Search

In plants, sugar metabolism involves a complex interplay of genetic, molecular and environmental factors. To better understand the molecular mechanisms underlying these processes, we utilized a multi-layered approach that integrated transcriptomic and metabolomic datasets generated from multiple different varieties of sweet corn. Through this analysis, we found 2533 genes that were differentially expressed in the immature kernel tissues of sweet corn, including genes involved in transcriptional regulation, sugar metabolism, primary metabolism, and other processes associated with adaptability of sweet corn. We also detected 31 differential metabolites among the three types of sweet corn. Utilizing an integrated approach encompassing transcriptomics and eGWAS, we elucidated the transcriptional regulatory patterns governing these differential metabolites. Specifically, we delved into the transcriptional modulation of malate- and ubiquitin-associated genes across a range of sweet corn varieties, shedding new light on the molecular mechanisms underlying their regulation. This study provides a framework for future research aimed at improving the current understanding of sugar metabolism and regulatory gene networks in sweet corn, which could ultimately lead to the development of novel strategies for crop improvement.

Abstract Occlusion has always been a challenging research topic in the field of multi‐target tracking. The invisibility of the target in full occlusion increases the difficulty of continuous tracking, which makes the recovery failure when the target is re‐visible, and ultimately leads to a decrease in tracking accuracy. To address full occlusion problem, an effective multi‐object tracking algorithm with full occlusion handle and adaptive fusion features is proposed. Firstly, a spatio‐temporal model is established for full occlusion, and a simple, efficient and training‐free method is proposed to find full occluded targets. Secondly, local high discrimination features with better stability and independence is proposed to realize effective correlation between targets before and after the full occlusion. Finally, an adaptive feature fusion mechanism is proposed, which can adjust feature structure dynamically according to the occlusion state. The experimental results show that most evaluation metrics of the proposed algorithm are superior to those of some typical algorithms proposed in recent years under full occlusion tracking scenes. The proposed algorithm can realize accurate occluded targets identification and improve tracking robustness under short‐term, long‐term and frequent full occlusion.

Currently, most pointcloud classification methods heavily rely on huge numbers of labeled samples. Notably, labeling a large-scale multispectral LiDAR (MS-LiDAR) pointcloud is time-consuming and costly. To address this issue, we propose a feature perturbation weakly supervised network for classifying MS-LiDAR pointclouds using a few labeled samples, termed as FPWS-Net. In the FPWS-Net, we innovatively design a dual semantic inference structure, including a primary semantic inference module and an auxiliary semantic inference module. To provide the network with rich, accurate supervised signals, we embed kernel point convolution (KPConv) into the network for modelling the contextual information of MS-LiDAR pointclouds and propagating the signals between labeled and unlabeled points. Additionally, to constrain feature perturbations resulting from the dual semantic inference structure, fully leverage unlabeled points, and fit the architecture of the FPWS-Net, we combine consistency constraint and mutual pseudo-labeling loss. The proposed FPWS-Net is tested on two datasets, and achieves at least an average F1-score of 83.69 %, an mIoU of 78.81 %, and an OA of 95.97 % using only 0.1 % labeled points. The comparative experimental results demonstrate that the FPWS-Net not only outperforms the state-of-the-art (SOTA) weakly supervised networks, but also achieves the comparable classification performance to the fully supervised methods in the airborne MS-LiDAR pointcloud classification tasks.

Maize is one of the most successful crops with regard to the utilization of heterosis. The haploid induction technique is one of the fastest methods to obtain pure maize material at the present stage. However, the molecular mechanism of haploid doubling is rarely reported. In this study, we treated B73 and ZNC442 haploid young shoots with colchicine for 0 h, 6.2 h, and 10 h, and analyzed the differentially expressed genes (DEGs). We found that colchicine treatment for 6.2 h and 10 h compared to 0 h resulted in a total of 4868 co-DEGs. GO enrichment analysis and KEGG metabolic pathway analysis found significantly enriched 282 GO terms and 31 significantly pathways, respectively. Additionally, The GO term and KEGG pathway genes of spindle, cytoskeleton, microtubules and nuclear division were selected for analysis, and three candidate genes were screened by taking intersections. Zm00001d033112, Zm00001d010525, and Zm00001d043386 were annotated as kinesin-associated protein 13, kinesin-like protein KIN-10C, and kinesin light-chain LC6, respectively. The real-time fluorescence quantification (RT-PCR) results revealed that Zm00001d033112, Zm00001d010525, and Zm00001d043386 had the same trends as RNA-seq. Interestingly, Zm00001d033112 is homologous gene AT3G20150 in Arabidopsis, which was involved in the regulation of chromosome movement and mitotic spindle assembly. Our study suggests that kinesin genes may play an important role in doubling chromosomes, thus providing valuable information for future studies on the molecular mechanisms of chromosome doubling in maize.

Locoweed is a collective name for a variety of plants, such as Oxytropis and Astragalus L. When these plants are infected by some fungi or endophytes, they will produce an alkaloid (swainsonine) that is harmful to livestock. Chronic toxicity characterized by neurological disorders occurs in livestock overfed on locoweed, and swainsonine (SW) is considered a major toxic component. The mechanism of the SW synthesis of endophytic fungi from locoweed remains unknown. In order to further discover the possible synthetic pathway of SW, in this study, a mycotoxin (SW) producer, Alternaria oxytropis isolate, UA003, isolated from Locoweed plants, and its mutant were subjected to transcriptomic analyses to ascertain the genes involved in the synthesis of this toxin. Mutant strain A. oxytropis E02 was obtained by ethyl methanesulfonate (EMS) mutagenesis treatment, and the strains were sequenced with different culture times for transcriptomic analysis and screening of differentially expressed genes. The results show a highly significant (p < 0.01) increase in SW yield in the A. oxytropis E02 strain obtained by EMS mutagenesis treatment compared to A. oxytropis UA003. A total of 637 differentially expressed genes were screened by transcriptome sequencing analysis, including 11 genes potentially associated with SW biosynthesis. These genes were screened using GO and KEGG data annotation and analysis. Among the differential genes, evm.TU.Contig4.409, evm.TU.Contig19.10, and evm.TU.Contig50.48 were associated with L-lysine biosynthesis, the L-pipecolic acid pathway, and the α-aminoadipic acid synthesis pathway. This study provides new insights to elucidate the mechanism of SW synthesis of endophytic fungi in locoweed and provides data support for further exploration of A. oxytropis genomics studies.

