Search

This study aims to construct a pentuple bottom line hierarchical pyramid at PT Bank Negara Indonesia Tbk. The triple bottom line is the key to drive the success of implementing business sustainability. The pentuple bottom line is a deconstruction of the triple bottom line concept. The researcher used a postmodernist paradigm with imaginary dialogue as a research method. The imaginary dialogue consists of two specialists namely accountant and investor. The result of this research is a pentuple bottom line hierarchical pyramid model. The pentuple bottom line hierarchical pyramid is a model for measuring company managerial performance consisting of ethical responsibilities, profit, people, planet, and prophet. First, ethical responsibilities are ethical responsibilities, the company has an obligation to carry out good and fair business practices, second, profit is an effort to fulfill the company's economic welfare third, people, the company tries to provide benefits and advantages for the stakeholders, fourth, planet, the company can preserve the environment, the fifth, prophet is mental or spiritual balance in the process of preserving life, business organizations must consider the expression of God-consciousness, transcendental consciousness, honesty, the ability to self-contemplate and sincere love

Soybean cyst nematode (SCN, Heterodera glycines Ichinohe) is one of the most economically destructive pathogens. The soybean line Zhongpin03-5373 (ZP), which combines resistance genes from several donors, is highly resistant to SCN race 3 (SCN3). In our previous study, two QTL (rhg1 and GmSNAP11) were identified in a population of recombinant inbred lines derived from a cross between ZP and the susceptible parent Zhonghuang 13. The two QTL explained around one-third of the resistance, suggesting the presence of further QTL contributing to SCN resistance. In the present study, we used an improved version of the genetic map comprising the previously applied 1062 molecular markers and 47 newly developed InDel (insertion-deletion) markers. The improved map revealed a novel locus contributing to SCN3 resistance: qSCN3-1, flanked by InDel marker InDel1-7 and SNP marker Map-0047, explained 4.55% of the phenotypic variance for resistance to SCN3 and was not involved in digenic epistatic interaction with rhg1 and GmSNAP11. Haplotypes of Map-0047_CAPS (a CAPS marker developed for Map-0047) and InDel1-7 were significantly associated with SCN3 resistance in a panel of 209 resistant and susceptible accessions. Using further allele-combination analysis for three functional markers representing three cloned resistance genes (rhg1, Rhg4, and GmSNAP11) and two markers flanking qSCN3-1, we found that adding the resistance allele of qSCN3-1 greatly increased soybean resistance to SCN, even in diverse genetic backgrounds. The qSCN3-1 locus will be useful for marker-assisted polygene pyramid breeding and should be targeted for the future identification of candidate genes.

The world suffers from the potable water shortage problem. Solar still is a simple device used to convert the brackish water into a drinkable water. We proposed a new modification in the design of the pyramid solar still to enlarge the exposure area and decrease the depth of the water film as possible. So, four rotating cylinders were incorporated into the basin of the pyramid distiller. Also, three electric heaters were fixed on the basin water to raise its temperature. The energy required to run the heaters was captured from a PV system. The performance of the modified pyramid solar still with rotating cylinders (MPSSRC) was investigated under different rotating speeds (0.1, 0.2, 0.5, 1.0, 1.5, and 2.0 rpm). The experimental results revealed that the total distillates of the MPSSRC without heaters and reference still were 7300 and 3000 mL/m² a day, respectively with an improvement of 143 %. In addition, the total distillates of the MPSSRC with heaters and reference still were 9100 and 2900 mL/m² a day, respectively. So, the productivity was enhanced by 214 %. The optimum increase in productivity was obtained at the cylinders’ speed of 0.5 rpm. The optimum thermal efficiency of the MPSSRC was obtained when using the electric heaters with the rotating speed of 0.5 rpm, where it was 65 % and 54 % for the MPSSRC with and without heaters, respectively.

The objective of integrated pest and pollinator management (IPPM) is to co-manage for pest control and pollination goals. Departing from the well-established concept of integrated pest management, we include pollinator management in a hierarchical decision support system of management actions. We depict this support system as an IPPM pyramid. Priority is given to proactive measures at the base of the pyramid, which are undertaken through landscape and crop field management of mobile organisms, primarily arthropods. Farther up the pyramid, practices in the form of reactive use of biotic and abiotic inputs should align with basal actions. The goal of IPPM is to minimize trade-offs, and to maximize co-benefits and synergies between pest and pollinator management. We contend that IPPM has the potential to contribute to sustainable pest control and crop pollination, as well as provide broader environmental benefits.

The control of three-dimensional (3D) geometrical shapes is one of important approaches that contribute the development of new functionalities in material science. We produced 3D Si pyramids with a...

Semantic segmentation is a task that covers most of the perception needs of intelligent vehicles in an unified way. Recent studies witnessed that attention mechanisms achieve impressive performance in computer vision task. Current attention mechanisms based segmentation methods differ with each other in position and form of the attention mechanism, and perform differently in practice. This paper firstly introduces the effectiveness of multi-scale context features and attention mechanisms in segmentation tasks. We find that multi-scale and channel attention can play a vital role in constructing effective context features. Based on this analysis, this paper proposes an efficient attention pyramid network (EAPNet) for semantic segmentation. Specifically, to efficient handle the problem of segmenting objects at multiple scales, we design efficient channel attention pyramid (ECAP) which employ atrous convolution with channel attention in cascade or in parallel to capture multi-scale context by using multiple atrous rates. Furthermore, we propose a residual attention fusion block (RAFB), whose purpose is to simultaneously focus on meaningful low-level feature maps and spatial location information. At the same time, we will explore different channel attention modules and spatial attention modules, and describe their impact on network performance. We empirically evaluate our EAPNet on two semantic segmentation datasets, including PASCAL VOC 2012 and Cityscapes datasets. Experimental results show that without MS COCO pre-training and any post-processing, EAPNet achieved 81.7% mIoU on the PASCAL VOC 2012 validation set. With deeplabv3+ as the benchmark, EAPNet improve the model performance of more than 1.50% mIoU.

