An Adaptive Multi-Scale Network Based on Depth Information for Crowd Counting.

Crowd counting, as a basic computer vision task, plays an important role in many fields such as video surveillance, accident prediction, public security, and intelligent transportation. At present, crowd counting tasks face various challenges. Firstly, due to the diversity of crowd distribution and increasing population density, there is a phenomenon of large-scale crowd aggregation in public places, sports stadiums, and stations, resulting in very serious occlusion. Secondly, when annotating large-scale datasets, positioning errors can also easily affect training results. In addition, the size of human head targets in dense images is not consistent, making it difficult to identify both near and far targets using only one network simultaneously. The existing crowd counting methods mainly use density plot regression methods. However, this framework does not distinguish the features between distant and near targets and cannot adaptively respond to scale changes. Therefore, the detection performance in areas with sparse population distribution is not good. To solve such problems, we propose an adaptive multi-scale far and near distance network based on the convolutional neural network (CNN) framework for counting dense populations and achieving a good balance between accuracy, inference speed, and performance. However, on the feature level, in order to enable the model to distinguish the differences between near and far features, we use stacked convolution layers to deepen the depth of the network, allocate different receptive fields according to the distance between the target and the camera, and fuse the features between nearby targets to enhance the feature extraction ability of pedestrians under nearby targets. Secondly, depth information is used to distinguish distant and near targets of different scales and the original image is cut into four different patches to perform pixel-level adaptive modeling on the population. In addition, we add density normalized average precision (nAP) indicators to analyze the accuracy of our method in spatial positioning. This paper validates the effectiveness of NF-Net on three challenging benchmarks in Shanghai Tech Part A and B, UCF_ CC_50, and UCF-QNRF datasets. Compared with SOTA, it has more significant performance in various scenarios. In the UCF-QNRF dataset, it is further validated that our method effectively solves the interference of complex backgrounds.

Effect of Fibronectin-Coated Micro-Grooved Titanium Surface on Alignment, Adhesion, and Proliferation of Human Gingival Fibroblasts.

BACKGROUND Surface characters of culture plates affect cellular behaviors such as cellular alignment and elongation. Microgrooves guide the cell growth along the grooves and spread. The aim of this study was to observe the effect of fibronectin (FN)-coated micro-grooved titanium plates on the alignment, spread, adhesion, and proliferation of human gingival fibroblasts (HGFs). MATERIAL AND METHODS Micro-grooved titanium plates were fabricated, and FN was immobilized onto the micro-grooved surfaces using silanization. HGFs were cultured on the smoothed or micro-grooved (with 35 µm width, 15 µm bridge, 10 µm depth) titanium plates, with or without the FN coating. We assessed the water contact angle and blood compatibility of the surfaces, and the earlier adhesion, adhesion strength, proliferation and morphology of the cells growing on the different titanium surfaces. RESULTS The results revealed that the blood hemolysis rates of different titanium surfaces were within the safety limits. HGFs aligned along the grooves, spread out more evidently, and showed significantly more adhesion in the FN-coated micro-grooved surface compared with other surfaces (p<0.05). CONCLUSIONS The micro-grooved surface coated with FN guides the HGFs to align along the grooves, and promotes cell spread, adhesion and proliferation, which might be used to improve the efficacy of dental implants.

GL13K-modified titanium regulates osteogenic differentiation via the NF-κB pathway.

The osteoimmune response plays a crucial regulatory role in the osseointegration of dental implants. Previous studies found the antimicrobial peptide coating (GL13K) could activate the immunomodulatory potential of macrophages (Raw 264.7) and promote osteogenic differentiation of bone marrow mesenchymal stem cells (BMSCs). To further investigate the mechanism of interaction between immunomodulation and differentiation, a co-culture model of the representative cells (Raw 264.7 and BMSCs) was constructed to mimic the immune microenvironment. In this system, GL13K coating of titanium implant effectively inhibited the polarization of the inflammatory M1 type and promoted the polarization of the anti-inflammatory M2 type. Furthermore, the inhibited NF-κB signaling pathway and Mip-2 gene expression were found and validated by bioinformatics analysis and virus-induced gene silencing, which significantly affected the tissue repair process. It can be concluded that the GL13K coating had the potential to establish a localized immune microenvironment conducive to osteogenic differentiation through cellular interactions. Subsequent investigations would be dedicated to a thorough examination of the osseointegration effects of GL13K coating.

Inflammatory and biocompatibility evaluation of antimicrobial peptide GL13K immobilized onto titanium by silanization.

The inflammatory reaction around the implant after implant placement is important not only for osseointegration but also for long-term implant survivals. In our study, GL13K, an antimicrobial peptide, was immobilized onto titanium surfaces to improve its anti-inflammatory properties. The method of silanization was used to immobilize the GL13K, which was confirmed by X-ray photoelectron spectroscopy, scanning electron microscopy, atomic force microscopy, water contact angle measurement. DAPI fluorescence staining and Cell Counting Kit-8 (CCK-8) were used to measure the cell attachment and cell viability of the RAW264.7, which indicated a good cytocompatibility. Cellular morphology of RAW264.7 on modified surfaces showed less cell pseudopod. ELISA and qRT-PCR were performed to measure the inflammatory activity of the modified titanium surfaces. The secretion levels of pro-inflammatory cytokines interleukin (IL)-1ß, tumor necrosis factor-alpha (TNF-α) and inducible nitric oxide synthase (iNOS) were downregulated at 12h, 24h, and 48h, while the anti-inflammatory cytokines IL-10 and arginase were upregulated at 12h, 24h, and 48h. All results indicate that the GL13K-coated titanium surfaces make the inflammatory process towards a less pro-inflammatory, which may promote the process of osseointegration.