The objective of this study was to develop an indirect ELISA utilizing a polyclonal antibody against bovine rotavirus (BRV) VP6 protein. To achieve this, pcDNA3.1-VP6, a recombinant eukaryotic expression plasmid, was constructed based on the sequence of the conserved BRV gene VP6 and was transfected into CHO-K1 cells using the transient transfection method. The VP6 protein was purified as the coating antigen using nickel ion affinity chromatography, and an indirect ELISA was subsequently established. The study found that the optimal concentration of coating for the VP6 protein was 1 μg/mL. The optimal blocking solution was 3% skim milk, and the blocking time was 120 min. The secondary antibody was diluted to 1:4000, and the incubation time for the secondary antibody was 30 min. A positive result was indicated when the serum OD450 was greater than or equal to 0.357. The coefficients of variation were less than 10% both within and between batches, indicating the good reproducibility of the method. The study found that the test result was positive when the serum dilution was 217, indicating the high sensitivity of the method. A total of 24 positive sera and 40 negative sera were tested using the well-established ELISA. The study also established an indirect ELISA assay with good specificity and sensitivity for the detection of antibodies to bovine rotavirus. Overall, the results suggest that the indirect ELISA method developed in this study is an effective test for detecting such antibodies.

The changes in the composition of intestinal microbiota and metabolites have been linked to digestive disorders in calves, especially neonatal calf diarrhea. Bovine rotavirus (BRV) and bovine coronavirus (BCoV) are known to be the primary culprits behind neonatal calf diarrhea. In this study, we analyzed changes in the fecal microbiota and metabolites of calves with neonatal diarrhea associated with BRV and BCoV infection using high-throughput 16S rRNA sequencing and metabolomics technology. The microbial diversity in the feces of calves infected with BRV and BCoV with diarrhea decreased significantly, and the composition changed significantly. The significant increase of Fusobacterium and the reductions of some bacteria genera, including Faecalibacterium, Bifidobacterium, Ruminococcus, Subdoligranulum, Parabacteroides, Collinsella, and Olsenella, etc., were closely related to diarrhea associated with BRV and BCoV infection. Metabolites in the feces of BRV and BCoV-infected calves with diarrhea were significantly changed. Phosphatidylcholine [PC; 16:1(9 Z)/16:1(9 Z)], lysophosphatidylethanolamine (LysoPE; 0:0/22:0), lysophosphatidylcholine (LysoPC; P-16:0) and LysoPE (0:0/18:0) were significantly higher in the feces of BRV-infected calves with diarrhea. In contrast, some others, such as desthiobiotin, were significantly lower. BRV infection affects glycerophospholipid metabolism and biotin metabolism in calves. Two differential metabolites were significantly increased, and 67 differential metabolites were significantly reduced in the feces of BCoV-infected calves with diarrhea. Seven significantly reduced metabolites, including deoxythymidylic acid (DTMP), dihydrobiopterin, dihydroneopterin triphosphate, cortexolone, cortisol, pantetheine, and pregnenolone sulfate, were enriched in the folate biosynthesis, pantothenate and CoA biosynthesis, pyrimidine metabolism, and steroid hormone biosynthesis pathway. The decrease in these metabolites was closely associated with increased harmful bacteria and reduced commensal bacteria. The content of short-chain fatty acids (SCFAs) such as acetic acid and propionic acid in the feces of BRV and BCoV-infected calves with diarrhea was lower than that of healthy calves, which was associated with the depletion of SCFAs-producing bacteria such as Parabacteroides, Fournierella, and Collinsella. The present study showed that BRV and BCoV infections changed the composition of the calf fecal microbiota and were associated with changes in fecal metabolites. This study lays the foundation for further revealing the roles of intestinal microbiota in neonatal calf diarrhea associated with BRV and BCoV infection.

Point cloud semantic segmentation, which contributes to scene understanding at different scales, is crucial for three-dimensional reconstruction and digital twin cities. However, current semantic segmentation methods mostly extract multi-scale features by down-sampling operations, but the feature maps only have a single receptive field at the same scale, resulting in the misclassification of objects with spatial similarity. To effectively capture the geometric features and the semantic information of different receptive fields, a multi-scale voxel-point adaptive fusion network (MVP-Net) is proposed for point cloud semantic segmentation in urban scenes. First, a multi-scale voxel fusion module with gating mechanism is designed to explore the semantic representation ability of different receptive fields. Then, a geometric self-attention module is constructed to deeply fuse fine-grained point features with coarse-grained voxel features. Finally, a pyramid decoder is introduced to aggregate context information at different scales for enhancing feature representation. The proposed MVP-Net was evaluated on three datasets, Toronto3D, WHU-MLS, and SensatUrban, and achieved superior performance in comparison to the state-of-the-art (SOTA) methods. For the public Toronto3D and SensatUrban datasets, our MVP-Net achieved a mIoU of 84.14% and 59.40%, and an overall accuracy of 98.12% and 93.30%, respectively.

Accurate pavement crack detection is important for routine maintenance of pavements and reduction of possible traffic accidents. Most existing rule- or learning-based point-level approaches cannot achieve high detection accuracy and efficiency owing to the disorderly arrangement, scattered intensities, diverse crack structures, large data volumes, and complex annotation of mobile laser scanning (MLS) point clouds. To address these issues, we developed SCL-GCN, a Stratified Contrastive Learning Graph Convolution Network with a novel dual-branch architecture for MLS-point cloud-based pavement crack detection. First, a multi-scale graph representation construction module was designed based on a stratification strategy. This module creates strengthened spaces for the raw pavement point cloud and its downsampled subset, from which adjacency matrices and initial representations are generated. The stratification strategy samples neighbors densely in the raw point clouds and sparsely in the downsampled subset to form the neighborhood for each point, utilizing long-range contexts to increase the effective receptive field while lowing the extra computation. Next, a graph feature contrastive learning module is proposed to take advantage of stratified features. This module supervises the learning process of the two branches to avoid learning bias caused by an imbalanced data distribution, promoting convergence and improving performance. The experimental results show that the developed SCL-GCN model outperforms state-of-the-art methods. With a training/testing ratio of only 1:6 and an overall training time of less than 70 min, the average precision, recall, and F1-score of the SCL-GCN reached 75.7%, 75.1%, and 75.2%, respectively.

