Improving the Model for Person Detection in Aerial Image Sequences Using the Displacement Vector: A Search and Rescue Scenario

Recent results in person detection using deep learning methods applied to aerial images gathered by Unmanned Aerial Vehicles (UAVs) have demonstrated the applicability of this approach in scenarios such as Search and Rescue (SAR) operations. In this paper, the continuation of our previous research is presented. The main goal is to further improve detection results, especially in terms of reducing the number of false positive detections and consequently increasing the precision value. We present a new approach that, as input to the multimodel neural network architecture, uses sequences of consecutive images instead of only one static image. Since successive images overlap, the same object of interest needs to be detected in more than one image. The correlation between successive images was calculated, and detected regions in one image were translated to other images based on the displacement vector. The assumption is that an object detected in more than one image has a higher probability of being a true positive detection because it is unlikely that the detection model will find the same false positive detections in multiple images. Based on this information, three different algorithms for rejecting detections and adding detections from one image to other images in the sequence are proposed. All of them achieved precision value about 80% which is increased by almost 20% compared to the current state-of-the-art methods.

Periodic Pattern Detection of Printed Fabric Based on Deep Learning Algorithm

Printed fabric patterns contain multiple repeat pattern primitives, which have a significant impact on fabric pattern design in the textile industry. The pattern primitive is often composed of multiple elements, such as color, form, and texture structure. Therefore, the more pattern elements it contains, the more complex the primitive is. In order to segment fabric primitives, this paper proposes a novel convolutional neural network (CNN) method with spatial pyramid pooling module as a feature extractor, which enables to learn the pattern feature information and determine whether the printed fabric has periodic pattern primitives. Furthermore, by choosing pair of activation peaks in a filter, a set of displacement vectors can be calculated. The activation peaks that are most accordant with the optimum displacement vector contribute to pick out the final size of primitives. The results show that the method with the powerful feature extraction capabilities of the CNN can segment the periodic pattern primitives of complex printed fabrics. Compared with the traditional algorithm, the proposed method has higher segmentation accuracy and adaptability.

Robust Estimation of Deformation from Observation Differences Using Some Evolutionary Optimisation Algorithms

In this paper, an original modification of the generalised robust estimation of deformation from observation differences (GREDOD) method is presented with the application of two evolutionary optimisation algorithms, the genetic algorithm (GA) and generalised particle swarm optimisation (GPSO), in the procedure of robust estimation of the displacement vector. The iterative reweighted least-squares (IRLS) method is traditionally used to perform robust estimation of the displacement vector, i.e., to determine the optimal datum solution of the displacement vector. In order to overcome the main flaw of the IRLS method, namely, the inability to determine the global optimal datum solution of the displacement vector if displaced points appear in the set of datum network points, the application of the GA and GPSO algorithms, which are powerful global optimisation techniques, is proposed for the robust estimation of the displacement vector. A thorough and comprehensive experimental analysis of the proposed modification of the GREDOD method was conducted based on Monte Carlo simulations with the application of the mean success rate (MSR). A comparative analysis of the traditional approach using IRLS, the proposed modification based on the GA and GPSO algorithms and one recent modification of the iterative weighted similarity transformation (IWST) method based on evolutionary optimisation techniques is also presented. The obtained results confirmed the quality and practical usefulness of the presented modification of the GREDOD method, since it increased the overall efficiency by about 18% and can provide more reliable results for projects dealing with the deformation analysis of engineering facilities and parts of the Earth’s crust surface.