Disease is one of the main factors affecting crop growth. How to reflect the external morphological features of the disease and completely retain the color and texture information of the disease area is one of the key research issues for crop disease segmentation. Meanwhile, aiming at the problem of low segmentation accuracy with traditional convolution neural network-based methods in the crop disease leaf image, this paper proposes a spatial pyramid-oriented encoder-decoder cascade convolution neural network for crop disease leaf segmentation. The network consists of a region disease detection network and a region disease segmentation network. Region disease detection network is a kind of network combining cascade convolution neural network with spatial pyramid. This method connects the three-level convolution neural network model, where the structure of the three-level neural network model varies from simple to complex. Different crop disease leaf features are extracted from the different neural network levels. And images are screened to complete the detection of crop disease leaf. What’s more, a space pyramid pooling layer is added to each network level. This pooling strategy does not require fixed size input, which increases the size selection of input model. The region segmentation network is established based on the Encoder-Decoder structure. The multi-scale convolution kernel is used to improve the local receptive field of the original convolution kernel and accurately segment the crop disease leaf area. Finally, we conduct experiments on the crop disease leaf images under different conditions, the results show that the proposed method has higher segmentation accuracy. In terms of Precision, Correct segmentation, over-segmentation and under-segmentation indexes, etc., the average values of proposed method are more than 90%. The average dice similarity coefficient is over 95% under different background. Moreover, it can meticulously reflect the external morphological features of the crop disease leaf and relatively better retain the color and texture information.

Fruit detection plays a vital role in harvesting robot platforms. However, complicated environment attributes such as illumination variation, occlusion, have made fruit detection a challenging task. A robust YOLOMuskmelon model that is accurate and fast was proposed to solve detection difficulties. The YOLOMuskmelon model incorporated ReLU activated ResNet43 backbone with new 2,3,4,3,2 residual block arrangement, spatial pyramid pooling(SPP), complete Intersection over Union (CIoU) loss, feature pyramid network(FPN), and distance Intersection over Union-Non Maximum Suppression(DIoU-NMS) to improve detection performance. The obtained average precision (AP) results of YOLOMuskmelon at 89.6% is greater than YOLOv3 at 82.3%, YOLOResNet50 at 85.5%, but less than YOLOv4 at 91.6%. However, the detection speed of YOLOMuskmelon at 96.3 frame per second(fps) outperformed YOLOv3 at 56.6fps, YOLOv4 at 54.1fps and YOLOResNet50 at 71.2fps. Meanwhile, the YOLOMuskmelon which is 56.1% faster than YOLOv4 model showed a better generalization and real-time fruit harvesting robots prospect.

Pyramid B was one of the most important buildings in the sacred precinct of the Early Postclassic city of Tula, Hidalgo. On its summit was a temple supported by anthropomorphic and zoomorphic columns and four pillars containing the reliefs of 16 individuals and other images. Based on comparative analysis with other archaeological specimens and images from conquest era codices, I propose that all 16 individuals were warrior-kings in sacred dress bearing a suite of weapons associated with the Tollan-Xicocotitlan elite.

This article summarizes recent excavations of Edificio 4 in the Early Postclassic city of Tula, Hidalgo, which, despite prior evidence of its considerable importance, was largely unexcavated. Despite changes in strategy that resulted in discontinuous rather than complete exposure, excavation successfully delineated the entire structure and exposed portions of all or virtually all of its interior rooms, revealing a layout and architectural features notably different from those of the other buildings in Tula's monumental center, and suggest that Edificio 4 had functioned as a palace whose occupants were closely tied to Pyramid B, one of Tula's two largest pyramids. These excavations provide additional perspectives on previously noted similarities between Edificio 4 and the Casa de las Águilas of Aztec Tenochtitlan, revealing striking similarities in layout which, together with equally striking artistic similarities noted previously, make it almost certain that a major portion of the Casa de las Águilas was constructed in the image of the corresponding portion of Tula's Edificio 4.

Expression recognition in the wild is easily distorted by nonfrontal and asymmetry faces. In nonfrontal faces, some areas are compressed and distorted. Even after frontalization, these compressed areas may still be blurred and distort expression recognition. Additionally, asymmetrical expressions are common on half or local face areas and produce incorrect expression features. Therefore, this paper presents a half-face frontalization and pyramid Fourier frequency conversion method. Despite the location, range and intensity of incorrect expressions in nonfrontal faces being unknown, according to discrete Fourier transform, it can be proven that the frequency band of the correct expression is much larger than that of incorrect expression on the same face. This can be taken advantage of by pyramid frequency conversion, which is designed based on Fourier frequency conversion. It can adjust incorrect expression frequency in multiscales to take them out off the band-pass of the convolution operations of deep learning and be eliminated completely, whereas correct expression information is reserved. Thus, expressions can be recognized effectively.

The solar still is the simplest method used for desalination. But it needs improvement as it has low productivity. In this project the modification was made in the pyramid shaped solar still. The absorber tray was modified in the shape of pyramid structure. This will reduce the glass and absorber tray gap and so the productivity is increased. The Solar flat plate collector is used to preheat the inlet water, which is send into the solar still for desalination. When the higher temperature water into the solar still, the heat required for vaporizing the salt water is less and thus the productivity is increased. The low cost solar flat plate collector was designed and tested in this project. The experimental and theoretical analysis of the pyramid solar still and low cost solar flat plate collector was made. The productivity of the ordinary solar still is 1610 ml. The productivity of the modified pyramid solar still is 2250 ml. The improved in the productivity of 50% in the modified pyramid solar still is due to the less water and glass distance. Also the productivity of the modified pyramid solar still when it is integrated with the low cost solar flat plate collector is 3100 ml. This is 60% in the productivity because of higher temperature inlet water temperature and less water and glass distance.