Fruit ripening is a highly complicated process that is accompanied by the formation of fruit quality. In recent years, a series of studies have demonstrated post-transcriptional control play important roles in fruit ripening and fruit quality formation. Till now, the post-transcriptional mechanisms for watermelon fruit ripening have not been comprehensively studied. In this study, we conducted PacBio single-molecule long-read sequencing to identify genome-wide alternative splicing (AS), alternative polyadenylation (APA) and long non-coding RNAs (lncRNAs) in watermelon fruit. In total, 6,921,295 error-corrected and mapped full-length non-chimeric (FLNC) reads were obtained. Notably, more than 42,285 distinct splicing isoforms were derived from 5,891,183 intron-containing full-length FLNC reads, including a large number of AS events associated with fruit ripening. In addition, we characterized 21,506 polyadenylation sites from 11,611 genes, 8703 of which have APA sites. Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis showed that fructose and mannose metabolism, starch and sucrose metabolism and carotenoid biosynthesis were both enriched in genes undergoing AS and APA. These results suggest that post-transcriptional regulation might potentially have a key role in regulation of fruit ripening in watermelon. Taken together, our comprehensive PacBio long-read sequencing results offer a valuable resource for watermelon research, and provide new insights into the molecular mechanisms underlying the complex regulatory networks of watermelon fruit ripening.

The indolizidine alkaloid-swainsonine (SW) is the main toxic component of locoweeds and the main cause of locoweed poisoning in grazing animals. The endophytic fungi, Alternaria Section Undifilum spp., are responsible for the biosynthesis of SW in locoweeds. The swnK gene is a multifunctional complex enzyme encoding gene in fungal SW biosynthesis, and its encoding product plays a key role in the multistep catalytic synthesis of SW by fungi using pipecolic acid as a precursor. However, the transcriptional regulation mechanism of the swnK gene is still unclear. To identify the transcriptional regulators involved in the swnK gene in endophytic fungi of locoweeds, we first analyzed the upstream non-coding region of the swnK gene in the A. oxytropis UA003 strain and predicted its high transcriptional activity region combined with dual-luciferase reporter assay. Then, a yeast one-hybrid library of A. oxytropis UA003 strain was constructed, and the transcriptional regulatory factors that may bind to the high-transcriptional activity region of the upstream non-coding region of the swnK gene were screened by this system. The results showed that the high transcriptional activity region was located at −656 bp and −392 bp of the upstream regulatory region of the swnK gene. A total of nine candidate transcriptional regulator molecules, including a C2H2 type transcription factor, seven annotated proteins, and an unannotated protein, were screened out through the Y1H system, which were bound to the upstream high transcriptional activity region of the swnK gene. This study provides new insight into the transcriptional regulation of the swnK gene and lays the foundation for further exploration of the regulatory mechanisms of SW biosynthesis in fungal endophytic locoweeds.

Semantic segmentation of large-scale mobile laser scanning (MLS) point clouds is essential for urban scene understanding. However, most of the existing semantic segmentation methods require a large quantity of labeled data, which are labor-intensive and time-consuming. To this end, we propose a multi-branch weakly supervised learning network (WSPointNet) to solve this challenge. Our method includes a basic weakly supervised framework and a multi-branch weakly supervised module. With input point clouds and few labels, the basic weakly supervised framework outputs the prediction values of the input point clouds and the underlying supervised signals of the whole network. Next, the multi-branch weakly supervised module explores the potential information of the unlabeled and labeled points while preventing model over-fitting. Concretely, the module includes an ensemble prediction constraint branch, a contrast-guided entropy regularization branch, and an adaptive pseudo-label learning branch. The ensemble prediction constraint branch aims to enhance the prediction stability of the point cloud. The contrast-guided entropy regularization branch is proposed to prevent model over-fitting by comparing the ensemble prediction labels with the current prediction labels. The adaptive pseudo-label learning branch provides efficient and adaptive supervised signals for model training by the consistency cost and ensemble prediction. Extensive experiments conducted on two MLS benchmarks showed that our WSPointNet achieved a promising semantic segmentation performance with sparse annotated points. For the public Toronto3D dataset, with only 0.1% labeled points, our WSPointNet obtained an overall accuracy of 96.76% and a mIoU of 78.96%, which outperformed most of comparative fully supervised methods.

Water is a kind of vital natural resource, which acts as the lifeblood of the ecosystem and the energy source for the living and production activities of humans. Regularly mapping the conditions of water resources and taking effective measures to prevent them from pollutions and shortages are very important and necessary to maintain the sustainability of the ecosystem. As a preliminary step for image-based water resource analysis, the complete recognition and accurate extraction of water bodies are important prerequisites in many applications. Nevertheless, due to the issues of topology diversities, appearance variabilities, and land cover interferences, there is still a large gap to achieve the human-level water bodies interpretation quality. This paper presents a hierarchical attentive high-resolution network, abbreviated as WaterHRNet, for extracting water bodies from remote sensing imagery. First, by building a multibranch high-resolution feature extractor integrated with global feature semantics aggregation, the WaterHRNet behaves laudably to supply high-quality, strong-semantic feature representations. Furthermore, by inlaying an effective feature attention scheme with the comprehensive exploitation of both the spatial and channel feature significances, the WaterHRNet is forced to strengthen the semantic-determinate, task-aware feature encodings. In addition, by designing a hierarchical processing principle with the progressive enhancement of category-attentive feature semantics, the WaterHRNet performs effectively to export semantic-discriminative, target-oriented feature representations for precise water body segmentation. The WaterHRNet is elaborately verified both quantitatively and qualitatively on three remote sensing datasets. Evaluation results show that the WaterHRNet achieves an average precision of 98.44%, average recall of 97.84%, average IoU of 96.35%, and average F1-score of 98.14%. Comparative analyses also demonstrate the superior performance and excellent feasibility of the WaterHRNet in segmenting water bodies.

Ubiquitination-mediated protein degradation plays important roles in ABA signal transduction and delivering responses to chloroplast stress signals in plants, but additional E3 ligases of protein ubiquitination remain to be identified to understand the complex signaling network. Here we reported that ZEITLUPE (ZTL), an F-box protein, negatively regulates abscisic acid (ABA) signaling during ABA-inhibited early seedling growth and ABA-induced stomatal closure in Arabidopsis thaliana. Using molecular biology and biochemistry approaches, we demonstrated that ZTL interacts with and ubiquitinates its substrate, CHLH/ABAR (Mg-chelatase H subunit/putative ABA receptor), to modulate CHLH stability via the 26S proteasome pathway. CHLH acts genetically downstream of ZTL in ABA and drought stress signaling. Interestingly, ABA conversely induces ZTL phosphorylation, and high levels of ABA also induce CHLH proteasomal degradation, implying that phosphorylated ZTL protein may enhance the affinity to CHLH, leading to the increased degradation of CHLH after ABA treatment. Taken together, our results revealed a possible mechanism of reciprocal regulation between ABA signaling and the circadian clock, which is thought to be essential for plant fitness and survival.

