Visual odometry is critical in visual simultaneous localization and mapping for robot navigation.However,the pose estimation performance of most current visual odometry algorithms degrades in scenes with unevenly dist...Visual odometry is critical in visual simultaneous localization and mapping for robot navigation.However,the pose estimation performance of most current visual odometry algorithms degrades in scenes with unevenly distributed features because dense features occupy excessive weight.Herein,a new human visual attention mechanism for point-and-line stereo visual odometry,which is called point-line-weight-mechanism visual odometry(PLWM-VO),is proposed to describe scene features in a global and balanced manner.A weight-adaptive model based on region partition and region growth is generated for the human visual attention mechanism,where sufficient attention is assigned to position-distinctive objects(sparse features in the environment).Furthermore,the sum of absolute differences algorithm is used to improve the accuracy of initialization for line features.Compared with the state-of-the-art method(ORB-VO),PLWM-VO show a 36.79%reduction in the absolute trajectory error on the Kitti and Euroc datasets.Although the time consumption of PLWM-VO is higher than that of ORB-VO,online test results indicate that PLWM-VO satisfies the real-time demand.The proposed algorithm not only significantly promotes the environmental adaptability of visual odometry,but also quantitatively demonstrates the superiority of the human visual attention mechanism.展开更多
U-Net has achieved good performance with the small-scale datasets through skip connections to merge the features of the low-level layers and high-level layers and has been widely utilized in biomedical image segmentat...U-Net has achieved good performance with the small-scale datasets through skip connections to merge the features of the low-level layers and high-level layers and has been widely utilized in biomedical image segmentation as well as recent microstructure image segregation of the materials.Three representative visual attention mechanism modules,named as squeeze-and-excitation networks,convolutional block attention module,and extended calibration algorithm,were intro-duced into the traditional U-Net architecture to further improve the prediction accuracy.It is found that compared with the original U-Net architecture,the evaluation index of the improved U-Net architecture has been significantly improved for the microstructure segmentation of the steels with the ferrite/martensite composite microstructure and pearlite/ferrite composite microstructure and the complex martensite/austenite island/bainite microstructure,which demonstrates the advantages of the utilization of the visual attention mechanism in the microstructure segregation.The reasons for the accuracy improvement were discussed based on the feature maps analysis.展开更多
Aiming at intercepting large maneuvering targets precisely,the guidance law of advanced self-seeking missiles requires not only inertial line-of-sight(LOS)angular rate but also target maneuvering acceleration.Moreover...Aiming at intercepting large maneuvering targets precisely,the guidance law of advanced self-seeking missiles requires not only inertial line-of-sight(LOS)angular rate but also target maneuvering acceleration.Moreover,the semi-strapdown stabilization platform has lost the ability to measure the inertial LOS angular rate directly,which needs to be extracted by numerical calculation.The differential operation commonly used in traditional methods can magnify the measurement error of the sensor,resulting in insufficient calculation accuracy of the line-of-sight angular rate.By analyzing the mathematical relationship between the missile-target relative motion and the angle tracking system,a multi-process-fusion integrated filter model of relative motion and angle tracking is presented.To overcome the defect that the infrared seeker cannot directly measure the missile-target distance,following the snake-hot-eye visual mechanism,a visual bionic imaging guidance method of estimating the missile-target relative distance from the infrared images is proposed to improve the observability of the filter model.Finally,target-tracking simulations verify that the estimation accuracy of target acceleration is improved by four times.展开更多
People attach great importance to high detection probability and low false alarm probability for infrared dim target detection. Consequently, a novel approach is proposed based on inverted local information entropy ma...People attach great importance to high detection probability and low false alarm probability for infrared dim target detection. Consequently, a novel approach is proposed based on inverted local information entropy map and the improved region growing technique. The idea originates from the intrinsic property of natural image, the visual mechanism of flying insects and the information entropy theory. Besides qualitative analyses, other methods including the norms of local signal-to-background ratio, local signal-to-noise ratio, region non-uniformity, single-frame detection probability and single-frame false alarm probability are adopted to quantitatively evaluate the proposed approach. Both qualitative and quantitative comparisons confirm the validity and efficiency of the proposed approach.展开更多