Solar energy plays a vital role in improving the shelf of the agricultural product through drying, solar greenhouse drying is more optimal than using an open air drying, in this study selecting a ideal shape of greenhouse dryer among the other shapes is investigated. Six shapes of solar greenhouse dryers are designed in such a way that each dryer maintains the same volume of 30 ft3. The six shapes are Parabola, Quonset, Modified Quonset, Pyramid, Igloo and tropical. The inside temperature of greenhouse dryer is in the following order from maximum to minimum, Quonset, Tropical, Pyramid, Parabola, Modified Quonset and igloo during summer season. Quonset is capable of generating 64% more temperature when compared to atmosphere, whereas tropical generates 57%, pyramid generates 56%, parabola and modified Quonset generates 55% and igloo generates 53% more temperature when compared to atmosphere temperature during summer. Quonset shape generates 7% more temperature when compared to its rival tropical shape during summer and 5% more temperature during winter. The ideal shape of the solar greenhouse dryer is Quonset Shape, it generates a maximum of 72 DegC in summer and 66 DegC in winter.

Traditional deep learning detection network has poor effect on the detection of infrared dim and small targets on the sea in the case of interference or bad weather. In this paper, an improved dim and small infrared ship detection network based on Haar wavelet is proposed. The HaarConv module is designed based on the high-frequency features obtained by Haar wavelet decomposition, which further increases the feature extraction ability of the backbone network for small targets. Meanwhile, the HaarUp-HaarDown module is designed by using Haar forward and inverse transform, replacing the up-sampling layer of the feature pyramid network and the down-sampling layer of backbone network to retain smaller target features. Furthermore, the pseudo-label-based method enables the network to conduct semi-supervised learning, which reduces the labeling cost and improves detection accuracy while expanding the amount of training data. The above method is applied to the YOLOv5-s lightweight network and 11278 infrared images (3352 labeled) of dim and small ships are collected as a dataset. The results show that the introduction of semi-supervised training method effectively expands the training dataset, and the mAP@.5:.95 increases by 23.5%. The proposed Haar wavelet improvement method can effectively improve the detection accuracy of dim and small infrared ship targets by more than 2%, and the number of parameters increases by only about 0.02M. Compared with existing methods, the proposed method reaches the state-of-the-art result and has good generalization performance.

Salvage excavations along the right of way of a 2 km stretch of proposed highway crossing the northern part of the Postclassic city of Tula, Hidalgo utilized a multi-phase investigation strategy, featuring pedestrian survey and exploratory test-pitting. This fieldwork led to extensive excavation in five localities, which uncovered significant portions of both elite and non-elite residential compounds, a possible administrative structure, and two temples, one of which is the earliest example of a twin temple pyramid in western Mesoamerica. The diversity of structures and corresponding functions encountered in excavation are comparable to those found in previous excavations that suggest the city was organized into barrios, each with its own political, religious, social, and other institutions that mimic those of the larger urban polity. While these investigations confirm previous evidence of considerable destruction of the ancient city in recent decades, they also demonstrate that significant portions are still intact.

Solar energy plays a vital role in improving the shelf of the agricultural product through drying, solar greenhouse drying is more optimal than using an open air drying, in this study selecting a ideal shape of greenhouse dryer among the other shapes is investigated. Six shapes of solar greenhouse dryers are designed in such a way that each dryer maintains the same volume of 30 ft3. The six shapes are Parabola, Quonset, Modified Quonset, Pyramid, Igloo and tropical. The inside temperature of greenhouse dryer is in the following order from maximum to minimum, Quonset, Tropical, Pyramid, Parabola, Modified Quonset and igloo during summer season. Quonset is capable of generating 64% more temperature when compared to atmosphere, whereas tropical generates 57%, pyramid generates 56%, parabola and modified Quonset generates 55% and igloo generates 53% more temperature when compared to atmosphere temperature during summer. Quonset shape generates 7% more temperature when compared to its rival tropical shape during summer and 5% more temperature during winter. The ideal shape of the solar greenhouse dryer is Quonset Shape, it generates a maximum of 72 DegC in summer and 66 DegC in winter.

Broadband photodetection is of vital importance for both civil and technological applications. The widespread use of commercial photodiodes based on traditional semiconductors (e.g. GaN, Si, and InGaAs) is limited to the relatively narrow response range. In this work, we have demonstrated a self-driven and broadband photodetector based on WS2/pyramid Si 2D/3D mixed-dimensional van der Waals (vdW) heterojunction, which is assembled by directly transferring 2D WS2 film on 3D pyramid Si. Thanks to the enhanced light absorption with the pyramid Si structure, the defect-induced narrowed bandgap of the WS2 film, and high-quality vdW heterojunction, impressive device performances in terms of a large responsivity of 290 mA W−1, a high specific detectivity of up to 2.6 × 1014 Jones and an ultrabroad response spectrum ranging from 265 nm to 3.0 μm are achieved at zero bias. Importantly, the photodetector can function as an infrared imaging cell with a high spatial resolution. The totality of these excellent features confirms that the demonstrated WS2/pyramid Si 2D/3D mixed-dimensional vdW heterojunction device may hold great promise for applications in high-performance broadband infrared photodetection and imaging.

Micro-pyramid functional surfaces are currently widely used in various advanced scientific, technological, industrial, and engineering fields with their excellent performances of compactness, light weight and higher heat transfer performance. Many recent studies have introduced micro cutting as a method to achieve high-quality micro pyramid surfaces. This paper concerns a micro-pyramid with a height and slope of 60 μm and 30°. Firstly, numerical simulation of the optical effect related to micro-pyramid surfaces was carried out to reveal the mechanism of functional surface imaging and its typical and potential applications. The simulated optical effect shows that the micro-pyramid can form four virtual images on the same side of an object. Next, a novel and simple fabrication method for micro-pyramidal structures was developed by using cross cutting with a 120° V-tip diamond tool by ultra-precision raster milling (UPRM), which can obtain good surface quality, high form accuracy and efficient productivity in contrast to grinding, laser machining and etching. Finally, precision injection molding was employed to replicate a micro-pyramid on the PMMA for optical testing. Although the quality of molded micro pyramid pattern decreased, optical testing showed that clear images were obtained, and the experimental results were consistent with the simulation results.

