This article proposes a VGG network with histogram of oriented gradient(HOG) feature fusion(HOG-VGG) for polarization synthetic aperture radar(PolSAR) image terrain classification.VGG-Net has a strong ability of deep ...This article proposes a VGG network with histogram of oriented gradient(HOG) feature fusion(HOG-VGG) for polarization synthetic aperture radar(PolSAR) image terrain classification.VGG-Net has a strong ability of deep feature extraction,which can fully extract the global deep features of different terrains in PolSAR images,so it is widely used in PolSAR terrain classification.However,VGG-Net ignores the local edge & shape features,resulting in incomplete feature representation of the PolSAR terrains,as a consequence,the terrain classification accuracy is not promising.In fact,edge and shape features play an important role in PolSAR terrain classification.To solve this problem,a new VGG network with HOG feature fusion was specifically proposed for high-precision PolSAR terrain classification.HOG-VGG extracts both the global deep semantic features and the local edge & shape features of the PolSAR terrains,so the terrain feature representation completeness is greatly elevated.Moreover,HOG-VGG optimally fuses the global deep features and the local edge & shape features to achieve the best classification results.The superiority of HOG-VGG is verified on the Flevoland,San Francisco and Oberpfaffenhofen datasets.Experiments show that the proposed HOG-VGG achieves much better PolSAR terrain classification performance,with overall accuracies of 97.54%,94.63%,and 96.07%,respectively.展开更多
A method for terrain classification based on vibration response resulted from wheel-terrain interaction is presented. Four types of terrains including sine,gravel,cement and pebble were tested.The vibration data were ...A method for terrain classification based on vibration response resulted from wheel-terrain interaction is presented. Four types of terrains including sine,gravel,cement and pebble were tested.The vibration data were collected by two single axis accelerometers and a triaxial seat pad accelerometer,and five data sources were utilized. The feature vectors were obtained by combining features extracted from amplitude domain,frequency domain,and time-frequency domain. The ReliefF algorithm was used to evaluate the importance of attributes; accordingly,the optimal feature subsets were selected. Further,the predicted class was determined by fusion of outputs provided by five data sources. Finally,a voting algorithm,wherein a class with the most frequent occurrence is the predicted class,was employed. In addition,four different classifiers,namely support vector machine,k-nearest neighbors,Nave Bayes,and decision tree,were used to perform the classification and to test the proposed method. The results have shown that performances of all classifiers are improved.Therefore,the proposed method is proved to be effective.展开更多
Legged robots have potential advantages in mobility compared with wheeled robots in outdoor environments. The knowledge of various ground properties and adaptive locomotion based on different surface materials plays a...Legged robots have potential advantages in mobility compared with wheeled robots in outdoor environments. The knowledge of various ground properties and adaptive locomotion based on different surface materials plays an important role in improving the stability of legged robots. A terrain classification and adaptive locomotion method for a hexapod robot named Qingzhui is proposed in this paper. First, a force-based terrain classification method is suggested. Ground contact force is calculated by collecting joint torques and inertial measurement unit information. Ground substrates are classified with the feature vector extracted from the collected data using the support vector machine algorithm. Then, an adaptive locomotion on different ground properties is proposed. The dynamic alternating tripod trotting gait is developed to control the robot, and the parameters of active compliance control change with the terrain. Finally, the method is integrated on a hexapod robot and tested by real experiments. Our method is shown effective for the hexapod robot to walk on concrete, wood, grass, and foam. The strategies and experimental results can be a valuable reference for other legged robots applied in outdoor environments.展开更多
Given the advances in satellite altimetry and multibeam bathymetry,benthic terrain classification based on digital bathymetric models(DBMs)has been widely used for the mapping of benthic topographies.For instance,coba...Given the advances in satellite altimetry and multibeam bathymetry,benthic terrain classification based on digital bathymetric models(DBMs)has been widely used for the mapping of benthic topographies.For instance,cobaltrich crusts(CRCs)are important mineral resources found on seamounts and guyots in the western Pacific Ocean.Thick,plate-like CRCs are known to form on the summit and slopes of seamounts at the 1000–3000 m depth,while the relationship between seamount topography and spatial distribution of CRCs remains unclear.The benthic terrain classification of seamounts can solve this problem,thereby,facilitating the rapid exploration of seamount CRCs.Our study used an EM122 multibeam echosounder to retrieve high-resolution bathymetry data in the CRCs contract license area of China,i.e.,the Jiaxie Guyots in 2015 and 2016.Based on the DBM construted by bathymetirc data,broad-and fine-scale bathymetric position indices were utilized for quantitative classification of the terrain units of the Jiaxie Guyots on multiple scales.The classification revealed four first-order terrain units(e.g.,flat,crest,slope,and depression)and eleven second-order terrain units(e.g.,local crests,depressions on crests,gentle slopes,crests on slopes,and local depressions,etc.).Furthermore,the classification of the terrain and geological analysis indicated that the Weijia Guyot has a large flat summit,with local crests at the southern summit,whereas most of the guyot flanks were covered by gentle slopes.“Radial”mountain ridges have developed on the eastern side,while large-scale gravitational landslides have developed on the western and southern flanks.Additionally,landslide masses can be observed at the bottom of these slopes.The coverage of local crests on the seamount is∼1000 km^(2),and the local crests on the peak and flanks of the guyots may be the areas where thick and continuous plate-like CRCs are likely to occur.展开更多
