An Adaptive Vehicle Detection Model for Traffic Surveillance of Highway Tunnels Considering Luminance Intensity.

Vehicle detection is essential for road traffic surveillance and active safety management. Deep learning methods have recently shown robust feature extraction capabilities and achieved improved detection results. However, vehicle detection models often perform poorly under abnormal lighting conditions, especially in highway tunnels. We proposed an adaptive vehicle detection model that accounts for varying luminance intensities to address this issue. The model categorizes the image data into abnormal and normal luminance scenarios. We employ an improved CycleGAN with edge loss as the adaptive luminance adjustment module for abnormal luminance scenarios. This module adjusts the brightness of the images to a normal level through a generative network. Finally, YOLOv7 is utilized for vehicle detection. The experimental results demonstrate that our adaptive vehicle detection model effectively detects vehicles under abnormal luminance scenarios in highway tunnels. The improved CycleGAN can effectively mitigate edge generation distortion. Under abnormal luminance scenarios, our model achieved a 16.3% improvement in precision, a 1.7% improvement in recall, and a 9.8% improvement in mAP_0.5 compared to the original YOLOv7. Additionally, our adaptive luminance adjustment module is transferable and can enhance the detection accuracy of other vehicle detection models.

Association analysis of indels in the VISFATIN gene with five cattle breeds and their growth traits.

VISFATIN is an adipose cytokine that has been proved to correlate with growth and development traits. In a previous study from our lab, two insertion/deletions (indels; including a 35-bp insertion at its intron 4 and a 6-bp deletion in intron 5) were identified within the VISFATIN gene. To validate these indels and evaluate their association with growth traits in Chinese cattle, a total of 413 samples from four Chinese indigenous breeds and 217 samples from Chinese breeds were detected. Three genotypes (WW, WI and II) at intron 4 were detected based on the 35-bp insertion (allele I) or deletion (allele W) and showed moderate polymorphism in all samples. Two genotypes (WW and WD) at intron 5 were detected based on the 6-bp deletion (allele D) or insertion (allele W) in Xianan (XN) cattle and Jinnan (JN) cattle population but showed poor polymorphisms. Association analysis illustrated that the indel at intron 4 is significantly associated with chest girth, rump length and body weight in Ji'an (JA) cattle and the indel at intron 5 can cause a significant difference in rump length in JN cattle. To our knowledge, it is the first time it has been shown that indels within the VISFATIN gene are associated with growth traits in the two Chinese indigenous cattle breeds. These findings suggest that the VISFATIN gene can be used as a molecular marker for JN and JA cattle breeding.

HMEJ-based safe-harbor genome editing enables efficient generation of cattle with increased resistance to tuberculosis.

The CRISPR/Cas9 system has been used in a wide range of applications in the production of gene-edited animals and plants. Most efforts to insert genes have relied on homology-directed repair (HDR)-mediated integration, but this strategy remains inefficient for the production of gene-edited livestock, especially monotocous species such as cattle. Although efforts have been made to improve HDR efficiency, other strategies have also been proposed to circumvent these challenges. Here we demonstrate that a homology-mediated end-joining (HMEJ)-based method can be used to create gene-edited cattle that displays precise integration of a functional gene at the ROSA26 locus. We found that the HMEJ-based method increased the knock-in efficiency of reporter genes by eightfold relative to the traditional HDR-based method in bovine fetal fibroblasts. Moreover, we identified the bovine homology of the mouse Rosa26 locus that is an accepted genomic safe harbor and produced three live-born gene-edited cattle with higher rates of pregnancy and birth, compared with previous work. These gene-edited cattle exhibited predictable expression of the functional gene natural resistance-associated macrophage protein-1 (NRAMP1), a metal ion transporter that should and, in our experiments does, increase resistance to bovine tuberculosis, one of the most detrimental zoonotic diseases. This research contributes to the establishment of a safe and efficient genome editing system and provides insights for gene-edited animal breeding.