The objective is to visualize energy consumption in North America using pyramidal geometry. The base polygon is made up of four points representing non-renewable consumption and the top corresponds to renewable consumption. To achieve the appropriate momentum of each non-renewable point, obtaining more or less height in the pyramid, a linear regression was obtained where the dependent variable is renewable and the independent variables are non-renewable. To obtain an appropriate proportion, the values were transformed into logarithms. The model visually identifies the position of renewable energy use according to the reduction of non-renewables. The main limitation was to stick to the annual BP Statistical Review of World Energy report, which groups regional information and thus the results were also regional. The originality lies in the pyramidal visualization of regional energy consumption. Some conclusions indicate that reducing 5% in average refined products could stimulate the use of renewable energies from 118.80 to 172.73 million tons, while the same reduction, but in fuel consumption could stimulate renewable consumption up to 139.77 million tons.

Scene text recognition has become a research hotspot owing to its abundant semantic information and various applications. Recent methods of scene text recognition usually focus on handling shape distortion, attention drift, or background noise, ignoring that text recognition encounters character scale-variation problem. To address this issue, in this paper, we propose a new scale-aware hierarchical attention network (SaHAN) for scene text recognition. Inspired by feature pyramid network, we exploit the inherent pyramidal structure of a deep convolutional network to retain multi-scale features for flexible receptive fields. Then, we construct a hierarchical attention decoder that performs the attention mechanism twice on multi-scale features to collect the most fine-grained information for prediction. The SaHAN is trained in a weak supervision way, requiring only images and corresponding text labels. Extensive experiments on seven benchmarks reveal that SaHAN achieves state-of-the-art performance.

Many cities order spatial data systematically, in particular aerial nadir images and orthophotomaps. However, only the orthoimages and orthophotomaps are usually used by the city administration, particularly in spatial planning. Some of the users are not aware of the possibilities as to how the aerial images can be used. Spatial data users, who may not be specialists in photogrammetry, are sometimes not aware that it is possible to obtain 3D information from 2D images as a point cloud. The idea of dense image matching (DIM) is well-known and described in the field of photogrammetry. Although dense image matching is a time- and memory-consuming process, this does not present a major drawback with modern computing. Images for the test area – Warsaw – are characterised by Ground Sampling Distance (GSD) equal to 8 cm. These images can be successfully used in change detection processes, comparing the dense image matching point cloud from two different dates. What is important while considering land cover change detection, is that it is not necessary to generate a detailed and high-density point cloud, e.g. in order to detect changes in buildings. The main idea of the article is to present the possibility of using higher levels of images pyramid in dense image matching within the change detection process as a way to optimize the processing time and point cloud accuracy. Which level of pyramid is needed to detect different changes in urban land cover will also be discussed.

Micro-expressions are brief and subtle facial expressions that go on and off the face in a fraction of a second. This kind of facial expressions usually occurs in high stake situations and is considered to reflect a human’s real intent. There has been some interest in micro-expression analysis, however, a great majority of the methods are based on classically established computer vision methods such as local binary patterns, histogram of gradients and optical flow. A novel methodology for micro-expression recognition using the Riesz pyramid, a multi-scale steerable Hilbert transform is presented. In fact, an image sequence is transformed with this tool, then the image phase variations are extracted and filtered as proxies for motion. Furthermore, the dominant orientation constancy from the Riesz transform is exploited to average the micro-expression sequence into an image pair. Based on that, the Mean Oriented Riesz Feature description is introduced. Finally the performance of our methods are tested in two spontaneous micro-expressions databases and compared to state-of-the-art methods.

Continuing isotopic investigation of the sacrificial burials and trophies beneath the Feathered Serpent Pyramid (Temple of Quetzalcoatl) in ancient Teotihuacan, Mexico, has produced new results. Isotopic proveniencing using bioapatite strontium and structural carbonate oxygen isotopes in tooth enamel was applied to 39 samples, 24 from the sacrificial victims and 15 from the trophy jaws. Both the strontium and oxygen isotope ratios suggest that most or all of the sacrificial victims came from the central highlands of Mexico, which includes the area of Teotihuacan. In this sense, we find somewhat less multiethnicity represented among the military at Teotihuacan than previously thought. Analysis of carbon isotope ratios in enamel structural carbonate indicated a childhood diet dominated by maize, relatively homogeneous among the victims at the pyramid, and typical for much of pre-Hispanic Mesoamerica.

Gliomas are characterized by high morbidity and high mortality in primary tumors. The identification of glioma type is helpful for radiologists to facilitate correct medical judgments and better prognosis for patients. In order to avoid harm to patients caused by a biopsy, radiologists attempt to classify Magnetic Resonance Images(MRI) using deep learning methods. In the present paper, we propose a deep learning convolutional neural network ResNet based on the pyramid dilated convolution for Gliomas classification. The pyramid dilated convolution is integrated into the bottom of Resnet to increase the receptive field of the original network and improve the classification accuracy. After adding the pyramid dilated convolution model, the receptive field of the original network underlying convolution was improved. A clinical dataset is used to test the pyramid dilated convolution ResNet neural network model proposed in this paper. The experimental results demonstrate that the proposed method can effectively improve glioma classification performance.

In this paper, we focus on the task query-based video localization, i.e., localizing a query in a long and untrimmed video. The prevailing solutions for this problem can be grouped into two categories: i) Top-down approach: It pre-cuts the video into a set of moment candidates, then it does classification and regression for each candidate; ii) Bottom-up approach: It injects the whole query content into each video frame, then it predicts the probabilities of each frame as a ground truth segment boundary (i.e., start or end). Both two frameworks have respective shortcomings: the top-down models suffer from heavy computations and they are sensitive to the heuristic rules, while the performance of bottom-up models is behind the performance of top-down counterpart thus far. However, we argue that the performance of bottom-up framework is severely underestimated by current unreasonable designs, including both the backbone and head network. To this end, we design a novel bottom-up model: Graph-FPN with Dense Predictions (GDP). For the backbone, GDP firstly generates a frame feature pyramid to capture multi-level semantics, then it utilizes graph convolution to encode the plentiful scene relationships, which incidentally mitigates the semantic gaps in the multi-scale feature pyramid. For the head network, GDP regards all frames falling in the ground truth segment as the foreground, and each foreground frame regresses the unique distances from its location to bi-directional boundaries. Extensive experiments on two challenging query-based video localization tasks (natural language video localization and video relocalization), involving four challenging benchmarks (TACoS, Charades-STA, ActivityNet Captions, and Activity-VRL), have shown that GDP surpasses the state-of-the-art top-down models.

