As urban landscapes evolve and vehicular volumes soar,traditional traffic monitoring systems struggle to scale,often failing under the complexities of dense,dynamic,and occluded environments.This paper introduces a no...As urban landscapes evolve and vehicular volumes soar,traditional traffic monitoring systems struggle to scale,often failing under the complexities of dense,dynamic,and occluded environments.This paper introduces a novel,unified deep learning framework for vehicle detection,tracking,counting,and classification in aerial imagery designed explicitly for modern smart city infrastructure demands.Our approach begins with adaptive histogram equalization to optimize aerial image clarity,followed by a cutting-edge scene parsing technique using Mask2Former,enabling robust segmentation even in visually congested settings.Vehicle detection leverages the latest YOLOv11 architecture,delivering superior accuracy in aerial contexts by addressing occlusion,scale variance,and fine-grained object differentiation.We incorporate the highly efficient ByteTrack algorithm for tracking,enabling seamless identity preservation across frames.Vehicle counting is achieved through an unsupervised DBSCAN-based method,ensuring adaptability to varying traffic densities.We further introduce a hybrid feature extraction module combining Convolutional Neural Networks(CNNs)with Zernike Moments,capturing both deep semantic and geometric signatures of vehicles.The final classification is powered by NASNet,a neural architecture search-optimized model,ensuring high accuracy across diverse vehicle types and orientations.Extensive evaluations of the VAID benchmark dataset demonstrate the system’s outstanding performance,achieving 96%detection,94%tracking,and 96.4%classification accuracy.On the UAVDT dataset,the system attains 95%detection,93%tracking,and 95%classification accuracy,confirming its robustness across diverse aerial traffic scenarios.These results establish new benchmarks in aerial traffic analysis and validate the framework’s scalability,making it a powerful and adaptable solution for next-generation intelligent transportation systems and urban surveillance.展开更多
Mating behavior is crucial for most insects,as it is closely tied to reproduction and population growth and relies heavily on chemical communication via cuticular hydrocarbons(CHCs)between individuals.However,little i...Mating behavior is crucial for most insects,as it is closely tied to reproduction and population growth and relies heavily on chemical communication via cuticular hydrocarbons(CHCs)between individuals.However,little is known about the mating behavior of Eupeodes corollae,a natural enemy insect,and how CHCs help it communicate.In this study,we performed a behavioral assay of the mating process of hoverfly E.corollae.The cuticular hydrocarbons of both male and female hoverflies were identified by gas chromatography-mass spectrometry(GC-MS).The electrophysiological activities of these compounds on the antennae of hoverflies were further determined by gas chromatography coupled with electroantennogram detection(GC-EAD)and electroantennogram(EAG).The effects of these compounds on the behavioral selection and mating of hoverflies were also determined.The results showed that the mating process of hoverflies was divided into five stages:orientation,approaching,wing fanning,mounting,and copulation.Fifth-aged individuals exhibited the highest copulation and mating success rates,the shortest male latency,and stable mating duration.The results of the determination of cuticular compounds showed that the CHCs of male and female hoverflies exhibited sexually monomorphic chemical profiles,and two compounds of(Z)-9-tricosene and n-tricosane could cause significant electrophysiological responses in both male and female hoverflies.Behavioral bioassay results showed that(Z)-9-tricosene can significantly induce the attraction response of male and female E.corollae and can effectively regulate the courtship behavior of male E.corollae.This finding provides a new perspective for a deeper understanding of hoverflies'chemical communication mechanism and a valuable scientific basis and potential application prospect for developing a pheromone-based behavior strategy to control pests.展开更多
Reverse flotation desilication is an indispensable step for obtaining high-grade fluorapatite. In this work, dodecyltrimethylammoni- um bromide (DTAB) is recommended as an efficient collector for the reverse flotation...Reverse flotation desilication is an indispensable step for obtaining high-grade fluorapatite. In this work, dodecyltrimethylammoni- um bromide (DTAB) is recommended as an efficient collector for the reverse flotation separation of quartz from fluorapatite. Its collectivity for quartz and selectivity for fluorapatite were also compared with figures corresponding to the conventional collector dodecylamine hydrochlor- ide (DAC) via microflotation experiments. The adsorption behaviors of DTAB and DAC on minerals were systematically investigated with surface chemical analyses, such as contact angle determination, zeta potential detection, and adsorption density measurement. The results re- vealed that compared to DAC, DTAB displayed a similar and strong collectivity for quartz, and it showed a better selectivity (or worse col- lectivity) for fluorapatite, resulting in a high-efficiency separation of the two minerals. The surface chemical analysis results showed that the adsorption ability of DTAB on the quartz surface was as strong as that of DAC, whereas the adsorption amount of DTAB on the fluorapatite surface was much lower than that of DAC, which is associated with the flotation performance. During the floatation separation of the actual ore, 8wt% fluorapatite with a higher grade can be obtained using DTAB in contrast to DAC. Therefore, DTAB is a promising collector for the high-efficiency purification and sustainable utilization of valuable fluorapatite recourses.展开更多
