Accurate segmentation of camouflage objects in aerial imagery is vital for improving the efficiency of UAV-based reconnaissance and rescue missions.However,camouflage object segmentation is increasingly challenging du...Accurate segmentation of camouflage objects in aerial imagery is vital for improving the efficiency of UAV-based reconnaissance and rescue missions.However,camouflage object segmentation is increasingly challenging due to advances in both camouflage materials and biological mimicry.Although multispectral-RGB based technology shows promise,conventional dual-aperture multispectral-RGB imaging systems are constrained by imprecise and time-consuming registration and fusion across different modalities,limiting their performance.Here,we propose the Reconstructed Multispectral-RGB Fusion Network(RMRF-Net),which reconstructs RGB images into multispectral ones,enabling efficient multimodal segmentation using only an RGB camera.Specifically,RMRF-Net employs a divergentsimilarity feature correction strategy to minimize reconstruction errors and includes an efficient boundary-aware decoder to enhance object contours.Notably,we establish the first real-world aerial multispectral-RGB semantic segmentation of camouflage objects dataset,including 11 object categories.Experimental results demonstrate that RMRF-Net outperforms existing methods,achieving 17.38 FPS on the NVIDIA Jetson AGX Orin,with only a 0.96%drop in mIoU compared to the RTX 3090,showing its practical applicability in multimodal remote sensing.展开更多
This paper proposes a desirable method to detect different kinds of low probability of intercept (LPI) radar signals, targeted at the main intra-pulse modulation method of LPI radar signals including the signals of li...This paper proposes a desirable method to detect different kinds of low probability of intercept (LPI) radar signals, targeted at the main intra-pulse modulation method of LPI radar signals including the signals of linear frequency modulation, phase code, and frequency code. Firstly, it improves the coherent integration of LPI radar signals by adding the periodicity of the ambiguity function. Then, it develops a frequency domain detection method based on fast Fourier transform (FFT) and segmented autocorrelation function to detect signals without features of linear frequency modulation by virtue of the distribution characteristics of noise signals in the frequency domain. Finally, this paper gives a verification of the performance of the method for different signal-to-noise ratios by conducting simulation experiments, and compares the method with existing ones. Additionally, this method is characterized by the straightforward calculation and high real-time performance, which is conducive to better detecting all kinds of LPI radar signals.展开更多
Aiming at the problems of demagnetization effect of electromagnetic buffer(EMB)caused by high velocity under intensive impact load and the difficulty and error of machining composite thin-walled long tube,a segmented ...Aiming at the problems of demagnetization effect of electromagnetic buffer(EMB)caused by high velocity under intensive impact load and the difficulty and error of machining composite thin-walled long tube,a segmented EMB is proposed.The inner tube and air-gap are divided into initial segments and the traversing segments.Through theoretical analysis,impact test and simulation,it can be found that the RRF curve has two peaks.Firstly,in order to reduce the resultant resistance force(RRF)peaks,the sensitivity analysis based on optimal Latin hypercube design(OLHD)and polynomial regression was performed.The results show that the smallest contribution ratio to the dynamic response is the seventh and ninth segments of the inner tube,which are less than 1%.Then,fully considering the uncertain factors,important parameters are selected for uncertain optimization after sensitivity analysis.The interval order and interval probability degree methods are used to establish interval uncertain optimization model of the RRF considering robustness.The model was solved using an interval nested optimization method based on radial basis function(RBF)neural network.Finally,the Pareto front is obtained and numerical simulation is performed to verify the optimal value.It indicates that the two kinds of RRF peak is obviously reduced,and the optimization object and strategy are effective.展开更多
This paper discusses the basic principle and design m ethod for light distribution of car lamp, introduces an important development: h igh efficient and flexible car lamp with reflecting light distribution-segmente d ...This paper discusses the basic principle and design m ethod for light distribution of car lamp, introduces an important development: h igh efficient and flexible car lamp with reflecting light distribution-segmente d reflector (multi-patch) car lamp, and puts out a design method for segmented reflector based on error analysis. Unlike classical car lamp with refractive lig ht distribution, the method of reflecting light distribution gives car lamp desi gn more flexibility. In the case of guarantying the lightness of car lamp and sa tisfying the standard demand for the light distribution, the design of the exter ior of the car lamp has more freedom. The high gradient of car lamp is more suit able for the demand of streamline of the car exterior. The shape of segmented re flector obtained by theory calculating of car lamp reflecting light distribution is only an ideal shape, which usually has considerable differences with the fin al shape and will influences light distribution. There exist difference between the calculated reflector and manufactured reflector. Owing to light reflecting c haracter, the small diversification of the reflector will reduce the big diver sification of the light distribution shape on light distribution screen in 25 -meter place, so light distribution quality can’t be ensured. To ensure the re flector by light distribution calculation accordance to reflector by practical m anufacture, the error effect of surface shape must be reasonably considered name ly the error effect of manufacture tache. The paper establishes error-analyzing model for segmented reflector according to the analysis of error of making proc ess for segmented reflector. Based on this error-analyzing model and by use of the analyzing software developed for segmented reflector light distribution, it could reasonably consider reflector errors made by manufacturing, such as reflec tor surface spray-painting and plating aluminum, which could give out shapes of reflector patches for segmented reflector well and truly, and direct the plan o f making process efficiently. The method put by the paper has successfully appli ed to develop segmented reflector lamp for several type cars and obtained good e ffect for the factory.展开更多
