No abstract

The object detection and recognition algorithm based on the fusion of millimeter-wave radar and high-definition video data can improve the safety of intelligent-driving vehicles effectively. However, due to the different data modalities of millimeter-wave radar and video, how to fuse the two effectively is the key point. The difficulty lies in the data fusion methods such as insufficient adaptability of image distortion in data alignment and coordinate transformation and also the mismatching of information levels of the data to be fused. To solve the problem of data fusion of millimeter wave radar and video, this paper proposes a decision-level fusion method of millimeter-wave radar and high-definition video data based on angular alignment. Specifically, through the joint calibration and approximate interpolation, projected to polar coordinate system, the radar and the camera are angularly aligned in the horizontal direction. Then objects are detected by a deep neural network model from video data, and combined with those detected by radar to make the joint decision. Finally, object detection and recognition task based on the fusion of the two kinds of data is completed. Theoretical analysis and experimental results indicate that the accuracy of the algorithm based on the two data fusion is superior to that of the single detection and recognition algorithm on the basis of millimeter-wave radar or video data.

Background Large-dose melatonin treatment in animal experiments was hardly translated into humans, which may explain the dilemma that the protective effects against myocardial injury in animal have been challenged by clinical trials. Ultrasound-targeted microbubble destruction (UTMD) has been considered a promising drug and gene delivery system to the target tissue. We aim to investigate whether cardiac gene delivery of melatonin receptor mediated by UTMD technology optimizes the efficacy of clinically equivalent dose of melatonin in sepsis-induced cardiomyopathy. Methods Melatonin and cardiac melatonin receptors in patients and rat models with lipopolysaccharide (LPS)- or cecal ligation and puncture (CLP)-induced sepsis were assessed. Rats received UTMD-mediated cardiac delivery of RORα/cationic microbubbles (CMBs) at 1, 3 and 5 days before CLP surgery. Echocardiography, histopathology and oxylipin metabolomics were assessed at 16–20 h after inducing fatal sepsis. Results We observed that patients with sepsis have lower serum melatonin than healthy controls, which was observed in the blood and hearts of Sprague–Dawley rat models with LPS- or CLP-induced sepsis. Notably, a mild dose (2.5 mg/kg) of intravenous melatonin did not substantially improve septic cardiomyopathy. We found decreased nuclear receptors RORα, not melatonin receptors MT1/2, under lethal sepsis that may weaken the potential benefits of a mild dose of melatonin treatment. In vivo, repeated UTMD-mediated cardiac delivery of RORα/CMBs exhibited favorable biosafety, efficiency and specificity, significantly strengthening the effects of a safe dose of melatonin on heart dysfunction and myocardial injury in septic rats. The cardiac delivery of RORα by UTMD technology and melatonin treatment improved mitochondrial dysfunction and oxylipin profiles, although there was no significant influence on systemic inflammation. Conclusions These findings provide new insights to explain the suboptimal effect of melatonin use in clinic and potential solutions to overcome the challenges. UTMD technology may be a promisingly interdisciplinary pattern against sepsis-induced cardiomyopathy.

No abstract