Fusing information from LiDAR and cameras can effectively enhance the overall perceptivity of autonomous vehicles in various scenarios. Despite the relatively good results achieved by point-wise fusion and Bird's-Eye-View (BEV) fusion, they still cannot fully leverage the image information and lack of effective depth information. For any fusion methods, the multi-modal features first need to be concatenated along the channel, and then the fused features are extracted using convolutional layers.
View Article and Find Full Text PDFIn this paper, a novel direction-of-arrival (DOA) estimation for unknown (anonymous) emitter signal (ES) based on time reversal (TR) and coprime array (CA) is proposed. The resolution and accuracy of DOA estimation are enhanced from two aspects: one is from the view of array arrangement: the new distribution of CA is designed to reduce the holes, increase the degree of freedom (DOF) and apertures by rotating and translating only one subarray, which simplifies the operation. The other one is from the view of the algorithm: a neoteric DOA estimation algorithm with noise suppression based on TR, Capon and adaptive neuro-fuzzy inference system (ANFIS) is proposed for solving the wide sidelobe, multipath effect, low resolution and accuracy produced by conventional algorithms, in particular, those cannot work effectively under the existed hole condition.
View Article and Find Full Text PDFObjective: To study the depletion of cardiac troponin T in Rats of early myocardial ischaemia.
Methods: Immunohistochemical method (LSAB) was used and the depletion area of CTnT in myocardial ischaemia were measured by the computer image analysis.
Results: There is obviously depletion of CTnT after 15 min in myocardial ischaemia of rats, the mean of CTnT depletion of myocardial ischaemic group is significant difference compared with that of the control group (P < 0.