With the development of underwater sonar detection technology,simultaneous localization and mapping(SLAM)approach has attracted much attention in underwater navigation field in recent years.But the weak detection abil...With the development of underwater sonar detection technology,simultaneous localization and mapping(SLAM)approach has attracted much attention in underwater navigation field in recent years.But the weak detection ability of a single vehicle limits the SLAM performance in wide areas.Thereby,cooperative SLAM using multiple vehicles has become an important research direction.The key factor of cooperative SLAM is timely and efficient sonar image transmission among underwater vehicles.However,the limited bandwidth of underwater acoustic channels contradicts a large amount of sonar image data.It is essential to compress the images before transmission.Recently,deep neural networks have great value in image compression by virtue of the powerful learning ability of neural networks,but the existing sonar image compression methods based on neural network usually focus on the pixel-level information without the semantic-level information.In this paper,we propose a novel underwater acoustic transmission scheme called UAT-SSIC that includes semantic segmentation-based sonar image compression(SSIC)framework and the joint source-channel codec,to improve the accuracy of the semantic information of the reconstructed sonar image at the receiver.The SSIC framework consists of Auto-Encoder structure-based sonar image compression network,which is measured by a semantic segmentation network's residual.Considering that sonar images have the characteristics of blurred target edges,the semantic segmentation network used a special dilated convolution neural network(DiCNN)to enhance segmentation accuracy by expanding the range of receptive fields.The joint source-channel codec with unequal error protection is proposed that adjusts the power level of the transmitted data,which deal with sonar image transmission error caused by the serious underwater acoustic channel.Experiment results demonstrate that our method preserves more semantic information,with advantages over existing methods at the same compression ratio.It also improves the error tolerance and packet loss resistance of transmission.展开更多
Target maneuver recognition is a prerequisite for air combat situation awareness,trajectory prediction,threat assessment and maneuver decision.To get rid of the dependence of the current target maneuver recognition me...Target maneuver recognition is a prerequisite for air combat situation awareness,trajectory prediction,threat assessment and maneuver decision.To get rid of the dependence of the current target maneuver recognition method on empirical criteria and sample data,and automatically and adaptively complete the task of extracting the target maneuver pattern,in this paper,an air combat maneuver pattern extraction based on time series segmentation and clustering analysis is proposed by combining autoencoder,G-G clustering algorithm and the selective ensemble clustering analysis algorithm.Firstly,the autoencoder is used to extract key features of maneuvering trajectory to remove the impacts of redundant variables and reduce the data dimension;Then,taking the time information into account,the segmentation of Maneuver characteristic time series is realized with the improved FSTS-AEGG algorithm,and a large number of maneuver primitives are extracted;Finally,the maneuver primitives are grouped into some categories by using the selective ensemble multiple time series clustering algorithm,which can prove that each class represents a maneuver action.The maneuver pattern extraction method is applied to small scale air combat trajectory and can recognize and correctly partition at least 71.3%of maneuver actions,indicating that the method is effective and satisfies the requirements for engineering accuracy.In addition,this method can provide data support for various target maneuvering recognition methods proposed in the literature,greatly reduce the workload and improve the recognition accuracy.展开更多
X-ray computed tomography(CT)has been an important technology in paleontology for several decades.It helps researchers to acquire detailed anatomical structures of fossils non-destructively.Despite its widespread appl...X-ray computed tomography(CT)has been an important technology in paleontology for several decades.It helps researchers to acquire detailed anatomical structures of fossils non-destructively.Despite its widespread application,developing an efficient and user-friendly method for segmenting CT data continues to be a formidable challenge in the field.Most CT data segmentation software operates on 2D interfaces,which limits flexibility for real-time adjustments in 3D segmentation.Here,we introduce Curves Mode in Drishti Paint 3.2,an open-source tool for CT data segmentation.Drishti Paint 3.2 allows users to manually or semi-automatically segment the CT data in both 2D and 3D environments,providing a novel solution for revisualizing CT data in paleontological studies.展开更多
基金National Natural Science Foundation of China(Grant Nos.62005049 and 62072110)Natural Science Foundation of Fujian Province(Grant No.2020J01451).