The brain’s selective visual attention mechanism(SVAM)enables robust visual recognition in noisy environment through diverse neural action potential peaks acting as filters.Spiking neural networks(SNNs)mimic this par...The brain’s selective visual attention mechanism(SVAM)enables robust visual recognition in noisy environment through diverse neural action potential peaks acting as filters.Spiking neural networks(SNNs)mimic this paradigm but limited noise immunity and high write current density hinder brain-like efficiency.Hardware implementing SVAM necessitates spiking spintronic devices with noise-resistant and low operation current densities;such devices remain unreported.Here,we report an orbit-torque(OT)actuated ferromagnetic spiking synapse and neuron featuring a tunable peak action potential.These are more akin to the biological neurons with varying sensitivities to external sensory stimuli,thereby augmenting the perception aptitude of the system in complex surroundings.Capitalizing on the high-efficient OT,the ferromagnetic device demands a write current density of 5×10^(6) A/cm^(2),which is an order of magnitude lower than other spiking devices actuated by spin-orbit torque.Leveraging these neuromorphic devices,an all-spin SNN with low current density and tunable action potential peak has been fabricated,successfully mimicking the SVAM.In complex noise environment,the SNN achieves 92%on Cifar-10 and 95%on MNIST dataset,surpassing state-of-the-art spin-based SNNs by 5%.Our work provides a promising avenue for exploring the SVAM-inspired spiking neuromorphic devices,enhancing the bionic performance of the SNNs.展开更多
基金Supported by Tianjin Municipal Natural Science Foundation of China(Grant No.19JCJQJC61600)Hebei Provincial Natural Science Foundation of China(Grant Nos.F2020202051,F2020202053).
文摘Visual odometry is critical in visual simultaneous localization and mapping for robot navigation.However,the pose estimation performance of most current visual odometry algorithms degrades in scenes with unevenly distributed features because dense features occupy excessive weight.Herein,a new human visual attention mechanism for point-and-line stereo visual odometry,which is called point-line-weight-mechanism visual odometry(PLWM-VO),is proposed to describe scene features in a global and balanced manner.A weight-adaptive model based on region partition and region growth is generated for the human visual attention mechanism,where sufficient attention is assigned to position-distinctive objects(sparse features in the environment).Furthermore,the sum of absolute differences algorithm is used to improve the accuracy of initialization for line features.Compared with the state-of-the-art method(ORB-VO),PLWM-VO show a 36.79%reduction in the absolute trajectory error on the Kitti and Euroc datasets.Although the time consumption of PLWM-VO is higher than that of ORB-VO,online test results indicate that PLWM-VO satisfies the real-time demand.The proposed algorithm not only significantly promotes the environmental adaptability of visual odometry,but also quantitatively demonstrates the superiority of the human visual attention mechanism.
基金support from National Natural Science Foundation of China(Nos.52071238 and U20A20279)National Key Research and Development Program of China(2022YFB3706701)the 111 Project(No.D18018)。
文摘U-Net has achieved good performance with the small-scale datasets through skip connections to merge the features of the low-level layers and high-level layers and has been widely utilized in biomedical image segmentation as well as recent microstructure image segregation of the materials.Three representative visual attention mechanism modules,named as squeeze-and-excitation networks,convolutional block attention module,and extended calibration algorithm,were intro-duced into the traditional U-Net architecture to further improve the prediction accuracy.It is found that compared with the original U-Net architecture,the evaluation index of the improved U-Net architecture has been significantly improved for the microstructure segmentation of the steels with the ferrite/martensite composite microstructure and pearlite/ferrite composite microstructure and the complex martensite/austenite island/bainite microstructure,which demonstrates the advantages of the utilization of the visual attention mechanism in the microstructure segregation.The reasons for the accuracy improvement were discussed based on the feature maps analysis.