Folate is commonly synthesized in natural plants and is an essential water-soluble vitamin of great importance inhuman health. Although the key genes involved in folate biosynthesis and transformation pathways have been identified in plants, the genetic architecture of folate in sweet corn kernels remain largely unclear. In this study, an association panel of 295 inbred lines of sweet corn was constructed. Six folate derivatives were quantified in sweet corn kernels at 20 days after pollination and a total of 95 loci were identified for eight folate traits using a genome-wide association study. A peak GWAS signal revealed that natural variation in ZmFCL, encoding a 5-formyltetrahydrofolate cyclo-ligase, accounted for 30.12% of phenotypic variation in 5-FTHF content. Further analysis revealed that two adjacent SNPs on the second exon resulting in an AA-to-GG in the gene and an Asn-to-Gly change in the protein could be the causative variant influencing 5-FTHF content. Meanwhile, 5-FTHF content was negatively correlated with ZmFCL expression levels in the population. These results extend our knowledge regarding the genetic basis of folate and provide molecular markers for the optimization of folate levels in sweet corn kernels.

MYB transcription factors (TFs) mediate plant responses and defenses to biotic and abiotic stresses. The effects of overexpression of MYB37, an R2R3 MYB subgroup 14 transcription factors in Arabidopsis thaliana, on chlorophyll content, chlorophyll fluorescence parameters, reactive oxygen species (ROS) metabolism, and the contents of osmotic regulatory substances were studied under 100 mM NaCl stress. Compared with the wild type (Col-0), MYB37 overexpression significantly alleviated the salt stress symptoms in A. thaliana plants. Chlorophyll a (Chl a) and chlorophyll b (Chl b) contents were significantly decreased in OE-1 and OE-2 than in Col-0. Particularly, the Chl a/b ratio was also higher in OE-1 and OE-2 than in Col-0 under NaCl stress. However, MYB37 overexpression alleviated the degradation of chlorophyll, especially Chl a. Salt stress inhibited the activities of PSII and PSI in Arabidopsis leaves, but did not affect the activity of PSII electron donor side oxygen-evolving complex (OEC). MYB37 overexpression increased photosynthesis in Arabidopsis by increasing PSII and PSI activities. MYB37 overexpression also promoted the transfer of electrons from QA to QB on the PSII receptor side of Arabidopsis under NaCl stress. Additionally, MYB37 overexpression increased Y(II) and Y(NPQ) of Arabidopsis under NaCl stress and decreased Y(NO). These results indicate that MYB37 overexpression increases PSII activity and regulates the proportion of energy dissipation in Arabidopsis leaves under NaCl stress, thus decreasing the proportion of inactivated reaction centers. Salt stress causes excess electrons and energy in the photosynthetic electron transport chain of Arabidopsis leaves, resulting in the release of reactive oxygen species (ROS), such as superoxide anion and hydrogen peroxide, leading to oxidative damage. Nevertheless, MYB37 overexpression reduced accumulation of malondialdehyde in Arabidopsis leaves under NaCl stress and alleviated the degree of membrane lipid peroxidation caused by ROS. Salt stress also enhanced the accumulation of soluble sugar (SS) and proline (Pro) in Arabidopsis leaves, thus reducing salt stress damage to plants. Salt stress also degraded soluble protein (SP). Furthermore, the accumulation of osmoregulation substances SS and Pro in OE-1 and OE-2 was not different from that in Col-0 since MYB37 overexpression in Arabidopsis OE-1, and OE-2 did not significantly affect plants under NaCl stress. However, SP content was significantly higher in OE-1 and OE-2 than in Col-0. These results indicate that MYB37 overexpression can alleviate the degradation of Arabidopsis proteins under NaCl stress, promote plant growth and improve salt tolerance.

Ship detection using synthetic aperture radar (SAR) has been extensively utilized in both the military and civilian fields. On account of complex backgrounds, large scale variations, small-scale targets, and other challenges, it is difficult for current SAR ship detection methods to strike a balance between detection accuracy and computation efficiency. To overcome those challenges, ESarDet, an efficient SAR ship detection method based on contextual information and a large effective receptive field (ERF), is proposed. We introduce the anchor-free object detection method YOLOX-tiny as a baseline model and make several improvements to it. First, CAA-Net, which has a large ERF, is proposed to better merge the contextual and semantic information of ships in SAR images to improve ship detection, particularly for small-scale ships with complex backgrounds. Further, to prevent the loss of semantic information regarding ship targets in SAR images, we redesign a new spatial pyramid pooling network, namely A2SPPF. Finally, in consideration of the challenge posed by the large variation in ship scale in SAR images, we design a novel convolution block, called A2CSPlayer, to enhance the fusion of feature maps from different scales. Extensive experiments are conducted on three publicly available SAR ship datasets, DSSDD, SSDD, and HRSID, to validate the effectiveness of the proposed ESarDet. The experimental results demonstrate that ESarDet has distinct advantages over current state-of-the-art (SOTA) detectors in terms of detection accuracy, generalization capability, computational complexity, and detection speed.

Object detection from remote sensing images serves as an important prerequisite to many applications. However, caused by scale and orientation variations, appearance and distribution diversities, occlusion and shadow contaminations, and complex environmental scenarios of the objects in remote sensing images, it brings great challenges to realize highly accurate recognition of geospatial objects. This paper proposes a novel one-stage anchor-free capsule network (OA-CapsNet) for detecting geospatial objects from remote sensing images. By employing a capsule feature pyramid network architecture as the backbone, a pyramid of high-quality, semantically strong feature representations are generated at multiple scales for object detection. Integrated with two types of capsule feature attention modules, the feature quality is further enhanced by emphasizing channel-wise informative features and class-specific spatial features. By designing a centreness-assisted one-stage anchor-free object detection strategy, the proposed OA-CapsNet performs effectively in recognizing arbitrarily-orientated and diverse-scale geospatial objects. Quantitative evaluations on two large remote sensing datasets show that a competitive overall accuracy with a precision, a recall, and an Fscore of 0.9625, 0.9228, and 0.9423, respectively, is achieved. Comparative studies also confirm the feasibility and superiority of the proposed OA-CapsNet in geospatial object detection tasks.