Hyperspectral remote sensing images terrain classification faces the problems of high data dimensionality and lack of labeled training data, resulting in unsatisfied terrain classification efficiency. The feature extr...Hyperspectral remote sensing images terrain classification faces the problems of high data dimensionality and lack of labeled training data, resulting in unsatisfied terrain classification efficiency. The feature extraction is required before terrain classification for preserving discriminative information and reducing data dimensionality. A hyperspectral remote sensing images feature extraction method, i.e., discrete cosine transform （DCT） spectral regression discriminant analysis （SRDA） subspace method, was presented to solve the above problems. The proposed DCT SRDA subspace method firstly takes DCT in the original spectral space and gets the DCT coefficients of each pixel spectral curve; secondly performs SRDA in the DCT coefficients space and obtains the DCT SRDA subspace. Minimum distance classifier was designed in the resulting DCT SRDA subspace to evaluate the feature extraction performance. Experiments for two real airborne visible/infrared imaging spectrometer （AVIRIS） hyperspectral images show that, comparing with spectral LDA subspace method, the proposed DCT SRDA subspace method can improve terrain classification efficiency.展开更多
Terrain classification information is of great significance for legged robots to traverse various terrains.Therefore,this communication presents an online terrain classification framework for legged robots,utilizing t...Terrain classification information is of great significance for legged robots to traverse various terrains.Therefore,this communication presents an online terrain classification framework for legged robots,utilizing the acoustic signals produced during locomotion.The Mel-Frequency Cepstral Coefficient(MFCC)feature vectors are extracted from the acoustic data recorded by an on-board microphone.Then the Gaussian mixture models(GMMs)are used to classify the MFCC features into different terrain type categories.The proposed framework was validated on a quadruped robot.Overall,our investigations achieved a classification time-resolution of 1 s when the robot trotted over three kinds of terrains,thus recording a comprehensive success rate of 92.7%.展开更多
Wheeled-legged robots integrate the mobility efficiency of wheeled platforms with the terrain adaptability of legged robots,making them ideal for complex,unstructured environments.However,balancing high payload capaci...Wheeled-legged robots integrate the mobility efficiency of wheeled platforms with the terrain adaptability of legged robots,making them ideal for complex,unstructured environments.However,balancing high payload capacity with agile multimodal locomotion remains a major challenge.This paper presents a field study conducted in the high-altitude region of Golmud,Qinghai,with elevations ranging from 2800 m to 4000 m.We evaluate three wheeled-legged robot platforms of different scales on diverse terrains including Gobi,desert,grassland,and wetlands.Our experiments demonstrate the robot's robust locomotion performance across multimodal tasks such as obstacle crossing,slope climbing,and terrain classification.Moreover,we validate the performance of autonomous perception systems,including real-time localization and 3D mapping,under harsh plateau conditions.The results provide valuable insights into the deployment of wheeled-legged robots in extreme natural environments and lay a solid foundation for future applications in inspection,rescue,and transport missions in high-altitude regions.展开更多
基金Sponsored by the Fundamental Research Funds for the Central Universities of China(Grant No.PA2023IISL0098)the Hefei Municipal Natural Science Foundation(Grant No.202201)+1 种基金the National Natural Science Foundation of China(Grant No.62071164)the Open Fund of Information Materials and Intelligent Sensing Laboratory of Anhui Province(Anhui University)(Grant No.IMIS202214 and IMIS202102)。
文摘This article proposes a VGG network with histogram of oriented gradient(HOG) feature fusion(HOG-VGG) for polarization synthetic aperture radar(PolSAR) image terrain classification.VGG-Net has a strong ability of deep feature extraction,which can fully extract the global deep features of different terrains in PolSAR images,so it is widely used in PolSAR terrain classification.However,VGG-Net ignores the local edge & shape features,resulting in incomplete feature representation of the PolSAR terrains,as a consequence,the terrain classification accuracy is not promising.In fact,edge and shape features play an important role in PolSAR terrain classification.To solve this problem,a new VGG network with HOG feature fusion was specifically proposed for high-precision PolSAR terrain classification.HOG-VGG extracts both the global deep semantic features and the local edge & shape features of the PolSAR terrains,so the terrain feature representation completeness is greatly elevated.Moreover,HOG-VGG optimally fuses the global deep features and the local edge & shape features to achieve the best classification results.The superiority of HOG-VGG is verified on the Flevoland,San Francisco and Oberpfaffenhofen datasets.Experiments show that the proposed HOG-VGG achieves much better PolSAR terrain classification performance,with overall accuracies of 97.54%,94.63%,and 96.07%,respectively.