文摘Accurate segmentation of camouflage objects in aerial imagery is vital for improving the efficiency of UAV-based reconnaissance and rescue missions.However,camouflage object segmentation is increasingly challenging due to advances in both camouflage materials and biological mimicry.Although multispectral-RGB based technology shows promise,conventional dual-aperture multispectral-RGB imaging systems are constrained by imprecise and time-consuming registration and fusion across different modalities,limiting their performance.Here,we propose the Reconstructed Multispectral-RGB Fusion Network(RMRF-Net),which reconstructs RGB images into multispectral ones,enabling efficient multimodal segmentation using only an RGB camera.Specifically,RMRF-Net employs a divergentsimilarity feature correction strategy to minimize reconstruction errors and includes an efficient boundary-aware decoder to enhance object contours.Notably,we establish the first real-world aerial multispectral-RGB semantic segmentation of camouflage objects dataset,including 11 object categories.Experimental results demonstrate that RMRF-Net outperforms existing methods,achieving 17.38 FPS on the NVIDIA Jetson AGX Orin,with only a 0.96%drop in mIoU compared to the RTX 3090,showing its practical applicability in multimodal remote sensing.
基金supported by the National Natural Science Foundation of China(61571462)Weapons and Equipment Exploration Research Project(7131464)
文摘This paper proposes a desirable method to detect different kinds of low probability of intercept (LPI) radar signals, targeted at the main intra-pulse modulation method of LPI radar signals including the signals of linear frequency modulation, phase code, and frequency code. Firstly, it improves the coherent integration of LPI radar signals by adding the periodicity of the ambiguity function. Then, it develops a frequency domain detection method based on fast Fourier transform (FFT) and segmented autocorrelation function to detect signals without features of linear frequency modulation by virtue of the distribution characteristics of noise signals in the frequency domain. Finally, this paper gives a verification of the performance of the method for different signal-to-noise ratios by conducting simulation experiments, and compares the method with existing ones. Additionally, this method is characterized by the straightforward calculation and high real-time performance, which is conducive to better detecting all kinds of LPI radar signals.
基金the National Natural Science Foundation of China(grant number 301070603)。
文摘Aiming at the problems of demagnetization effect of electromagnetic buffer(EMB)caused by high velocity under intensive impact load and the difficulty and error of machining composite thin-walled long tube,a segmented EMB is proposed.The inner tube and air-gap are divided into initial segments and the traversing segments.Through theoretical analysis,impact test and simulation,it can be found that the RRF curve has two peaks.Firstly,in order to reduce the resultant resistance force(RRF)peaks,the sensitivity analysis based on optimal Latin hypercube design(OLHD)and polynomial regression was performed.The results show that the smallest contribution ratio to the dynamic response is the seventh and ninth segments of the inner tube,which are less than 1%.Then,fully considering the uncertain factors,important parameters are selected for uncertain optimization after sensitivity analysis.The interval order and interval probability degree methods are used to establish interval uncertain optimization model of the RRF considering robustness.The model was solved using an interval nested optimization method based on radial basis function(RBF)neural network.Finally,the Pareto front is obtained and numerical simulation is performed to verify the optimal value.It indicates that the two kinds of RRF peak is obviously reduced,and the optimization object and strategy are effective.
文摘This paper discusses the basic principle and design m ethod for light distribution of car lamp, introduces an important development: h igh efficient and flexible car lamp with reflecting light distribution-segmente d reflector (multi-patch) car lamp, and puts out a design method for segmented reflector based on error analysis. Unlike classical car lamp with refractive lig ht distribution, the method of reflecting light distribution gives car lamp desi gn more flexibility. In the case of guarantying the lightness of car lamp and sa tisfying the standard demand for the light distribution, the design of the exter ior of the car lamp has more freedom. The high gradient of car lamp is more suit able for the demand of streamline of the car exterior. The shape of segmented re flector obtained by theory calculating of car lamp reflecting light distribution is only an ideal shape, which usually has considerable differences with the fin al shape and will influences light distribution. There exist difference between the calculated reflector and manufactured reflector. Owing to light reflecting c haracter, the small diversification of the reflector will reduce the big diver sification of the light distribution shape on light distribution screen in 25 -meter place, so light distribution quality can’t be ensured. To ensure the re flector by light distribution calculation accordance to reflector by practical m anufacture, the error effect of surface shape must be reasonably considered name ly the error effect of manufacture tache. The paper establishes error-analyzing model for segmented reflector according to the analysis of error of making proc ess for segmented reflector. Based on this error-analyzing model and by use of the analyzing software developed for segmented reflector light distribution, it could reasonably consider reflector errors made by manufacturing, such as reflec tor surface spray-painting and plating aluminum, which could give out shapes of reflector patches for segmented reflector well and truly, and direct the plan o f making process efficiently. The method put by the paper has successfully appli ed to develop segmented reflector lamp for several type cars and obtained good e ffect for the factory.
