In this research, E2YOLOX-VFL is proposed as a novel approach to address the challenges of optical image multi-scale ship detection and recognition in complex maritime and land backgrounds. Firstly, the typical anchor-free network YOLOX is utilized as the baseline network for ship detection. Secondly, the Efficient Channel Attention module is incorporated into the YOLOX Backbone network to enhance the model’s capability to extract information from objects of different scales, such as large, medium, and small, thus improving ship detection performance in complex backgrounds. Thirdly, we propose the Efficient Force-IoU (EFIoU) Loss function as a replacement for the Intersection over Union (IoU) Loss, addressing the issue whereby IoU Loss only considers the intersection and union between the ground truth boxes and the predicted boxes, without taking into account the size and position of targets. This also considers the disadvantageous effects of low-quality samples, resulting in inaccuracies in measuring target similarity, and improves the regression performance of the algorithm. Fourthly, the confidence loss function is improved. Specifically, Varifocal Loss is employed instead of CE Loss, effectively handling the positive and negative sample imbalance, challenging samples, and class imbalance, enhancing the overall detection performance of the model. Then, we propose Balanced Gaussian NMS (BG-NMS) to solve the problem of missed detection caused by the occlusion of dense targets. Finally, the E2YOLOX-VFL algorithm is tested on the HRSC2016 dataset, achieving a 9.28% improvement in mAP compared to the baseline YOLOX algorithm. Moreover, the detection performance using BG-NMS is also analyzed, and the experimental results validate the effectiveness of the E2YOLOX-VFL algorithm.

Drone aerial videos offer a promising future in modern digital media and remote sensing applications, but effectively tracking several objects in these recordings is difficult. Drone aerial footage typically includes complicated sceneries with moving objects, such as people, vehicles, and animals. Complicated scenarios such as large-scale viewing angle shifts and object crossings may occur simultaneously. Random finite sets are mixed in a detection-based tracking framework, taking the object’s location and appearance into account. It maintains the detection box information of the detected object and constructs the Box-MeMBer object position prediction framework based on the MeMBer random finite set point object tracking. We develop a hierarchical connection structure in the OSNet network, build MB-OSNet to get the object appearance information, and connect feature maps of different levels through the hierarchy such that the network may obtain rich semantic information at different sizes. Similarity measurements are computed and collected for all detections and trajectories in a cost matrix that estimates the likelihood of all possible matches. The cost matrix entries compare the similarity of tracks and detections in terms of position and appearance. The DB-Tracker algorithm performs excellently in multi-target tracking of drone aerial videos, achieving MOTA of 37.4% and 46.2% on the VisDrone and UAVDT data sets, respectively. DB-Tracker achieves high robustness by comprehensively considering the object position and appearance information, especially in handling complex scenes and target occlusion. This makes DB-Tracker a powerful tool in challenging applications such as drone aerial videos.

Ship detection from optical remote sensing images remains challenging due to cluttered sea–land backgrounds, large scale variations, low-contrast small targets, and dense ship occlusion. Existing detectors struggle to balance global modeling capability, detection precision, and computational efficiency. This paper proposes a Mamba-enhanced Real-Time Detection Transformer (RT-DETR) framework for high-precision ship detection and identification. First, a Mamba-based Deformable Spatial Attention (Mamba-DSA) backbone is proposed to integrate linear-time state-space feature modeling and deformable spatial attention, which strengthens ship-specific feature representation and suppresses background interference. Second, a Context-Guided Spatial Feature Reconstruction Feature Pyramid Network (CGRFPN) is designed to enhance multi-scale context awareness and rectangular region calibration, effectively reducing missed detections in dense ship scenes. Third, a Spatial-to-Depth Depthwise Convolution (SPD-DWConv) module is developed to enhance small-target features without introducing excessive computation overhead. Experiments on HRSC2016, NWPU VHR-10, and DOTA-v1.5 datasets show that the proposed method outperforms the baseline RT-DETR by 9.0% in precision, 16.5% in recall, 19.0% in mAP@50, and 14.1% in mAP@50:95. The proposed method achieves strong robustness and efficiency, showing high practical value for maritime monitoring, port security, and emergency response.