基金Supported by the National Natural Science Foundation of China(51005018)
文摘A method for terrain classification based on vibration response resulted from wheel-terrain interaction is presented. Four types of terrains including sine,gravel,cement and pebble were tested.The vibration data were collected by two single axis accelerometers and a triaxial seat pad accelerometer,and five data sources were utilized. The feature vectors were obtained by combining features extracted from amplitude domain,frequency domain,and time-frequency domain. The ReliefF algorithm was used to evaluate the importance of attributes; accordingly,the optimal feature subsets were selected. Further,the predicted class was determined by fusion of outputs provided by five data sources. Finally,a voting algorithm,wherein a class with the most frequent occurrence is the predicted class,was employed. In addition,four different classifiers,namely support vector machine,k-nearest neighbors,Nave Bayes,and decision tree,were used to perform the classification and to test the proposed method. The results have shown that performances of all classifiers are improved.Therefore,the proposed method is proved to be effective.
基金This work was supported by the National Nature Science Foundation of China(Grant Nos.U1613208 and 51927809)the National Key R&D Program of China(Grant No.2017YFE0112200)the European Union's Horizon 2020 Research and Innovation Program under the Marie Sklodowska-Curie grant(Grant No.734575).
文摘Legged robots have potential advantages in mobility compared with wheeled robots in outdoor environments. The knowledge of various ground properties and adaptive locomotion based on different surface materials plays an important role in improving the stability of legged robots. A terrain classification and adaptive locomotion method for a hexapod robot named Qingzhui is proposed in this paper. First, a force-based terrain classification method is suggested. Ground contact force is calculated by collecting joint torques and inertial measurement unit information. Ground substrates are classified with the feature vector extracted from the collected data using the support vector machine algorithm. Then, an adaptive locomotion on different ground properties is proposed. The dynamic alternating tripod trotting gait is developed to control the robot, and the parameters of active compliance control change with the terrain. Finally, the method is integrated on a hexapod robot and tested by real experiments. Our method is shown effective for the hexapod robot to walk on concrete, wood, grass, and foam. The strategies and experimental results can be a valuable reference for other legged robots applied in outdoor environments.
基金The National Natural Science Foundation of China under contract Nos 42072324 and 91958202the Key Special Project for Introduced Talents Team of Southern Marine Science and Engineering Guangdong Laboratory(Guangzhou)under contract No.GML2019ZD0106+1 种基金the Resource&Environment Project of China Ocean Mineral Resources R&D Association under contract No.DY135-C1-1-03the Geological Survey Project of China Geological Survey under contract No.DD20190629.