Spatiotemporal information is essential for video salient object detection (VSOD) due to the highly attractive object motion for human's attention. Previous VSOD methods usually use Long Short-Term Memory (LSTM) or 3D ConvNet (C3D), which can only encode motion information through step-by-step propagation in the temporal domain. Recently, the non-local mechanism is proposed to capture long-range dependencies directly. However, it is not straightforward to apply the non-local mechanism into VSOD, because i) it fails to capture motion cues and tends to learn motion-independent global contexts; ii) its computation and memory costs are prohibitive for video dense prediction tasks such as VSOD. To address the above problems, we design a Constrained Self-Attention (CSA) operation to capture motion cues, based on the prior that objects always move in a continuous trajectory. We group a set of CSA operations in Pyramid structures (PCSA) to capture objects at various scales and speeds. Extensive experimental results demonstrate that our method outperforms previous state-of-the-art methods in both accuracy and speed (110 FPS on a single Titan Xp) on five challenge datasets. Our code is available at https://github.com/guyuchao/PyramidCSA.

This letter presents a self-supervised framework for learning depth from monocular videos. In particular, the main contributions of this letter include: (1) We present a windowed bundle adjustment framework to train the network. Compared to most previous works that only consider constraints from consecutive frames, our framework increases the camera baseline and introduces more constraints to avoid overfitting. (2) We extend the widely used U-Net architecture by applying a Spatial Pyramid Net (SPN) and a Super Resolution Net (SRN). The SPN fuses information from an image spatial pyramid for the depth estimation, which addresses the context information attenuation problem of the original U-Net. The SRN learns to estimate a high resolution depth map from a low resolution image, which can benefit the recovery of details. (3) We adopt a clip loss function to handle moving objects and occlusions that were solved by designing complicated network or requiring extra information (such as segmentation mask [1] ) in previous works. Experimental results show that our algorithm provides state-of-the-art results on the KITTI benchmark.

The choice of the operating wavelength of electromagnetic radiation is justified for a pyramid considered as an antenna. It is shown that due to the strong dispersion of the refractive index of the pyramid material, there will always be a part of the spectral range, in which the refractive index corresponds to the condition of electromagnetic wave localization (the photonic jet phenomenon). It is shown that the pyramid can simultaneously serve as a transmitting antenna both at the fundamental frequency and at multiple frequencies. Our consideration and approach are not limited only to the shape of the Cheops pyramid and can be generalized to all other shapes of known pyramids. It can be assumed that, despite the difference in the pyramid shapes throughout the world, such structures can play the role of antennas subject to the principle of mesoscale.

Image-based classification of histology sections plays an important role in predicting clinical outcomes. In this paper, we propose a Locality-Constrained Group Lasso Coding (LCGLC) method for microvessel image classification, which realizes the automatic “hot spot” detection of angiogenesis for human liver carcinoma. First, we extract Scale-Invariant Feature Transform (SIFT) descriptors on the Single-Opponent (SO) feature map, which simulates the biological functionality of human visual systems. Then, we present the feature-biased dictionary learning to effectively generate the dictionary of SIFT descriptors. With the learned dictionary, our LCGLC method introduces the locality constraint in classical group lasso problem to encode SIFT descriptors. Furthermore, we apply the Spatial Pyramid Matching (SPM) for the code pooling of microvessel images. Finally, we use Support Vector Machine (SVM) to classify a tissue image as having angiogenesis or not. Comprehensive experiments on the microvessel dataset show that the proposed LCGLC method achieves better performance compared with other representative approaches.

In this paper, a new method for manufacturing flexible and repeatable sensors made of silicon solar cells is reported. The method involves depositing the noble metal film directly onto the Si template and stripping out the substrate with a pyramid morphology by using an adhesive polymer. In order to evaluate the enhancement ability of the substrate, Rhodamine 6G (R6G) were used as surface-enhanced Raman scattering (SERS) probe molecules, and the results showed a high sensitivity and stability. The limit of detection was down to 10−12 M for R6G. The finite-difference time domain (FDTD) was used to reflect the distribution of the electromagnetic field, and the electric field was greatly enhanced on the surface of the inverted pyramidal substrate, especially in pits. The mechanism of Raman enhancement of two types of pyramidal SERS substrate, before and after stripping of the noble metal film, is discussed. By detecting low concentrations of plasmid DNA, the identification of seven characteristic peaks was successfully realized using a noble metallic pyramidal substrate.

Object detection has always been a challenging task in the field of computer vision due to complex background, large scale variation and many small objects, which are especially pronounced for remote sensing imagery. In recent years, object detection in remote sensing with the development of deep learning has also made great breakthroughs. At present, almost all state-of-the-art object detectors rely on pre-defined anchor boxes for remote sensing imagery. However, too many anchor boxes will introduce a large number of hyper-parameters, which not only increase the memory footprint, but also increase the computational redundancy of the detection model. In contrast, we propose an anchor-free single-stage detector for remote sensing imagery object detection, avoiding a large number of hyper-parameters related to the anchor box, which usually affect the performance of the detection model. Specially, considering the large-scale differences in the objects and the characteristics of small objects in remote sensing imagery, we design a dense path aggregation feature pyramid network (DPAFPN), which can make full use of the high-level semantic information and low-level location information in remote sensing imagery, and to a certain extent, avoid information loss during shallow feature transfer. In our experiments, extensive experiments on two public remote sensing datasets DOTA, NWPU VHR-10 were conducted. The experimental results demonstrate that our detector has good performance and is meaningful for object detection in remote sensing imagery.

