, we propose a new method for automatic registration between images that can be applied to noisy images such as old aerial photographs taken with analog film, in the case where changes in man-made objects such as buildings in urban areas are extracted from multitemporal high-resolution remote sensing images. The proposed method performs image-to-image registration by applying template matching to road masks extracted from images using a two-step deep learning model. We applied the proposed method to multitemporal images, including images taken more than 36 years before the reference image. As a result, the proposed method achieved registration accuracy at the subpixel level, which was more accurate than the conventional area-based and feature-based methods, even for image pairs with the most distant acquisition times. The proposed method is expected to provide more robust image-to-image registration for differences in sensor characteristics, acquisition time, resolution and color tone of two remote sensing images, as well as to temporal variations in vegetation and the effects of building shadows. These results were obtained with a road extraction model trained on images from a single area, single time period and single platform, demonstrating the high versatility of the model. Furthermore, the performance is expected to be improved and stabilized by using images from different areas, time periods and platforms for training.

Automatic Registration of Multi-Projector Based on Coded Structured Light

Multi-projector display systems are widely used in virtual reality, flight simulators, and other entertainment systems. Geometric distortion and color inconsistency are two key problems to be solved. In this paper a geometric correction principle is theoretically demonstrated and a consistency principle of geometric correction is first proposed. A new method of automatic registration of a multi-projector on a curved screen is put forward. Two pairs of binocular-cameras are used to reconstruct the curved screen. To capture feature points of the curved screen precisely, a group of red-blue coded structured light images is designed to be projected onto the screen. Geometric homography between each projector and the curved screen is calculated to gain a pre-warp template. Work which can gain a seamless display is illustrated by a six-projector system on the curved screen.

Improved Surface-Based Registration of CT and Intraoperative 3D Ultrasound of Bones.

The intraoperative registration of preoperative CT volumes is a key process of most computer-assisted orthopedic surgery (CAOS) systems. In this work, is reported a new method for automatic registration of long bones, based on the segmentation of the bone cortical in intraoperative 3D ultrasound images. A bone classifier was developed based on features, obtained from the principal component analysis of the Hessian matrix, of every voxel in an intraoperative ultrasound volume. 3D freehand ultrasound was used for the acquisition of the intraoperative ultrasound volumes. Corresponding bone surface segmentations in ultrasound and preoperative CT imaging were used for the intraoperative registration. Validation on a phantom of the tibia produced encouraging results, with a maximum mean segmentation error of 0.34⁡mm (SD=0.26⁡mm) and a registration accuracy error of 0.64⁡mm (SD=0.49⁡mm).

A new strategic neurosurgical planning tool for brainstem cavernous malformations using interactive computer graphics with multimodal fusion images

In this study, the authors used preoperative simulation employing 3D computer graphics (interactive computer graphics) to fuse all imaging data for brainstem cavernous malformations. The authors evaluated whether interactive computer graphics or 2D imaging correlated better with the actual operative field, particularly in identifying a developmental venous anomaly (DVA). The study population consisted of 10 patients scheduled for surgical treatment of brainstem cavernous malformations. Data from preoperative imaging (MRI, CT, and 3D rotational angiography) were automatically fused using a normalized mutual information method, and then reconstructed by a hybrid method combining surface rendering and volume rendering methods. With surface rendering, multimodality and multithreshold techniques for 1 tissue were applied. The completed interactive computer graphics were used for simulation of surgical approaches and assumed surgical fields. Preoperative diagnostic rates for a DVA associated with brainstem cavernous malformation were compared between conventional 2D imaging and interactive computer graphics employing receiver operating characteristic (ROC) analysis. The time required for reconstruction of 3D images was 3-6 hours for interactive computer graphics. Observation in interactive mode required approximately 15 minutes. Detailed anatomical information for operative procedures, from the craniotomy to microsurgical operations, could be visualized and simulated three-dimensionally as 1 computer graphic using interactive computer graphics. Virtual surgical views were consistent with actual operative views. This technique was very useful for examining various surgical approaches. Mean (±SEM) area under the ROC curve for rate of DVA diagnosis was significantly better for interactive computer graphics (1.000±0.000) than for 2D imaging (0.766±0.091; p<0.001, Mann-Whitney U-test). The authors report a new method for automatic registration of preoperative imaging data from CT, MRI, and 3D rotational angiography for reconstruction into 1 computer graphic. The diagnostic rate of DVA associated with brainstem cavernous malformation was significantly better using interactive computer graphics than with 2D images. Interactive computer graphics was also useful in helping to plan the surgical access corridor.