基金supported in part by the Tianjin Technology Innovation Guidance Special Fund Project under Grant No.21YDTPJC00850in part by the National Natural Science Foundation of China under Grant No.41906161in part by the Natural Science Foundation of Tianjin under Grant No.21JCQNJC00650。
文摘With the development of underwater sonar detection technology,simultaneous localization and mapping(SLAM)approach has attracted much attention in underwater navigation field in recent years.But the weak detection ability of a single vehicle limits the SLAM performance in wide areas.Thereby,cooperative SLAM using multiple vehicles has become an important research direction.The key factor of cooperative SLAM is timely and efficient sonar image transmission among underwater vehicles.However,the limited bandwidth of underwater acoustic channels contradicts a large amount of sonar image data.It is essential to compress the images before transmission.Recently,deep neural networks have great value in image compression by virtue of the powerful learning ability of neural networks,but the existing sonar image compression methods based on neural network usually focus on the pixel-level information without the semantic-level information.In this paper,we propose a novel underwater acoustic transmission scheme called UAT-SSIC that includes semantic segmentation-based sonar image compression(SSIC)framework and the joint source-channel codec,to improve the accuracy of the semantic information of the reconstructed sonar image at the receiver.The SSIC framework consists of Auto-Encoder structure-based sonar image compression network,which is measured by a semantic segmentation network's residual.Considering that sonar images have the characteristics of blurred target edges,the semantic segmentation network used a special dilated convolution neural network(DiCNN)to enhance segmentation accuracy by expanding the range of receptive fields.The joint source-channel codec with unequal error protection is proposed that adjusts the power level of the transmitted data,which deal with sonar image transmission error caused by the serious underwater acoustic channel.Experiment results demonstrate that our method preserves more semantic information,with advantages over existing methods at the same compression ratio.It also improves the error tolerance and packet loss resistance of transmission.
基金supported by the National Natural Science Foundation of China (Project No.72301293)。
文摘Target maneuver recognition is a prerequisite for air combat situation awareness,trajectory prediction,threat assessment and maneuver decision.To get rid of the dependence of the current target maneuver recognition method on empirical criteria and sample data,and automatically and adaptively complete the task of extracting the target maneuver pattern,in this paper,an air combat maneuver pattern extraction based on time series segmentation and clustering analysis is proposed by combining autoencoder,G-G clustering algorithm and the selective ensemble clustering analysis algorithm.Firstly,the autoencoder is used to extract key features of maneuvering trajectory to remove the impacts of redundant variables and reduce the data dimension;Then,taking the time information into account,the segmentation of Maneuver characteristic time series is realized with the improved FSTS-AEGG algorithm,and a large number of maneuver primitives are extracted;Finally,the maneuver primitives are grouped into some categories by using the selective ensemble multiple time series clustering algorithm,which can prove that each class represents a maneuver action.The maneuver pattern extraction method is applied to small scale air combat trajectory and can recognize and correctly partition at least 71.3%of maneuver actions,indicating that the method is effective and satisfies the requirements for engineering accuracy.In addition,this method can provide data support for various target maneuvering recognition methods proposed in the literature,greatly reduce the workload and improve the recognition accuracy.
文摘X-ray computed tomography(CT)has been an important technology in paleontology for several decades.It helps researchers to acquire detailed anatomical structures of fossils non-destructively.Despite its widespread application,developing an efficient and user-friendly method for segmenting CT data continues to be a formidable challenge in the field.Most CT data segmentation software operates on 2D interfaces,which limits flexibility for real-time adjustments in 3D segmentation.Here,we introduce Curves Mode in Drishti Paint 3.2,an open-source tool for CT data segmentation.Drishti Paint 3.2 allows users to manually or semi-automatically segment the CT data in both 2D and 3D environments,providing a novel solution for revisualizing CT data in paleontological studies.