The information-accurate road network database is greatly significant and provides essential input to many transportation-related activities. Recently, remote sensing images have been an important data source for assisting rapid road network updating tasks. However, due to the diverse challenging scenarios of roads in remote sensing images, such as occlusions, shadows, material diversities, and topology variations, it is still difficult to realize highly accurate extraction of roads. This paper proposes a novel context-augmentation and self-attention capsule feature pyramid network (CS-CapsFPN) to extract roads from remote sensing images. By designing a capsule feature pyramid network architecture, the proposed CS-CapsFPN can extract and fuze different-level and different-scale high-order capsule features to provide a high-resolution and semantically strong feature representation for predicting the road region maps. By integrating the context-augmentation and self-attention modules, the proposed CS-CapsFPN can exploit multi-scale contextual properties at a high-resolution perspective and emphasize channel-wise informative features to further enhance the feature representation robustness. Quantitative evaluations on two test datasets show that the proposed CS-CapsFPN achieves a competitive performance with a precision, recall, intersection-over-union, and Fscore of 0.9470, 0.9407, 0.8957, and 0.9438, respectively. Comparative studies also confirm the feasibility and superiority of the proposed CS-CapsFPN in road extraction tasks.

Precisely identifying pavement cracks from charge-coupled devices (CCDs) captured high-resolution images faces many challenges. Even though convolutional neural networks (CNNs) have achieved impressive performance in this task, the stacked convolutional layers fail to extract long-range contextual features and impose high computational costs. Therefore, we propose a locally enhanced Transformer network (LETNet) to completely and efficiently detect pavement cracks. In the LETNet, Transformer is employed to model long-range dependencies. By designing a convolution stem and a local enhancement module, both low-level and high-level local features can be compensated. To take advantage of these rich features, a skip connection strategy and an efficient upsampling module is built to restore detailed information. In addition, a defect rectification module is further developed to reinforce the network for hard sample recognition. The quantitative comparison demonstrates that the proposed LETNet outperformed four advanced deep learning-based models with respect to both efficiency and effectiveness. Specifically, the average precision, recall, ODS, IoU, and frame per second (FPS) of the LETNet on three testing datasets are approximately 93.04%, 92.85%, 92.94%, 94.07%, and 30.80FPS, respectively. We also built a comprehensive pavement crack dataset containing 156 high-resolution manually annotated CCD images and made it publicly available on Zenodo.

Accurately and precisely delineating road-markings from very high spatial resolution unmanned aerial vehicle (UAV) images face many challenges, such as complex scenarios, diverse road marking sizes and shapes, and absent and occluded road markings. To address these issues, we formulate an attentive capsule feature pyramid network (ACapsFPN) by integrating capsule representations with attention mechanisms into the feature pyramid network (FPN), aiming at improving road marking extraction accuracy. Different from the current convolutional neural network (CNN) models based on scalar neuron representations, capsule networks characterize entity features by leveraging vectorial capsule neurons, whose lengths and instantiation parameters contribute to the identification of features and their variants. By constructing a capsule FPN, the ACapsFPN is capable of extracting and integrating multi-level and multi-scale capsule features to provide high-quality and semantically-strong feature abstractions. By formulating a multi-scale context feature descriptor and the ternary feature attention modules, the ACapsFPN can emphasize informative features to generate a class-specific feature representation. Quantitative and qualitative evaluations show the ACapsFPN provides a valuable means for extracting road markings in UAV images under different kinds of complex conditions. In addition, comparative analyses with existing alternatives also demonstrate the superiority and robustness of the ACapsFPN in UAV road marking extraction.

Fruit ripening is a highly complicated process, which is modulated by phytohormones, signal regulators and environmental factors playing in an intricate network that regulates ripening-related genes expression. Although transcriptomics is an effective tool to predict protein levels, protein abundances are also extensively affected by post-transcriptional and post-translational regulations. Here, we used RNA sequencing (RNA-seq) and tandem mass tag (TMT)-based quantitative proteomics to study the comprehensive mRNA and protein expression changes during fruit development and ripening in watermelon, a non-climacteric fruit. A total of 6,226 proteins were quantified, and the large number of quantitative proteins is comparable to proteomic studies in model organisms such as Oryza sativa L. and Arabidopsis. Base on our proteome methodology, integrative analysis of the transcriptome and proteome showed that the mRNA and protein levels were poorly correlated, and the correlation coefficients decreased during fruit ripening. Proteomic results showed that proteins involved in alternative splicing and the ubiquitin proteasome pathway were dynamically expressed during ripening. Furthermore, the spliceosome and proteasome were significantly enriched by Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis, suggesting that post-transcriptional and post-translational mechanisms might play important roles in regulation of fruit ripening-associated genes expression, which might account for the poor correlation between mRNAs and proteins during fruit ripening. Our comprehensive transcriptomic and proteomic data offer a valuable resource for watermelon research, and provide new insights into the molecular mechanisms underlying the complex regulatory networks of fruit ripening.

Vitamin E, consisting of tocopherols and tocotrienols, serves as a lipid-soluble antioxidant in sweet corn kernels, providing nutrients to both plants and humans. Though the key genes involved in the vitamin E biosynthesis pathway have been identified in plants, the genetic architecture of vitamin E content in sweet corn kernels remains largely unclear. In the present study, an association panel of 204 inbred lines of sweet corn was constructed. Seven compounds of vitamin E were quantified in sweet corn kernels at 28 days after pollination. A total of 119 loci for vitamin E were identified using a genome-wide association study based on genotyping by sequencing, and a genetic network of vitamin E was constructed. Candidate genes identified were involved mainly in RNA regulation and protein metabolism. The known gene ZmVTE4, encoding γ-tocopherol methyltransferase, was significantly associated with four traits (α-tocopherol, α-tocotrienol, the α/γ-tocopherol ratio, and the α/γ-tocotrienol ratio). The effects of two causative markers on ZmVTE4 were validated by haplotype analysis. Finally, two elite cultivars (Yuetian 9 and Yuetian 22) with a 4.5-fold increase in the sum of α- and γ-tocopherols were developed by marker-assisted selection, demonstrating the successful biofortification of sweet corn. Three genes (DAHPS, ADT2, and cmu2) involved in chorismate and tyrosine synthesis were significantly associated with the α/γ-tocotrienol ratio. These results shed light on the genetic architecture of vitamin E and may accelerate the nutritional improvement of sweet corn. Keywords: Sweet corn, GBS, Genome-wide association study, Vitamin E, Marker-assisted selection