Fluoroscopic 3D Image Generation from Patient-Specific PCA Motion Models Derived from 4D-CBCT Patient Datasets: A Feasibility Study

A method for generating fluoroscopic (time-varying) volumetric images using patient-specific motion models derived from 4-dimensional cone-beam CT (4D-CBCT) images is developed. 4D-CBCT images acquired immediately prior to treatment have the potential to accurately represent patient anatomy and respiration during treatment. Fluoroscopic 3D image estimation is done in two steps: 1) deriving motion models and 2) optimization. To derive motion models, every phase in a 4D-CBCT set is registered to a reference phase chosen from the same set using deformable image registration (DIR). Principal components analysis (PCA) is used to reduce the dimensionality of the displacement vector fields (DVFs) resulting from DIR into a few vectors representing organ motion found in the DVFs. The PCA motion models are optimized iteratively by comparing a cone-beam CT (CBCT) projection to a simulated projection computed from both the motion model and a reference 4D-CBCT phase, resulting in a sequence of fluoroscopic 3D images. Patient datasets were used to evaluate the method by estimating the tumor location in the generated images compared to manually defined ground truth positions. Experimental results showed that the average tumor mean absolute error (MAE) along the superior-inferior (SI) direction and the 95th percentile in two patient datasets were (2.29 mm and 5.79 mm) for patient 1 and (1.89 mm and 4.82 mm) for patient 2. This study has demonstrated the feasibility of deriving 4D-CBCT-based PCA motion models that have the potential to account for the 3D non-rigid patient motion and localize tumors and other patient anatomical structures on the day of treatment.

Vacuum-induced lateral deformation around a vertical drain in dredged slurry

The horizontal strain in the vacuum preloading/dewatering of dredged slurry is significant to the apparent clogging effect and estimation of surface settlement around a drain; however, it has seldom been investigated in previous studies. In this study, a vacuum consolidation model test assisted with the particle image velocimetry (PIV) technology was conducted. The displacement vector field was obtained through PIV analysis and image processing; it was used to visually observe the deformation features around a drain. Based on the displacement field, the vertical/horizontal strains at varied radial distances were calculated to explain the “soil pile” and apparent clogging effect. From the strain distribution with radial distances, a significant lateral compression zone near the drain and an extension zone at farther areas were confirmed. Furthermore, a simple explicit model was established to evaluate the horizontal strain within a prefabricated vertical drain unit cell considering a horizontal attenuated vacuum and compression/extension zone. Finally, this method was applied to predict the horizontal displacement in the model test. The results showed that the proposed method can estimate the lateral displacement of soft clay slurry fairly well.

Estimating the accumulative dose uncertainty for intracavitary and interstitial brachytherapy

Background Image-guided adaptive brachytherapy shows the ability to deliver high doses to tumors while sparing normal tissues. However, interfraction dose delivery introduces uncertainties to high dose estimation, which relates to normal tissue toxicity. The purpose of this study was to investigate the high-dose regions of two applicator approaches in brachytherapy. Method For 32 cervical cancer patients, the CT images from each fraction were wrapped to a reference image, and the displacement vector field (DVF) was calculated with a hybrid intensity-based deformable registration algorithm. The fractional dose was then accumulated to calculate the position and the overlap of high dose (D2cc) during multiple fractions. Result The overall Dice similarity coefficient (DSC) of the deformation algorithm for the bladder and the rectum was (0.97 and 0.91). No significant difference was observed between the two applicators. However, the location of the intracavitary brachytherapy (ICBT) high-dose region was relatively concentrated. The overlap volume of bladder and rectum D2cc was 0.42 and 0.71, respectively, which was higher than that of interstitial brachytherapy (ISBT) (0.26 and 0.31). The cumulative dose was overestimated in ISBT cases when using the GEC-recommended method. The ratio of bladder and rectum D2cc to the GEC method was 0.99 and 1, respectively, which was higher than that of the ISBT method (0.96 and 0.94). Conclusion High-dose regions for brachytherapy based on different applicator types were different. The 3D-printed ICBT has better high-dose region consistency than freehand ISBT and hence is more predictable.