Verification of 3D freeform parts by registration of multiscale shape descriptors

Precision inspection of freeform parts takes an important role in manufacturing quality control. The aim of this inspection is to verify that the geometric dimensions and produced part tolerances meet quality requirements. This is achieved by fitting the scanned data to the computer-aided design (CAD) model. This verification is complicated since the produced part includes defects and distortions. Currently, industry uses semimanual verification, which is expensive, often inaccurate, and very time-consuming. This paper describes a new method for automatic registration and alignment of two 3D freeform shapes, one from the scanned data and the other from the CAD model. The method makes no assumptions about their initial positions. Instead, the proposed algorithm uses a multiscale shape descriptor to select features on the scanned data and identify their corresponding features on the CAD model. The proposed shape descriptor is invariant with respect to local shapes and is robust to noise. A coarse alignment is computed by finding and registering the best matching triplet of features. The iterative closest point algorithm uses resulting coarse alignment to achieve a tuned alignment. The proposed method is automatic, efficient, and straightforward to implement. The algorithm can also be effective in the case of partial scanned inspected shapes. The feasibility of the proposed method is demonstrated on a blade model.

Thermal influences on the habitat preference and the diurnal activity in three European Rana species.

The diurnal behaviour of frogs was recorded quantitatively in a habitatlike experimental environment by a new method of automatic registration via thermocouples. Three species with different habitat preferences during their summer activity period were chosen: the terrestrial common frog Rana temporaria LINNÈ and the semiaquatic water frog Rana lessonae CAMERANO and Rana ridibunda PALLAS. The activity, the location and the skin temperatures of these frogs were recorded continuously in four different temperature ranges (8.1° C-31.0° C) within the temperature span of the summer activity period. The thermal requirements and behavioural adaptations to the habitat of each species were analysed. The experimental results coincided with field observations and showed some details not yet known. The northern species R. temporaria exhibited a distinctive behavioural thermoregulation including cooling behaviour at high temperatures and warming behaviour at low temperatures during the day. In all temperatures tested these frogs remained on land changing their preferred location from the open area to the hiding places. The main activity period shifted from night to day with decreasing temperatures. The more southern species R. lessonae preferred higher temperatures than the other species showing basking behaviour during the day independent of the ambient temperature. With decreasing temperatures the preferred location changed from the shore to the water and the activity during the night almost disappeared. The closely related R. ridibunda tolerated high temperatures too, but only rarely basked. This species, however, reacted contrarily to decreasing temperatures: it changed its preference from the water to the land. This behavioural differenciation between the water frog species may be of importance for the actual habitat preference of these central european water frogs.

Kurzzeitkinetik des Streckungswachstums und des Youngschen Moduls von Weizenkoleoptilen nach IES-Applikation und Wasserpotentialänderungen )

Summary A new method for automatic registration of the extension growth of coleoptile, hypocotyl and stem segments was developed. The extension growth and Young’s modulus measured by the method of resonance frequency were analysed in wheat coleoptile segments after IAA-application and under water stress. The data obtained by both methods are in good agreement and suggest the conclusion that the IAA-induced extension growth of coleoptile segments is a result of the decrease in the rigidity of cell walls. The decrease of pressure potential by incubation of coleoptile segments with 0.4 M mannitol as medium completely inhibits extension growth, while the decrease of osmotic potential by incubation with 0.65 M gylcerol has only a small influence on the extension growth of coleoptile segments.