This study proposes a novel face detector called DEFace that focuses on the challenging tasks of face detection to cope with a small size that is under 12 pixels and occlusions due to a mask or human body parts. This study proposed the extended feature pyramid network (FPN) module to detect small faces by expanding the range of P layer, and the network by adding a receptive context module (RCM) after each predicted feature head from the top-down pathway in the FPN architecture to enhance the feature discriminability and the robustness. Based on the FPN principle, the combination between the low- and high-resolutions are beneficial for object detection with different object sizes. Furthermore, with assistance from the RCM, the proposed method can use a broad range of context information especially for small faces. To evaluate the performance of the proposed method, various public face datasets are used such as the WIDER Face dataset, the face detection dataset and benchmark (FDDB), and the masked faces (MAFA) dataset, which consist of challenging samples such as small face regions and occlusions by hair or other people. The results indicate that DEFace can detect the face region more accurately in comparison to the other state-of-the-art methods while maintaining the processing time.

Small object is one of the primary challenges in the field of object detection, which is notably pronounced to the detection in the images from Unmanned Aerial Vehicles (UAV). Existing detectors based on deep-learning methods usually apply the feature extraction networks with a large down-sampling factor to obtain higher-level features. However, such big stride tends to make the feature information of small objects become the little point or even vanish in the low-resolution feature maps due to the limitation of pixels. Therefore, a novel structure called Multi-branch Parallel Feature Pyramid Networks (MPFPN) is proposed in this article, which aims to extract more abundant feature information of the objects with a small size. Specifically, the parallel branch is designed to recover the features that missed in the deeper layers. Meanwhile, a supervised spatial attention module (SSAM) is applied to weaken the impact of background noise inference and focus object information. Furthermore, we adopt cascade architecture in the Fast R-CNN stage for a more powerful localization capability. Experiments on the public drone-based datasets named VisDrone-DET demonstrate that our method achieves competitive performance compared with other state-of-the-art detection algorithms.

The semantic segmentation of remote sensing (RS) image is a hot research field. With the development of deep learning, the semantic segmentation based on a full convolution neural network greatly improves the segmentation accuracy. The amount of information on the RS image is very large, but the sample size is extremely uneven. Therefore, even the common network can segment RS images to a certain extent, but the segmentation accuracy can still be greatly improved. The common neural network deepens the network to improve the classification accuracy, but it has a lot of loss to the target spatial features and scale features, and the existing common feature fusion methods can only solve some problems. A segmentation network is built to solve the above problems very well. The network employs the InceptionV-4 network as the backbone and improves it. We modify the network structure and introduce the changed Atrous Spatial Pyramid Pooling module to extract the multi-scale features of the target from different training stages. Without losing the depth of the network, using Inception blocks to strengthen the width of the network can obtain more abstract features. At the same time, the backbone network is used for semantic fusion of the context, it can retain more spatial features, then an effective decoder network is designed. Finally, evaluate our model on the ISPRS 2D Semantic Labeling Contest Potsdam and Inria Aerial Image Labeling Dataset. The results show that the network has very superior performance, reaching 89.62% IOU score and 94.49% F1 score on the Potsdam dataset, and the IOU score on the Inria dataset has been greatly improved.

Ship detection of synthetic aperture radar (SAR) images is one of the research hotspots in the field of marine surveillance. Fusing salient features to detection network can effectively improve the precision of ship detection. However, how to effectively fuse the salient features of SAR images is still a difficult task. In this paper, to improve the ship detection precision, we design a novel one-stage ship detection network to fuse salient features and deep convolutional neural network (CNN) features. Firstly, a saliency map extraction algorithm is proposed. The algorithm is applied to generate saliency map by using multi-scale pyramid features and frequency domain features. Secondly, the backbone of the ship detection network contains a two-stream network. The upper-stream network uses the original SAR image as input to extract multi-scale deep CNN features. The lower-stream network uses the corresponding saliency map as input to acquire multi-scale salient features. Thirdly, for integrating the salient features to deep CNN features, a novel salient feature fusion method is designed. Finally, an improved bi-directional feature pyramid network is applied to the ship detection network for reducing the computational complexity and network parameters. The proposed methods are evaluated on the public ship detection dataset and the experimental results shows that it can make a significant improvement in the precision of SAR image ship detection.

To detect the shape of a small magnetic target in the shallow underground layer, this article proposes a recognition method based on Mask-RCNN. Firstly, using COMSOL software and MATLAB software to establish the database of magnetic targets model under different shapes and orientations, which greatly enriched the diversity of the training data set. Then, the ${G}_{\mathrm {zz}}$ component of the magnetic gradient tensor matrix is selected to highlight the shape features of the magnetic target, and the contour image is generated. The experimental data set is created by using the deep learning annotation tool Labelme. Finally, Resnet101 is used as the backbone network and feature pyramid network (FPN) structure is used to extract features. The regional recommendation network (RPN) is trained end-to-end to create regional recommendations for each feature map. The detection results of 200 test images show that the average detection accuracy of the method is 97%, and the recall rate is 94%. The simulation results show that the recognition accuracy and robustness of the method are improved.

In order to solve the problem of low recognition rate and low real-time performance of vehicle detection in complex road environment, a data-driven forward vehicle detection algorithm based on improved tiny-YOLOv3 is proposed. Based on tiny-YOLOv3, the context feature information is combined to increase the two scale detections of tiny-YOLOv3 to three. The spatial pyramid pooling (SPP) module is added to increase the number of feature channels to improve the network feature extraction ability. According to the dense arrangement of vehicles on the horizontal axis in the road image ahead, we change the grid size of tiny-YOLOv3 and increase the number of candidate boxes on the horizontal axis. In addition, combined with the characteristics of the vehicle size in the road image ahead, K-means clustering method is used to select the appropriate number and size of target candidate boxes. We obtain the optimal detection model by multi-scale training of the improved network. The experimental results show that the average accuracy of the improved algorithm on the KITTI datasets is 91.03%, which is 7.12% higher than that of tiny-YOLOv3. And the detection speed of improved network is 144 frames/s, which meets the real-time requirements.