基金funded by the Open Access Initiative of the University of Bremen and the DFG via SuUB BremenThe authors extend their appreciation to the Deanship of Research and Graduate Studies at King Khalid University for funding this work through Large Group Project under grant number(RGP2/367/46)+1 种基金This research is supported and funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R410)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘As urban landscapes evolve and vehicular volumes soar,traditional traffic monitoring systems struggle to scale,often failing under the complexities of dense,dynamic,and occluded environments.This paper introduces a novel,unified deep learning framework for vehicle detection,tracking,counting,and classification in aerial imagery designed explicitly for modern smart city infrastructure demands.Our approach begins with adaptive histogram equalization to optimize aerial image clarity,followed by a cutting-edge scene parsing technique using Mask2Former,enabling robust segmentation even in visually congested settings.Vehicle detection leverages the latest YOLOv11 architecture,delivering superior accuracy in aerial contexts by addressing occlusion,scale variance,and fine-grained object differentiation.We incorporate the highly efficient ByteTrack algorithm for tracking,enabling seamless identity preservation across frames.Vehicle counting is achieved through an unsupervised DBSCAN-based method,ensuring adaptability to varying traffic densities.We further introduce a hybrid feature extraction module combining Convolutional Neural Networks(CNNs)with Zernike Moments,capturing both deep semantic and geometric signatures of vehicles.The final classification is powered by NASNet,a neural architecture search-optimized model,ensuring high accuracy across diverse vehicle types and orientations.Extensive evaluations of the VAID benchmark dataset demonstrate the system’s outstanding performance,achieving 96%detection,94%tracking,and 96.4%classification accuracy.On the UAVDT dataset,the system attains 95%detection,93%tracking,and 95%classification accuracy,confirming its robustness across diverse aerial traffic scenarios.These results establish new benchmarks in aerial traffic analysis and validate the framework’s scalability,making it a powerful and adaptable solution for next-generation intelligent transportation systems and urban surveillance.
基金funded by the National Natural Science Foundation of China(32272621)the Key Project of Inter-Government International Science&Technology Innovation Cooperation,China(2019YFE0105800)+1 种基金the Major Special Projects for Green Pest Control,China(110202201017(LS-01))the Agricultural Science and Technology Innovation Program of Chinese Academy of Agricultural Sciences。
文摘Mating behavior is crucial for most insects,as it is closely tied to reproduction and population growth and relies heavily on chemical communication via cuticular hydrocarbons(CHCs)between individuals.However,little is known about the mating behavior of Eupeodes corollae,a natural enemy insect,and how CHCs help it communicate.In this study,we performed a behavioral assay of the mating process of hoverfly E.corollae.The cuticular hydrocarbons of both male and female hoverflies were identified by gas chromatography-mass spectrometry(GC-MS).The electrophysiological activities of these compounds on the antennae of hoverflies were further determined by gas chromatography coupled with electroantennogram detection(GC-EAD)and electroantennogram(EAG).The effects of these compounds on the behavioral selection and mating of hoverflies were also determined.The results showed that the mating process of hoverflies was divided into five stages:orientation,approaching,wing fanning,mounting,and copulation.Fifth-aged individuals exhibited the highest copulation and mating success rates,the shortest male latency,and stable mating duration.The results of the determination of cuticular compounds showed that the CHCs of male and female hoverflies exhibited sexually monomorphic chemical profiles,and two compounds of(Z)-9-tricosene and n-tricosane could cause significant electrophysiological responses in both male and female hoverflies.Behavioral bioassay results showed that(Z)-9-tricosene can significantly induce the attraction response of male and female E.corollae and can effectively regulate the courtship behavior of male E.corollae.This finding provides a new perspective for a deeper understanding of hoverflies'chemical communication mechanism and a valuable scientific basis and potential application prospect for developing a pheromone-based behavior strategy to control pests.
基金the National Nat-ural Science Foundation of China(No.51974093).
文摘Reverse flotation desilication is an indispensable step for obtaining high-grade fluorapatite. In this work, dodecyltrimethylammoni- um bromide (DTAB) is recommended as an efficient collector for the reverse flotation separation of quartz from fluorapatite. Its collectivity for quartz and selectivity for fluorapatite were also compared with figures corresponding to the conventional collector dodecylamine hydrochlor- ide (DAC) via microflotation experiments. The adsorption behaviors of DTAB and DAC on minerals were systematically investigated with surface chemical analyses, such as contact angle determination, zeta potential detection, and adsorption density measurement. The results re- vealed that compared to DAC, DTAB displayed a similar and strong collectivity for quartz, and it showed a better selectivity (or worse col- lectivity) for fluorapatite, resulting in a high-efficiency separation of the two minerals. The surface chemical analysis results showed that the adsorption ability of DTAB on the quartz surface was as strong as that of DAC, whereas the adsorption amount of DTAB on the fluorapatite surface was much lower than that of DAC, which is associated with the flotation performance. During the floatation separation of the actual ore, 8wt% fluorapatite with a higher grade can be obtained using DTAB in contrast to DAC. Therefore, DTAB is a promising collector for the high-efficiency purification and sustainable utilization of valuable fluorapatite recourses.