Geometric feature acts as an important role in point cloud shape classification tasks. Previous methods have proved that the geometric information of point clouds effectively improves the classification accuracy. Mo-Net firstly introduced geometric moments into point cloud shape classification, which, to fit the form of second order geometric moments, extends the number of input channels from three to nine. Unfortunately, similar to PointNet, Mo-Net cannot capture the local structures. To address this issue, we propose a graph geometric moments convolution neural network (GGM-Net), which learns local geometric features from geometric moments representation of a local point set. The core module of the GGM-Net is to learn features from geometric moments (termed as GGM convolution). Specifically, the GGM convolution learns point features and local features from the first and second order geometric moments of points and its local neighbors, respectively, and then combines these features by using an addition operation. In this way, a geometrical local representation about points is obtained, which leads to much surface geometry awareness and robustness. Equipped with the GGM convolution, GGM-Net, a simple end-to-end architecture, is developed to achieve a competitive accuracy on the benchmark dataset ModelNet40 and perform more efficiently in terms of memory and computational complexity.

Objective: To determine the feasibility of decellularized small intestinal submucosa (SIS) matrix in repairing ureteral strictures. Methods: Two patients with ureteral stenoses underwent ureteral reconstruction with SIS matrix at the Zhejiang Provincial Corps Hospital of Chinese People's Armed Forces between June 2014 and June 2016. The ureteral stenoses were repaired with a semi-tubular SIS matrix and the postoperative recoveries were observed. Results: Both operations were successfully completed. The average operative time was 90 min and the average length of hospital stay was 15 days. No fevers, incision infections, intestinal obstruction, graft rejection, or other serious complications were noted. After 2 months, ureteroscopic examinations showed that the surfaces of the original patches were covered by mucosa and there were no apparent stenoses in the lumens. The ureteral stents were replaced every 2 months postoperatively and removed 12 months postoperatively. No infections or urinary leakage occurred after removal of the stents. Intravenous urography was performed 6 and 12 months postoperatively. The results showed that the ureters were not obstructed and there was no apparent stenosis at the anastomosis sites. The average follow-up time was >12 months. Long-term follow-up is still ongoing, and computed tomography examinations of the urinary tract have been conducted in the outpatient department of our hospital 1, 3, and 6 months after removal of the double-J stents, suggesting the absence of hydronephrosis. The serum creatinine levels remained stable during the follow-up. Conclusion: SIS matrix reconstruction is a feasible method to repair ureters stenosis. Keywords: Ureteral stenosis, Decellularized matrix, Ureteroplasty, Ureteral reconstruction, Ureteral obstruction

As the optical remote sensing techniques keep developing with a rapid pace, remote sensing images are positively considered in many fields. Accordingly, a great number of algorithms have been exploited for remote sensing image interpretation purposes. Thereinto, object recognition acts as an important ingredient to many applications. However, to achieve highly accurate object recognition is still challengeable caused by the orientation and size diversities, spatial distribution and density variations, shape and aspect ratio irregularities, occlusion and shadow impacts, as well as complex texture and surrounding environment changes. In this paper, a sparse anchoring guided high-resolution capsule network (SAHR-CapsNet) is proposed for geospatial object detection based on remote sensing images. First, formulated with the multibranch high-resolution capsule network architecture assisted by multiscale feature propagation and fusion, the SAHR-CapsNet can extract semantically strong and spatially accurate feature semantics at multiple scales. Second, integrated with the efficient capsule-based self-attention module, the SAHR-CapsNet functions promisingly to attend to target-specific spatial features and informative channel features. Finally, adopted with the capsule-based sparse anchoring network, the SAHR-CapsNet performs efficiently in generating a fixed number of lightweight, high-quality sparse region proposals. Quantitative assessments and comparative analyses on two challenging remote sensing image datasets demonstrate the applicability and effectiveness of the developed SAHR-CapsNet for geospatial object detection applications.

This paper presents a feature reasoning-based graph convolution network (FR-GCNet) to improve the classification accuracy of airborne multispectral LiDAR (MS-LiDAR) point clouds. In the FR-GCNet, we directly assign semantic labels to all points by exploring representative features both globally and locally. Based on the graph convolution network (GCN), a global reasoning unit is embedded to obtain the global contextual feature by revealing spatial relationships of points, while a local reasoning unit is integrated to dynamically learn edge features with attention weights in each local graph. Extensive experiments on the Titan MS-LiDAR data showed that the proposed FR-GCNet achieved a promising classification performance with an overall accuracy of 93.55%, an average F1-score of 78.61%, and a mean Intersection over Union (IoU) of 66.78%. Comparative experimental results demonstrated the superiority of the FR-GCNet against other state-of-the-art approaches.

Air quality has a significant influence on people’s health. Severe air pollution can cause respiratory diseases, while good air quality is beneficial to physical and mental health. Therefore, the prediction of air quality is very important. Since the concentration data of air pollutants are time series, their time characteristics should be considered in their prediction. However, the traditional neural network for time series prediction is limited by its own structure, which makes it very easy for it to fall into a local optimum during the training process. The empirical mode decomposition fuzzy forecast model for air quality, which is based on the extreme learning machine, is proposed in this paper. Empirical mode decomposition can analyze the changing trend of air quality well and obtain the changing trend of air quality under different time scales. According to the changing trend under different time scales, the extreme learning machine is used for fast training, and the corresponding prediction value is obtained. The adaptive fuzzy inference system is used for fitting to obtain the final air quality prediction result. The experimental results show that our model improves the accuracy of both short-term and long-term prediction by about 30% compared to other models, which indicates the remarkable efficacy of our approach. The research of this paper can provide the government with accurate future air quality information, which can take corresponding control measures in a targeted manner.

Urban areas are the center of human settlement with intensive anthropic activities and dense built-up infrastructures, suffering significant evolution in population shift, land-use change, industrial production, and so on [...]