Defect detection is an essential requirement for quality control in the production of printed circuit boards (PCBs) manufacturing. The traditional defect detection methods have various drawbacks, such as strongly depending on a carefully designed template, highly computational cost, and noise-susceptibility, which pose a significant challenge in a production environment. In this paper, a deep learning-based image detection method for PCB defect detection is proposed. This method builds a new network based on Faster RCNN. We use a ResNet50 with Feature Pyramid Networks as the backbone for feature extraction, to better detect small defects on the PCB. Secondly, we use GARPN to predict more accurate anchors and merge the residual units of ShuffleNetV2. The experimental results show that this method is more suitable for use in production than other PCB defect detection methods. We have also tested in other PCB defects dataset, and experiments have shown that this method is equally valid.

Traffic congestion due to vehicular accidents seriously affects normal travel, and accurate and effective mitigating measures and methods must be studied. To resolve traffic accident compensation problems quickly, a vehicle-damage-detection segmentation algorithm based on transfer learning and an improved mask regional convolutional neural network (Mask RCNN) is proposed in this paper. The experiment first collects car damage pictures for preprocessing and uses Labelme to make data set labels, which are divided into training sets and test sets. The residual network (ResNet) is optimized, and feature extraction is performed in combination with Feature Pyramid Network (FPN). Then, the proportion and threshold of the Anchor in the region proposal network (RPN) are adjusted. The spatial information of the feature map is preserved by bilinear interpolation in ROIAlign, and different weights are introduced in the loss function for different-scale targets. Finally, the results of self-made dedicated dataset training and testing show that the improved Mask RCNN has better Average Precision (AP) value, detection accuracy and masking accuracy, and improves the efficiency of solving traffic accident compensation problems.

Reliable poverty data are critical for regional economic analysis and policy making, especially considering that economic inequality and sustainable development are widespread social concerns. This article proposes a multitask learning model combining deep residual neural networks and feature pyramid networks to estimate poverty level from multiple sources including the night-time light data, Landsat 8 imagery, and spectral index data. We first train the multitask learning model using the multisource data in Chongqing, China and then estimate the representative economic indicators in the study area. The model is evaluated with the Pearson correlation coefficient of the actual and estimated economic indicators. The result shows that the proposed model outperforms other models with the Pearson correlation coefficient up to 0.87 in the annual estimates of economic indicators between 2013 and 2017. As all the data used in this article are publicly available, the proposed model can be used to estimate the economic indicators in other regions as well.

International audience; Image pyramids are employed for years in digital image processing. They permit to store and use different scales/levels of details of an image. To represent all the topological information of the different levels, combinatorial pyramids have proved having many interests. But, when using an explicit representation, one drawback of this structure is the memory space required to store such a pyramid. In this paper, this drawback is solved by defining a compact version of combinatorial pyramids. This definition is based on the definition of a new operation, called "merge-and-simplify", which simultaneously merges regions and simplifies their boundaries. Our experiments show that the memory space of our solution is much smaller than the one of the original version. Moreover, the computation time of our solution is faster, because there are less levels in our pyramid than in the original one.

Existing self-supervised monocular depth estimation methods usually explore increasingly large networks to achieve accurate estimation results. However, larger networks are more difficult to train and require more storage space. To balance the network size and the computational accuracy, we propose in this article a compact lightweight network for monocular depth estimation, named LW-Net. First, we construct a compact network by designing an iterative decoder with shared weights and a lightweight pyramid encoder. The proposed network includes significantly fewer parameters than most of the existing monocular depth estimation networks. Second, we exploit a self-supervised training strategy by combining the proposed LW-Net model with a pose network, and we then use a hybrid loss function to train the decoder and encoder separately. The proposed training strategy results in the LW-Net model achieving a better performance in terms of estimation accuracy than other methods. Finally, we respectively run the proposed LW-Net model on the KITTI and Make3D datasets to conduct a comprehensive comparison with several state-of-the-art methods. The experimental results demonstrate that our method performs the best in terms of computational accuracy while utilizing the fewest parameters. Specifically, the model parameters of our method are reduced by 46.6%, the time cost is decreased by 7.69%, and the frame rate is increased by 5.19% compared with the existing state-of-the-art method.

As an alternative to the popular rectangular parallelepiped model, we have developed a novel 3D analytical forward-problem solution for the gravity gradient tensor of a vertical pyramid model with parabolic density contrast variation. Its flexibility and effectiveness are demonstrated with the help of synthetic simulations and a case study involving Chintalapudi subbasin, India. We have addressed the singularities and numerical stability in numerical implementation of our algorithm for modeling and practical implementation.

The presently available staggered-grid finite-difference (SGFD) schemes for the 3D first-order elastic-wave equation can only achieve high-order spatial accuracy, but they exhibit second-order temporal accuracy. Therefore, the commonly used SGFD methods may suffer from visible temporal dispersion and even instability when relatively large time steps are involved. To increase the temporal accuracy and stability, we have developed a novel time-space-domain high-order SGFD stencil, characterized by ([Formula: see text])th-order spatial and ([Formula: see text])th-order temporal accuracies ([Formula: see text]), to numerically solve the 3D first-order elastic-wave equation. The core idea of this new stencil is to use a double-pyramid stencil with an operator length parameter [Formula: see text] together with the conventional second-order SGFD to approximate the temporal derivatives. At the same time, the spatial derivatives are discretized by the orthogonality stencil with an operator length parameter [Formula: see text]. We derive the time-space-domain dispersion relation of this new stencil and determine finite-difference (FD) coefficients using the Taylor-series expansion. In addition, we further optimize the spatial FD coefficients by using a least-squares (LS) algorithm to minimize the time-space-domain dispersion relation. To create accurate and reasonable P-, S-, and converted wavefields, we introduce the 3D wavefield-separation technique into our temporal high-order SGFD schemes. The decoupled P- and S-wavefields are extrapolated by using the P- and S-wave dispersion-relation-based FD coefficients, respectively. Moreover, we design an adaptive variable-length operator scheme, including operators [Formula: see text] and [Formula: see text], to reduce the extra computational cost arising from adopting this new stencil. Dispersion and stability analyses indicate that our new methods have higher accuracy and better stability than the conventional ones. Using several 3D modeling examples, we demonstrate that our SGFD schemes can yield greater temporal accuracy on the premise of guaranteeing high-order spatial accuracy. Through effectively combining our new stencil, LS-based optimization, large time step, variable-length operator, and graphic processing unit, the computational efficiency can be significantly improved for the 3D case.