文摘Given the advances in satellite altimetry and multibeam bathymetry,benthic terrain classification based on digital bathymetric models(DBMs)has been widely used for the mapping of benthic topographies.For instance,cobaltrich crusts(CRCs)are important mineral resources found on seamounts and guyots in the western Pacific Ocean.Thick,plate-like CRCs are known to form on the summit and slopes of seamounts at the 1000–3000 m depth,while the relationship between seamount topography and spatial distribution of CRCs remains unclear.The benthic terrain classification of seamounts can solve this problem,thereby,facilitating the rapid exploration of seamount CRCs.Our study used an EM122 multibeam echosounder to retrieve high-resolution bathymetry data in the CRCs contract license area of China,i.e.,the Jiaxie Guyots in 2015 and 2016.Based on the DBM construted by bathymetirc data,broad-and fine-scale bathymetric position indices were utilized for quantitative classification of the terrain units of the Jiaxie Guyots on multiple scales.The classification revealed four first-order terrain units(e.g.,flat,crest,slope,and depression)and eleven second-order terrain units(e.g.,local crests,depressions on crests,gentle slopes,crests on slopes,and local depressions,etc.).Furthermore,the classification of the terrain and geological analysis indicated that the Weijia Guyot has a large flat summit,with local crests at the southern summit,whereas most of the guyot flanks were covered by gentle slopes.“Radial”mountain ridges have developed on the eastern side,while large-scale gravitational landslides have developed on the western and southern flanks.Additionally,landslide masses can be observed at the bottom of these slopes.The coverage of local crests on the seamount is∼1000 km^(2),and the local crests on the peak and flanks of the guyots may be the areas where thick and continuous plate-like CRCs are likely to occur.
基金supported in part by the National Natural Science Foundation of China (61003199)the Natural Science Foundation of Shaanxi Province of China (2014JQ5183, 2014JM8331)the Special Foundation for Natural Science of the Education Department of Shaanxi Province of China (2013JK1129, 2013JK1075)
文摘Hyperspectral remote sensing images terrain classification faces the problems of high data dimensionality and lack of labeled training data, resulting in unsatisfied terrain classification efficiency. The feature extraction is required before terrain classification for preserving discriminative information and reducing data dimensionality. A hyperspectral remote sensing images feature extraction method, i.e., discrete cosine transform （DCT） spectral regression discriminant analysis （SRDA） subspace method, was presented to solve the above problems. The proposed DCT SRDA subspace method firstly takes DCT in the original spectral space and gets the DCT coefficients of each pixel spectral curve; secondly performs SRDA in the DCT coefficients space and obtains the DCT SRDA subspace. Minimum distance classifier was designed in the resulting DCT SRDA subspace to evaluate the feature extraction performance. Experiments for two real airborne visible/infrared imaging spectrometer （AVIRIS） hyperspectral images show that, comparing with spectral LDA subspace method, the proposed DCT SRDA subspace method can improve terrain classification efficiency.
基金supported by the National Natural Science Foundation of China(62003190)the Shandong Provincial Natural Science Foundation(ZR201911040226)the Open Research Projects of Zhejiang Lab(2022NB0AB06).
文摘Terrain classification information is of great significance for legged robots to traverse various terrains.Therefore,this communication presents an online terrain classification framework for legged robots,utilizing the acoustic signals produced during locomotion.The Mel-Frequency Cepstral Coefficient(MFCC)feature vectors are extracted from the acoustic data recorded by an on-board microphone.Then the Gaussian mixture models(GMMs)are used to classify the MFCC features into different terrain type categories.The proposed framework was validated on a quadruped robot.Overall,our investigations achieved a classification time-resolution of 1 s when the robot trotted over three kinds of terrains,thus recording a comprehensive success rate of 92.7%.
基金supported in part by the National Key R&D Program of china(2022YFB4701500 and 2024YFB4708705)in part by the National Natural Science Foundation of China(52475021,52305024 and 52205012)+2 种基金in part by the Natural Science Foundation of jiangsu Province,China(BK20230928)in part by the China Postdoctoral Science Foundation,China(2023M731690)in part by the Fundamental Research Funds for the Central Universities,China(30923011029).
文摘Wheeled-legged robots integrate the mobility efficiency of wheeled platforms with the terrain adaptability of legged robots,making them ideal for complex,unstructured environments.However,balancing high payload capacity with agile multimodal locomotion remains a major challenge.This paper presents a field study conducted in the high-altitude region of Golmud,Qinghai,with elevations ranging from 2800 m to 4000 m.We evaluate three wheeled-legged robot platforms of different scales on diverse terrains including Gobi,desert,grassland,and wetlands.Our experiments demonstrate the robot's robust locomotion performance across multimodal tasks such as obstacle crossing,slope climbing,and terrain classification.Moreover,we validate the performance of autonomous perception systems,including real-time localization and 3D mapping,under harsh plateau conditions.The results provide valuable insights into the deployment of wheeled-legged robots in extreme natural environments and lay a solid foundation for future applications in inspection,rescue,and transport missions in high-altitude regions.