基金sponsored by the National Natural Science Foundation of China under Grant No.51979275the Joint Open Research Fund Program of State Key Laboratory of Hydroscience and Engineering and Tsinghua—Ningxia Yinchuan Joint Institute of Internet of Waters on Digital Water Governance under Grant No.sklhse-2022-Iow08+2 种基金the Open Fund of Key Laboratory of Urban Land Resources Monitoring and Simulation,Ministry of Natural Resources under Grant No.KF-2021-06-115the National Key R&D Program of China under Grant No.2018YFD0700603the 2115 Talent Development Program of China Agricultural University.
文摘Aiming at intercepting large maneuvering targets precisely,the guidance law of advanced self-seeking missiles requires not only inertial line-of-sight(LOS)angular rate but also target maneuvering acceleration.Moreover,the semi-strapdown stabilization platform has lost the ability to measure the inertial LOS angular rate directly,which needs to be extracted by numerical calculation.The differential operation commonly used in traditional methods can magnify the measurement error of the sensor,resulting in insufficient calculation accuracy of the line-of-sight angular rate.By analyzing the mathematical relationship between the missile-target relative motion and the angle tracking system,a multi-process-fusion integrated filter model of relative motion and angle tracking is presented.To overcome the defect that the infrared seeker cannot directly measure the missile-target distance,following the snake-hot-eye visual mechanism,a visual bionic imaging guidance method of estimating the missile-target relative distance from the infrared images is proposed to improve the observability of the filter model.Finally,target-tracking simulations verify that the estimation accuracy of target acceleration is improved by four times.
基金supported by National Natural Science Foundation of China(No.61471355)
文摘People attach great importance to high detection probability and low false alarm probability for infrared dim target detection. Consequently, a novel approach is proposed based on inverted local information entropy map and the improved region growing technique. The idea originates from the intrinsic property of natural image, the visual mechanism of flying insects and the information entropy theory. Besides qualitative analyses, other methods including the norms of local signal-to-background ratio, local signal-to-noise ratio, region non-uniformity, single-frame detection probability and single-frame false alarm probability are adopted to quantitatively evaluate the proposed approach. Both qualitative and quantitative comparisons confirm the validity and efficiency of the proposed approach.
基金supported by the National Natural Science Foundation of China(12304160,12304161,62172155,U22A2027,62274183,and 62301595)the Research Foundation from National University of Defense Technology(ZK24-18,23-ZZCX-ZZGC-01-02,and 22-ZZCX-046-02)。
文摘The brain’s selective visual attention mechanism(SVAM)enables robust visual recognition in noisy environment through diverse neural action potential peaks acting as filters.Spiking neural networks(SNNs)mimic this paradigm but limited noise immunity and high write current density hinder brain-like efficiency.Hardware implementing SVAM necessitates spiking spintronic devices with noise-resistant and low operation current densities;such devices remain unreported.Here,we report an orbit-torque(OT)actuated ferromagnetic spiking synapse and neuron featuring a tunable peak action potential.These are more akin to the biological neurons with varying sensitivities to external sensory stimuli,thereby augmenting the perception aptitude of the system in complex surroundings.Capitalizing on the high-efficient OT,the ferromagnetic device demands a write current density of 5×10^(6) A/cm^(2),which is an order of magnitude lower than other spiking devices actuated by spin-orbit torque.Leveraging these neuromorphic devices,an all-spin SNN with low current density and tunable action potential peak has been fabricated,successfully mimicking the SVAM.In complex noise environment,the SNN achieves 92%on Cifar-10 and 95%on MNIST dataset,surpassing state-of-the-art spin-based SNNs by 5%.Our work provides a promising avenue for exploring the SVAM-inspired spiking neuromorphic devices,enhancing the bionic performance of the SNNs.
