Search

Vehicle detection and tracking from unmanned aerial vehicles (UAVs) aerial images are among the main tasks of intelligent traffic systems. Especially in tasks with long distances, extensive backgrounds, and small objects, it increases the difficulty of localization and regression, which can easily lead to missed detections and false positives. This paper proposes a detection-based small-scale vehicle tracking framework that integrates an improved YOLOX network and the DeepSORT algorithm to address these issues. Based on the original YOLOX network, a shallow feature extraction network, 160×160 pixels, is added to enhance the ability to extract small-scale object features. A convolutional block attention module (CBAM) is inserted in front of the neck network to select crucial information for vehicle detection tasks while suppressing noncritical ones. EIoU_Loss is introduced as the bounding box regression loss function in training to speed up their convergence and improve the localization accuracy of the small objects. Furthermore, an image segmentation method is proposed to effectively reduce missed and false detection events. It divides the original high-definition image into multiple subimages, first detected and then reassembled. Finally, the improved YOLOX network is used as the detector of the DeepSORT to perform small-scale vehicle detection and tracking tasks in various traffic scenarios. Experiments show that the proposed method can significantly improve the detection accuracy of the network and effectively solve the problems of missed detection and false positives in small-scale vehicle tracking tasks in high-resolution aerial images captured by high-altitude UAVs. Significantly, the algorithm proposed in this paper has sufficient robustness for small-scale tracking tasks of aerial videos captured at different altitudes., Author(s): Heshan Zhang [1]; Xin Tan [1]; Mengwei Fan [1]; Cunshu Pan [1]; Zhanji Zheng [1]; Shuang Luo [1]; Jin Xu (corresponding author) [1] 1. Introduction With the rapid development [...]

Although organic amendment has been widely accepted to be capable of facilitating soil agglomeration in coastal salt-affected soils, quantitative characterization with respect to how abiotic and biotic components drive the formation and stabilization of soil aggregates remains largely unexplored and poorly understood. In the current study, wet-sieving, Miseq sequencing, etc., were employed to study the impacts of different application amounts of sewage sludge on soil aggregates, physicochemical properties, enzyme activities, and microbial core microbiomes in coastal saline soils. The results indicated that sewage sludge was conducive to soil agglomeration, abiotic constraint alleviation, microbial activity enhancement, and bacterial and fungal community stabilization and functionalization. The results derived from variation partitioning analysis and the structural equation model showed that elevated soil organic carbon and mitigated salinization were dominant abiotic factors that directly drove the stabilization and functionalization of bacterial and fungal microbiomes. In addition, bacterial families (e.g., Xanthomonadaceae, Rhodospirillaceae, and Micrococcaceae) and fungal genera (e.g., Trichoderma, Cephaliophora, Mortierella, and Penicillium) were potential functional microbial populations related to soil agglomeration in organic amended coastal salt-affected soils. Together, these abiotic and biotic agents jointly drove soil agglomeration and totally explained 87% of the variations in soil aggregates. Collectively, this study highlighted the approach and effectiveness of the impacts of organic amendment on soil agglomeration in coastal salt-affected land based on qualitative and quantitative analysis, which would enhance our knowledge with respect to coastal salt-affected soil quality indication and development. [ABSTRACT FROM AUTHOR]