Scene text detection has attracted many researches due to its importance to various applications. However, current approaches could not keep a good balance between accuracy and speed, i.e., a high-performance accuracy but with a low processing speed, or vice-versa. In this paper, we propose a novel model, named PyrBoxes, for efficient and effective multi-scale scene text detection. PyrBoxes consists of an SSD-based backbone that utilizes deep layers with strong semantics to detect texts in various sizes, and a proposed grouped pyramid module that leverages basic layers to append detailed locations into detection. Most existing detectors discard features from the basic layers due to the efficiency issue. We argue these layers contain fine-grained information, which is complementary to high-level semantics. Based on this, the grouped pyramid module combines the basic layers recursively into a detection layer via a top-down partition and a bottom-up group. Extensive experiments on both horizontal and oriented benchmarks, including ICDAR2013 Focused Scene Text, ICDAR2015 Incidental Text and COCO-Text, demonstrate that PyrBoxes achieves state-of-the-art or highly competitive performance compared with baselines, while runs significantly faster at inference. Furthermore, by experimenting on another ChiTVText dataset, PyrBoxes shows great generality to Chinese and long text lines. By visualizing some qualitative results, as expected, PyrBoxes provides more accurate locations and reduces the rate of missed detections, especially for small-sized texts.

In this paper, we design a new backbone network by using of dilated convolutions. By replacing the backbone network in the state-of-the-art FPN framework with the one we designed, we propose a new deep learning method called dilated convolutional feature pyramid network (DCFPN), and apply it to thigh fracture detection. To evaluate our method, we establish a dataset including 3842 thigh fracture X-ray radiographs collected from Linyi People's Hospital. The experiment results show that the Average Precision (AP) of DCFPN reaches 82.1% in the detection of 358 testing thigh fracture images, which is 3.9% higher than that of state-of-the-art FPN. As a consequence, the DCFPN has strong potential applicability in practical clinical environments.

Synthetic aperture radar (SAR) automatic target recognition plays a crucial role in both national defense and civil applications. Although many methods have been proposed, it remains one of the most challenging tasks to identify different terrain vehicle targets. In this paper, a novel method is proposed based on the attribute scattering center model (ASCM) and discriminative dictionary learning. This method contains three main stages. In the first stage, the low-level local features are generated by the convolution operation between SAR patches and the ASCMs with different parameters. These parameters are selected by genetic algorithm in advance with labeled patches. In the feature coding stage, a discriminative dictionary learning method is proposed with the label consistent and locality constraint on the sparse coefficient to incorporate the label information and local geometric information into the sparse representation, which is called label consistent and locality constraint discriminative dictionary learning (LcLcDDL) method. The low-level local features are sparsely coded using the dictionary learned by LcLcDDL method. In the feature pooling stage, the spatial pyramid matching method with max pooling is utilized to aggregate the coding coefficients of the low-level local features to generate the high-level global feature for each patch. The generated high-level global feature is feed into the linear support vector machine to recognize which classes the patch belongs to. Experimental results conducted on the moving and stationary target acquisition and recognition data set show that the performance of the proposed method is better than several available approaches.

This paper describes a new type of image segmentation method based on deep convolutional neural networks (DCNN) in the actual autonomous driving scene. The spatial pyramid pooling model is used to identify and segment the actual scene to complete the machine-aware task. In order to improve the information aggregation of the whole image, we use atrous convolution for multi-scale feature extraction based on the pyramid structure of image cascade network (ICNet), removing a residual module in the fifth stage of the network, in order to reduce the scale of the convolutional layer. The feature map is preprocessed by padding and atrous convolution before the four-level spatial pyramid model. Then, conventional convolutions are introduced to compose the atrous spatial pyramid pooling (ASPP) structure. Finally, the four feature maps in the pyramid are merged with the feature maps before input into the pyramid. This paper analyzes the spatial pyramid model, receptive field, and dilation convolution in detail and propose atrous image cascade network (AtICNet). Experiment results in the cityscape dataset have shown that AtICNet has some improvements over ICNet, by improving the accuracy of the segmentation.

Automatic face recognition in the wild still suffers from low-quality, low resolution, noisy, and occluded input images that can severely impact identification accuracy. In this paper, we present a novel technique to enhance the quality of such extreme low-resolution face images beyond the current state of the art. We model the correlation between high and low resolution faces in a multi-resolution pyramid and show that we can recover the original structure of an un-seen extreme low-resolution face image. By exploiting domain knowledge of the structure of the input signal and using sparse recovery optimization algorithms, we can recover a consistent sparse representation of the extreme low-resolution signal. The proposed super-resolution method is robust to noise and face alignment, and can handle extreme low-resolution faces up to 16x magnification factor with just 7 pixels between the eyes. Moreover, the formulation of the proposed algorithm allows for simultaneous occlusion removal capability, a desirable property that other super-resolution algorithms do not possess, to the best of our knowledge. Most importantly, we show that our method generalizes on real-world low-quality surveillance images, showing the potentially big impact this can have in a real-world scenario.

In this letter, we investigate fine-grained classification of arbitrary-oriented ships in very high resolution optical imagery using Bag of Word model with Spatial Pyramid (SP-BoW). Given that base...