Influence of Particle Shape on the Macroscopic and Mesolevel Mechanical Properties of Slip Zone Soil Based on 3D Scanning and 3D DEM

The macroscopic and mesolevel mechanical mechanisms of slip zone soil are a crucial subject for the research of landslide deformation evolution and slope control, but the effects of the shape and psephicity of coarse particles in a slip zone soil on the mechanical properties of the slip soil zone still need to be explored. Discrete element method (DEM) can effectively monitor and track the mesolevel mechanical parameters of geotechnical materials, such as displacement vector field, contact force chain, and particle coordination number. The rock blocks in the medium-sized shear test undergo a sophisticated process by 3D scanning technology, and a database of the blocks is established and accurately modeled by combining 3D DEM to simulate the indoor medium-sized shear test for numerical investigation in line with the test conditions. The numerical simulation results demonstrate that the psephicity and particle shape of the rock blocks significantly affect the dilatancy and mesolevel mechanical parameters of the slip zone soil specimens. In addition, the numerical models featured by poorer psephicity and more irregular particle shape display more evident dilatancy, larger particle coordination numbers, as well as better contact density inside the model. Some references for the study of the macroscopic and mesolevel mechanical mechanisms of slip zone soil are provided.

Optical pulses in carbon nanotubes with strong electron-electron interaction due to impurities

In this paper, we investigate electromagnetic pulse propagation in a medium with impurity carbon nanotubes, which are associated with the acoustic subsystem. The electron spectrum for the carbon system is obtained from the model that takes into account Coulomb impurities. Based on the Maxwell's and the wave equations for the vector of the medium displacements, we obtain the effective equations for the vector potential of the electromagnetic field and the component of the displacement vector of the medium. The dependence of the pulse shape on the various system parameters is analyzed.

Dense 3D displacement vector fields for point cloud-based landslide monitoring

We propose a novel fully automated deformation analysis pipeline capable of estimating real 3D displacement vectors from point cloud data. Different from the traditional methods that establish displacements based on the proximity in the Euclidean space, our approach estimates dense 3D displacement vector fields by searching for corresponding points across the epochs in the space of 3D local feature descriptors. Due to this formulation, our method is also sensitive to motion and deformations that occur parallel to the underlying surface. By enabling efficient parallel processing, the proposed method can be applied to point clouds of arbitrary size. We compare our approach to the traditional methods on point cloud data of two landslides and show that while the traditional methods often underestimate the displacements, our method correctly estimates full 3D displacement vectors.

Evaluation of inter- and intra-fraction 6D motion for stereotactic body radiation therapy of spinal metastases: influence of treatment time

Background The objective of this study was to analyze the amplitude of translational and rotational movements occurring during stereotactic body radiotherapy (SBRT) of spinal metastases in two different positioning devices. The relevance of intra-fractional imaging and the influence of treatment time were evaluated. Methods Twenty patients were treated in the supine position either (1) on a body vacuum cushion with arms raised and resting on a clegecel or (2) on an integrated SBRT solution consisting of a SBRT table top, an Orfit™ AIO system, and a vacuum cushion. Alignments between the cone beam computed tomography (CBCT) and the planning computed tomography allowed corrections of inter- and intra-fraction positional shifts using a 6D table. The absolute values of the translational and rotational setup errors obtained for 329 CBCT were recorded. The translational 3D vector, the maximum angle, and the characteristic times of the treatment fractions were calculated. Results An improvement in the mean (SD) inter-fraction 3D vector (mm) from 7.8 (5.9) to 5.9 (3.8) was obtained by changing the fixation devices from (1) to (2) (p < 0.038). The maximum angles were less than 2° for a total of 87% for (1) and 96% for (2). The mean (SD) of the intra-fraction 3D vectors (mm) was lower for the new 1.1 (0.8) positioning fixation (2) compared to the old one (1) 1.7 (1.7) (p = 0.004). The angular corrections applied in the intra-fraction were on average very low (0.4°) and similar between the two systems. A strong correlation was found between the 3D displacement vector and the fraction time for (1) and (2) with regression coefficients of 0.408 (0.262–0.555, 95% CI) and 0.069 (0.010–0.128, 95% CI), respectively. An accuracy of 1 mm would require intra-fraction imaging every 5 min for both systems. If the expected accuracy was 2 mm, then only system (2) could avoid intra-fractional imaging. Conclusions This study allowed us to evaluate setup errors of two immobilization devices for spine SBRT. The association of inter- and intra-fraction imaging with 6D repositioning of a patient is inevitable. The correlation between treatment time and corrections to be applied encourages us to move toward imaging modalities which allow a reduction in fraction time.