Background: High-quality colonoscopy is essential to prevent the occurrence of colorectal cancers. The data of colonoscopy are mainly stored in the form of images. Therefore, artificial intelligence-assisted colonoscopy based on medical images is not only a research hotspot, but also one of the effective auxiliary means to improve the detection rate of adenomas. This research has become the focus of medical institutions and scientific research departments and has important clinical and scientific research value. Methods: In this paper, we propose a YOLOv5 model based on a self-attention mechanism for polyp target detection. This method uses the idea of regression, using the entire image as the input of the network and directly returning the target frame of this position in multiple positions of the image. In the feature extraction process, an attention mechanism is added to enhance the contribution of information-rich feature channels and weaken the interference of useless channels; Results: The experimental results show that the method can accurately identify polyp images, especially for the small polyps and the polyps with inconspicuous contrasts, and the detection speed is greatly improved compared with the comparison algorithm. Conclusions: This study will be of great help in reducing the missed diagnosis of clinicians during endoscopy and treatment, and it is also of great significance to the development of clinicians’ clinical work.

Stress induced by low temperature, which represents a widespread environmental factor, strongly affects maize growth and yield. However, the physiological characteristics and molecular regulatory mechanisms of maize seedlings in response to cold remain poorly understood. In this study, using RNA-seq, we investigated the transcriptome profiles of two sweet corn inbred lines, “Richao” (RC) and C5, under cold stress. A total of 357 and 455 differentially expressed genes (DEGs) were identified in the RC and C5 lines, respectively, 94 DEGs were detected as common DEGs related to cold response in both genotypes, and a total of 589 DEGs were detected as cold tolerance-associated genes. By combining protein function clustering analysis and significantly enriched Gene Ontology (GO) terms analysis, we suggest that transcription factors may play a dominating role in the cold stress response and tolerance of sweet corn. Furthermore, 74 differentially expressed transcription factors were identified, of those many genes involved in the metabolism and regulation of hormones. These results expand our understanding of the complex mechanisms involved in chilling tolerance in maize, and provide a set of candidate genes for further genetic analyses.

A multispectral light detection and ranging (LiDAR) system, which simultaneously collects spatial geometric data and multi-wavelength intensity information, opens the door to three-dimensional (3-D) point cloud classification and object recognition. Because of the irregular distribution property of point clouds and the massive data volume, point cloud classification directly from multispectral LiDAR data is still challengeable and questionable. In this paper, a point-wise multispectral LiDAR point cloud classification architecture termed as SE-PointNet++ is proposed via integrating a Squeeze-and-Excitation (SE) block with an improved PointNet++ semantic segmentation network. PointNet++ extracts local features from unevenly sampled points and represents local geometrical relationships among the points through multi-scale grouping. The SE block is embedded into PointNet++ to strengthen important channels to increase feature saliency for better point cloud classification. Our SE-PointNet++ architecture has been evaluated on the Titan multispectral LiDAR test datasets and achieved an overall accuracy, a mean Intersection over Union (mIoU), an F1-score, and a Kappa coefficient of 91.16%, 60.15%, 73.14%, and 0.86, respectively. Comparative studies with five established deep learning models confirmed that our proposed SE-PointNet++ achieves promising performance in multispectral LiDAR point cloud classification tasks.

The up-to-date and information-accurate road database plays a significant role in many applications. Recently, with the improvement in image resolutions and quality, remote sensing images have provided an important data source for road extraction tasks. However, due to the topology variations, spectral diversities, and complex scenarios, it is still challenging to realize fully automated and highly accurate road extractions from remote sensing images. This paper proposes a novel dual-attention capsule U-Net (DA-CapsUNet) for road region extraction by combining the advantageous properties of capsule representations and the powerful features of attention mechanisms. By constructing a capsule U-Net architecture, the DA-CapsUNet can extract and fuse multiscale capsule features to recover a high-resolution and semantically strong feature representation. By designing the multiscale context-augmentation and two types of feature attention modules, the DA-CapsUNet can exploit multiscale contextual properties at a high-resolution perspective and generate an informative and class-specific feature encoding. Quantitative evaluations on a large dataset showed that the DA-CapsUNet provides a competitive road extraction performance with a precision of 0.9523, a recall of 0.9486, and an F-score of 0.9504, respectively. Comparative studies with eight recently developed deep learning methods also confirmed the applicability and superiority or compatibility of the DA-CapsUNet in road extraction tasks.

Building extraction has attracted much attentions for decades as a prerequisite for many applications and is still a challenging topic in the field of photogrammetry and remote sensing. Due to the lack of spectral information, massive data processing, and approach universality, building extraction from point clouds is still a thorny and challenging problem. In this paper, a novel deep-learning-based framework is proposed for building extraction from point cloud data. Specifically, first, a sample generation method is proposed to split the raw preprocessed multi-spectral light detection and ranging (LiDAR) data into numerous samples, which are directly fed into convolutional neural networks and completely cover the original inputs. Then, a graph geometric moments (GGM) convolution is proposed to encode the local geometric structure of point sets. In addition, a hierarchical architecture equipped with GGM convolution, called GGM convolutional neural networks, is proposed to train and recognize building points. Finally, the test scenes with varying sizes can be fed into the framework and obtain a point-wise extraction result. We evaluate the proposed framework and methods on the airborne multi-spectral LiDAR point clouds collected by an Optech Titan system. Compared with previous state-of-the-art networks, which are designed for point cloud segmentation, our method achieves the best performance with a correctness of 95.1%, a completeness of 93.7%, an F-measure of 94.4%, and an intersection over union (IoU) of 89.5% on two test areas. The experimental results confirm the effectiveness and efficiency of the proposed framework and methods.

Unmanned aerial vehicles using light detection and ranging (UAV LiDAR) with high spatial resolution have shown great potential in forest applications because they can capture vertical structures of forests. Individual tree segmentation is the foundation of many forest research works and applications. The tradition fixed bandwidth mean shift has been applied to individual tree segmentation and proved to be robust in tree segmentation. However, the fixed bandwidth-based segmentation methods are not suitable for various crown sizes, resulting in omission or commission errors. Therefore, to increase tree-segmentation accuracy, we propose a self-adaptive bandwidth estimation method to estimate the optimal kernel bandwidth automatically without any prior knowledge of crown size. First, from the global maximum point, we divide the three-dimensional (3D) space into a set of angular sectors, for each of which a canopy surface is simulated and the potential tree crown boundaries are identified to estimate average crown width as the kernel bandwidth. Afterwards, we use a mean shift with the automatically estimated kernel bandwidth to extract individual tree points. The method is iteratively implemented within a given area until all trees are segmented. The proposed method was tested on the 7 plots acquired by a Velodyne 16E LiDAR system, including 3 simple plots and 4 complex plots, and 95% and 80% of trees were correctly segmented, respectively. Comparative experiments show that our method contributes to the improvement of both segmentation accuracy and computational efficiency.

