The detection of small objects in aerial images is a fundamental task in the
field of computer vision. Moving objects in aerial photography have problems
such as different shapes and sizes, dense overlap, occlusion by the background,
and object blur, however, the original YOLO algorithm has low overall detection
accuracy due to its weak ability to perceive targets of different scales. In
order to improve the detection accuracy of densely overlapping small targets
and fuzzy targets, this paper proposes a dynamic-attention scale-sequence
fusion algorithm (DASSF) for small target detection in aerial images. First, we
propose a dynamic scale sequence feature fusion (DSSFF) module that improves
the up-sampling mechanism and reduces computational load. Secondly, a x-small
object detection head is specially added to enhance the detection capability of
small targets. Finally, in order to improve the expressive ability of targets
of different types and sizes, we use the dynamic head (DyHead). The model we
proposed solves the problem of small target detection in aerial images and can
be applied to multiple different versions of the YOLO algorithm, which is
universal. Experimental results show that when the DASSF method is applied to
YOLOv8, compared to YOLOv8n, on the VisDrone-2019 and DIOR datasets, the model
shows an increase of 9.2% and 2.4% in the mean average precision (mAP),
respectively, and outperforms the current mainstream methods.

本文提出了一种适用于航拍图像中小目标检测的动态注意力尺度序列融合算法 (DASSF)，通过改进 YOLO 算法的能力以感知不同尺度的目标来提高密集重叠小目标和模糊目标的检测精度。实验结果表明，在 VisDrone-2019 和 DIOR 数据集上，将 DASSF 方法应用于 YOLOv8 时，与 YOLOv8n 相比，模型的平均精度 (mean average precision) 分别提高了 9.2% 和 2.4%，超过了当前主流方法。

DASSF：用于航空目标检测的动态注意力尺度序列融合

DASSF: Dynamic-Attention Scale-Sequence Fusion for Aerial Object  Detection

You Only Look Once (YOLO) algorithm is a representative target detection
algorithm emerging in 2016, which is known for its balance of computing speed
and accuracy, and now plays an important role in various fields of human
production and life. However, there are still many limitations in the
application of YOLO algorithm in underwater environments due to problems such
as dim light and turbid water. With limited land area resources, the ocean must
have great potential for future human development. In this paper, starting from
the actual needs of marine engineering applications, taking underwater
structural health monitoring (SHM) and underwater biological detection as
examples, we propose improved methods for the application of underwater YOLO
algorithms, and point out the problems that still exist.

YOLO 算法在水下环境中的应用存在限制，本文从海洋工程应用的实际需求出发，以水下结构健康监测和水下生物检测为例，提出了改进的水下 YOLO 算法应用方法，并指出了仍然存在的问题。

YOLO 系列水下环境目标检测算法

YOLO series target detection algorithms for underwater environments

Overtaking is a critical maneuver in driving that requires accurate
information about the location and distance of other vehicles on the road. This
study suggests a real-time overtaking assistance system that uses a combination
of the You Only Look Once (YOLO) object detection algorithm and stereo vision
techniques to accurately identify and locate vehicles in front of the driver,
and estimate their distance. The system then signals the vehicles behind the
driver using colored lights to inform them of the safe overtaking distance. The
proposed system has been implemented using Stereo vision for distance analysis
and You Only Look Once (YOLO) for object identification. The results
demonstrate its effectiveness in providing vehicle type and the distance
between the camera module and the vehicle accurately with an approximate error
of 4.107%. Our system has the potential to reduce the risk of accidents and
improve the safety of overtaking maneuvers, especially on busy highways and
roads.

本研究提出了一种可以实时辅助驾驶员超车的系统，结合 YOLO 算法和立体视觉技术精确识别和定位前方车辆并估算其距离，再使用彩色灯光通知后续车辆安全超车距离，实验结果表明该系统精度可达误差率 4.107％，具有减少事故风险，提高道路行车安全的潜力。