ABSTRACT
4D millimeter wave (mmWave) imaging radar is a new type of vehicle sensor technology that is critical to autonomous driving systems due to its lower cost and robustness in complex weather. However, the sparseness and noise of point clouds are still the main problems restricting the practical application of 4D imaging radar. In this paper, we introduce SMIFormer, a multi-view feature fusion network framework based on 4D radar single-modal input. SMIFormer decouples the 3D point cloud scene into 3 independent but interrelated perspectives, including bird's-eye view (BEV), front view (FV), and side view (SV), thereby better modeling the entire 3D scene and overcoming the shortcomings of insufficient feature representation capabilities under single-view built from extremely sparse point clouds. For multi-view features, we proposed multi-view feature interaction (MVI) to exploit the inner relationship between different views by integrating features from intra-view interaction and cross-view interaction. We evaluated the proposed SMIFormer on the View-of-Delft (VoD) dataset. The mAP of our method reached 48.77 and 71.13 in the fully annotated area and the driving corridor area, respectively. This shows that 4D radar has great development potential in the field of 3D object detection.
ABSTRACT
The aims of this study were to design the formulation of curcumin (CUR) liposomes coated with N-trimethyl chitosan chloride (TMC) and to evaluate in vitro release characteristics and in vivo pharmacokinetics and bioavailability of TMC-coated CUR liposomes in rats. The structure of synthesized TMC was examined by infrared spectroscopy, with the presence of trimethyl groups, and by proton nuclear magnetic resonance spectroscopy, indicating the high degree of substitution quaternization (65.6%). Liposomes, composed of soybean phosphotidylcholine, cholestrol, and D-α-tocopheryl polyethylene glycol 1000 succinate, were prepared by a thin-film dispersion method. Characteristics of the CUR liposomes, including entrapment efficiency (86.67%), drug-loading efficiency (2.33%), morphology, particle size (221.4 nm for uncoated liposomes and 657.7 nm for TMC-coated liposomes), and zeta potential (-9.63 mV for uncoated liposomes and +15.64 mV for TMC-coated liposomes) were investigated. Uncoated CUR liposomes and TMC-coated CUR liposomes showed a similar in vitro release profile. Nearly 50% of CUR was released from liposomes, whereas 80% of CUR was released from CUR propylene glycol solution. CUR incorporated into TMC-coated liposomes exhibited different pharmacokinetic parameters and enhanced bioavailability (C(max) = 46.13 µg/L, t(1/2) = 12.05 hours, AUC = 416.58 µg/L·h), compared with CUR encapsulated by uncoated liposomes (C(max) = 32.12 µg/L, t(1/2) = 9.79 hours, AUC = 263.77 µg/L·h) and CUR suspension (C(max) = 35.46 µg/L, t(1/2) = 3.85 hours, AUC = 244.77 µg/L·h). In conclusion, oral delivery of coated CUR liposomes is a promising strategy for poorly water-soluble CUR.
