Unmanned Aerial Vehicles(UAVs)are increasingly employed in traffic surveillance,urban planning,and infrastructure monitoring due to their cost-effectiveness,flexibility,and high-resolution imaging.However,vehicle dete...Unmanned Aerial Vehicles(UAVs)are increasingly employed in traffic surveillance,urban planning,and infrastructure monitoring due to their cost-effectiveness,flexibility,and high-resolution imaging.However,vehicle detection and classification in aerial imagery remain challenging due to scale variations from fluctuating UAV altitudes,frequent occlusions in dense traffic,and environmental noise,such as shadows and lighting inconsistencies.Traditional methods,including sliding-window searches and shallow learning techniques,struggle with computational inefficiency and robustness under dynamic conditions.To address these limitations,this study proposes a six-stage hierarchical framework integrating radiometric calibration,deep learning,and classical feature engineering.The workflow begins with radiometric calibration to normalize pixel intensities and mitigate sensor noise,followed by Conditional Random Field(CRF)segmentation to isolate vehicles.YOLOv9,equipped with a bi-directional feature pyramid network(BiFPN),ensures precise multi-scale object detection.Hybrid feature extraction employs Maximally Stable Extremal Regions(MSER)for stable contour detection,Binary Robust Independent Elementary Features(BRIEF)for texture encoding,and Affine-SIFT(ASIFT)for viewpoint invariance.Quadratic Discriminant Analysis(QDA)enhances feature discrimination,while a Probabilistic Neural Network(PNN)performs Bayesian probability-based classification.Tested on the Roundabout Aerial Imagery(15,474 images,985K instances)and AU-AIR(32,823 instances,7 classes)datasets,the model achieves state-of-the-art accuracy of 95.54%and 94.14%,respectively.Its superior performance in detecting small-scale vehicles and resolving occlusions highlights its potential for intelligent traffic systems.Future work will extend testing to nighttime and adverse weather conditions while optimizing real-time UAV inference.展开更多
Waxy maize is a specialty maize that produces mainly amylopectin starch with special food or industrial values. The objective of this study was to overcome the limitations of wx mutant allele acquisition and breeding ...Waxy maize is a specialty maize that produces mainly amylopectin starch with special food or industrial values. The objective of this study was to overcome the limitations of wx mutant allele acquisition and breeding efficiency by conversion of parental lines from normal to waxy maize. The intended mutation activity was achieved by in vivo CRISPR/Cas9 machinery involving desired-target mutation of the Wx locus in the ZC01 background,abbreviated as ZC01-DTM^(wx). Triple selection was applied to segregants to obtain high genome background recovery with transgene-free wx mutations. The targeted mutation was identified, yielding six types of mutations among progeny crossed with ZC01-DTM^(wx).The amylopectin contents of the endosperm starch in mutant lines and hybrids averaged94.9%, while those of the wild-type controls were significantly(P < 0.01) lower, with an average of 76.9%. Double selection in transgene-free lines was applied using the Bar strip test and Cas9 PCR screening. The genome background recovery ratios of the lines were determined using genome-wide SNP data. That of lines used as male parents was as high as98.19% and that of lines used as female parents was as high as 86.78%. Conversion hybrids and both parental lines showed agronomic performance similar to that of their wild-type counterparts. This study provides a practical example of the efficient extension of CRISPR/Cas9 targeted mutation to industrial hybrids for transformation of a recalcitrant species.展开更多
基金supported through Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R508)Princess Nourah bint Abdulrahman University,Riyadh,Saudi ArabiaThe research team thanks the Deanship of Graduate Studies and Scientific Research at Najran University for supporting the research project through the Nama’a program,with the project code NU/GP/SERC/13/18-5.
文摘Unmanned Aerial Vehicles(UAVs)are increasingly employed in traffic surveillance,urban planning,and infrastructure monitoring due to their cost-effectiveness,flexibility,and high-resolution imaging.However,vehicle detection and classification in aerial imagery remain challenging due to scale variations from fluctuating UAV altitudes,frequent occlusions in dense traffic,and environmental noise,such as shadows and lighting inconsistencies.Traditional methods,including sliding-window searches and shallow learning techniques,struggle with computational inefficiency and robustness under dynamic conditions.To address these limitations,this study proposes a six-stage hierarchical framework integrating radiometric calibration,deep learning,and classical feature engineering.The workflow begins with radiometric calibration to normalize pixel intensities and mitigate sensor noise,followed by Conditional Random Field(CRF)segmentation to isolate vehicles.YOLOv9,equipped with a bi-directional feature pyramid network(BiFPN),ensures precise multi-scale object detection.Hybrid feature extraction employs Maximally Stable Extremal Regions(MSER)for stable contour detection,Binary Robust Independent Elementary Features(BRIEF)for texture encoding,and Affine-SIFT(ASIFT)for viewpoint invariance.Quadratic Discriminant Analysis(QDA)enhances feature discrimination,while a Probabilistic Neural Network(PNN)performs Bayesian probability-based classification.Tested on the Roundabout Aerial Imagery(15,474 images,985K instances)and AU-AIR(32,823 instances,7 classes)datasets,the model achieves state-of-the-art accuracy of 95.54%and 94.14%,respectively.Its superior performance in detecting small-scale vehicles and resolving occlusions highlights its potential for intelligent traffic systems.Future work will extend testing to nighttime and adverse weather conditions while optimizing real-time UAV inference.
基金supported the National Transgenic Science and Technology Program(2019ZX08010-003)the National Natural Science Foundation of China(31771808)+3 种基金the National Key Research and Development Program of China(2016YFD0101803)the Key Area Research and Development Program of Guangdong Province(2018B020202008)Beijing Municipal Science and Technology Commission(D171100007717001)National Engineering Laboratory for Crop Molecular Breeding。
文摘Waxy maize is a specialty maize that produces mainly amylopectin starch with special food or industrial values. The objective of this study was to overcome the limitations of wx mutant allele acquisition and breeding efficiency by conversion of parental lines from normal to waxy maize. The intended mutation activity was achieved by in vivo CRISPR/Cas9 machinery involving desired-target mutation of the Wx locus in the ZC01 background,abbreviated as ZC01-DTM^(wx). Triple selection was applied to segregants to obtain high genome background recovery with transgene-free wx mutations. The targeted mutation was identified, yielding six types of mutations among progeny crossed with ZC01-DTM^(wx).The amylopectin contents of the endosperm starch in mutant lines and hybrids averaged94.9%, while those of the wild-type controls were significantly(P < 0.01) lower, with an average of 76.9%. Double selection in transgene-free lines was applied using the Bar strip test and Cas9 PCR screening. The genome background recovery ratios of the lines were determined using genome-wide SNP data. That of lines used as male parents was as high as98.19% and that of lines used as female parents was as high as 86.78%. Conversion hybrids and both parental lines showed agronomic performance similar to that of their wild-type counterparts. This study provides a practical example of the efficient extension of CRISPR/Cas9 targeted mutation to industrial hybrids for transformation of a recalcitrant species.