Objective: Glioblastoma multiforme (GBM), an aggressive primary brain tumor, is radioresistant and recurs despite aggressive surgery, chemotherapy, and radiotherapy. Curcumin as a potential radiosensitizer has received extensive attention in cancer treatment. To explore an effectiveness of this radiosensitizer for GBM treatment, we evaluated the radiosensitizing effect of curcumin and investigated its potential molecular mechanisms in the human glioma cell line U87. Methods: The cytotoxic effects of curcumin on U87 cells were evaluated using the Cell Counting Kit-8 assay, and the radiosensitivity of U87 cells treated with curcumin was accessed by colony information assay. The effects of curcumin on cell proliferation and cell cycle regulation were determined using the 5-ethynyl-2-deoxyuridine incorporation assay and flow cytometry, respectively. Western blotting was applied to determine the effects of curcumin on protein expression of dual-specificity phosphatase-2 (DUSP-2), extracellular signal-regulated kinase (ERK), and c-Jun N-terminal kinase (JNK) as well as phosphorylated ERK and JNK. Results: Curcumin significantly inhibited the proliferation of U87 cells in a dose-and time-dependent manner. Curcumin treatment at the concentrations of 5 µM and 10 M could significantly reduce the clonogenic activity and enhance the radiosensitivity of U87 cells with sensitive enhancement ratios (SERs) of 1.71 and 4.65, respectively. Curcumin resulted in G2/M cell cycle arrest in U87 cells, which were radiosensitive. Pre-treatment of U87-MG cells with 5 µM curcumin enhanced radiation-induced cell proliferation inhibition and apoptosis. Furthermore, we observed that curcumin increased DUSP-2 protein expression and decreased the phosphorylation of ERK and JNK. Conclusion: Our results suggest that low-dose curcumin may enhance the radiosensitivity of human glioma U87 cells in vitro by inducing G2/M cell cycle arrest through up-regulation of DUSP-2 expression and inhibition of ERK and JNK phosphorylation.

Vehicle detection from remote sensing images plays a significant role in transportation related applications. However, the scale variations, orientation variations, illumination variations, and partial occlusions of vehicles, as well as the image qualities, bring great challenges for accurate vehicle detection. In this paper, we present an affine-function transformation-based object matching framework for vehicle detection from unmanned aerial vehicle (UAV) images. First, meaningful and non-redundant patches are generated through a superpixel segmentation strategy. Then, the affine-function transformation-based object matching framework is applied to a vehicle template and each of the patches for vehicle existence estimation. Finally, vehicles are detected and located after matching cost thresholding, vehicle location estimation, and multiple response elimination. Quantitative evaluations on two UAV image datasets show that the proposed method achieves an average completeness, correctness, quality, and F1-measure of 0.909, 0.969, 0.883, and 0.938, respectively. Comparative studies also demonstrate that the proposed method achieves compatible performance with the Faster R-CNN and outperforms the other eight existing methods in accurately detecting vehicles of various conditions.

Forests play a key role in terrestrial ecosystems, and the variables extracted from single trees can be used in various fields and applications for evaluating forest production and assessing forest ecosystem services. In this study, we developed an automated hierarchical single-tree segmentation approach based on the high density three-dimensional (3D) Unmanned Aerial Vehicle (UAV) point clouds. First, this approach obtains normalized non-ground UAV points in data preprocessing; then, a voxel-based mean shift algorithm is used to roughly classify the non-ground UAV points into well-detected and under-segmentation clusters. Moreover, potential tree apices for each under-segmentation cluster are obtained with regard to profile shape curves and finally input to the normalized cut segmentation (NCut) algorithm to segment iteratively the under-segmentation cluster into single trees. We evaluated the proposed method using datasets acquired by a Velodyne 16E LiDAR system mounted on a multi-rotor UAV. The results showed that the proposed method achieves the average correctness, completeness, and overall accuracy of 0.90, 0.88, and 0.89, respectively, in delineating single trees. Comparative analysis demonstrated that our method provided a promising solution to reliable and robust segmentation of single trees from UAV LiDAR data with high point cloud density.

Sweet corn kernels were used in this research to study the dynamics of vitamin E, by evaluatingthe expression levels of genes involved in vitamin E synthesis, the accumulation of vitamin E, and the antioxidant activity during the different stage of kernel development. Results showed that expression levels of ZmHPT and ZmTC genes increased, whereas ZmTMT gene dramatically decreased during kernel development. The contents of all the types of vitamin E in sweet corn had a significant upward increase during kernel development, and reached the highest level at 30 days after pollination (DAP). Amongst the eight isomers of vitamin E, the content of γ-tocotrienol was the highest, and increased by 14.9 folds, followed by α-tocopherolwith an increase of 22 folds, and thecontents of isomers γ-tocopherol, α-tocotrienol, δ-tocopherol,δ-tocotrienol, and β-tocopherol were also followed during kernel development. The antioxidant activity of sweet corn during kernel development was increased, and was up to 101.8 ± 22.3 μmol of α-tocopherol equivlent/100 g in fresh weight (FW) at 30 DAP. There was a positive correlation between vitamin E contents and antioxidant activity in sweet corn during the kernel development, and a negative correlation between the expressions of ZmTMT gene and vitamin E contents. These results revealed the relations amongst the content of vitamin E isomers and the gene expression, vitamin E accumulation, and antioxidant activity. The study can provide a harvesting strategy for vitamin E bio-fortification in sweet corn.

Over the past decade, land-based laser scanning technologies have been actively studied and implemented, in response to the need for detailed three-dimensional (3D) data about our rural and urban environment for topographic mapping, cadastral mapping, and other street-level features, which are difficult and time consuming to measure by other instruments. For rural areas in China, the complex terrain and poor planning limit the applicability of this advanced technology. To improve the efficiency of rural surveys, we present two SSW (Shoushi and SiWei) laser scanning systems for rapid topographic mapping: stop-and-go and electro-tricycle laser scanning systems. The objective of this paper is to evaluate whether laser scanning data collected by the developed SSW systems meet the accuracy requirements for rural homestead mapping. We investigated the performance of the two laser scanning systems on Ma’anshan Village, a small, typical village in Hubei Province, China. To obtain full coverage of the village, we fused the stop-and-go and electro-tricycle laser scanning data. The performance of the developed SSW systems is described by the results of building contours extracted from the fused data against the established building vector map.