Abstract：Although YOLOv2 approach is extremely fast on object detection; its backbone network has the low ability on feature extraction and fails to make full use of multi-scale local region features, which restricts the improvement of object detection accuracy. Therefore, this paper proposed a DC-SPP-YOLO (Dense Connection and Spatial Pyramid Pooling Based YOLO) approach for ameliorating the object detection accuracy of YOLOv2. Specifically, the dense connection of convolution layers is employed in the backbone network of YOLOv2 to strengthen the feature extraction and alleviate the vanishing-gradient problem. Moreover, an improved spatial pyramid pooling is introduced to pool and concatenate the multi-scale local region features, so that the network can learn the object features more comprehensively. The DC-SPP-YOLO model is established and trained based on a new loss function composed of mean square error and cross entropy, and the object detection is realized. Experiments demonstrate that the mAP (mean Average Precision) of DC-SPP-YOLO proposed on PASCAL VOC datasets and UA-DETRAC datasets is higher than that of YOLOv2; the object detection accuracy of DC-SPP-YOLO is superior to YOLOv2 by strengthening feature extraction and using the multi-scale local region features.

No abstract

Objective To explore the duration of SARS-CoV-2 remained in the environment of quarantine hotels. Methods 39 Patients by RT-PCR were included. We collected the clinical features, laboratory test results, smear sample information, and quarantine room information. Genome sequencing and phylogenetic analysis were launched. We analyzed the factors associated with environmental contamination. Result Among 39 COVID-19 cases, 10 were asymptomatic and 37 were imported from aboard. 271 swab samples of environmental surfaces related to observational patients were collected. 18 swab samples from 7 patients were positive. The highest contaminated rate occurred in Cup (100%), followed by hand sink (12.82%) and toilet seat and flush (7.89%), telephone (5.56%), bedside table (5.56%), floor drain (5.41%), etc. It showed environmental surface contamination was associated with the clinical cyclical threshold values of patients ( P = 0.01) and the sampling interval time after the cases left the room( P = 0.03). Duration of contamination on environmental surfaces was associated with the wet status of sampling site ( P = 0.01). Conclusion Our findings revealed that environmental contamination might be attributed to the viral load of patients' respiratory tract and the sampling interval time after the cases left the room. Moist surfaces are prone to remain SARS-CoV-2 RNA positive. Our study highlighted the importance of strict strategy to chemical disinfection in the quarantine rooms.

No abstract

No abstract