A detection method of the rescue targets in the marine casualty based on improved YOLOv5s

Abstract

In recent years, with the deep exploitation of marine resources and the development of maritime transportation, ship collision accidents occur frequently, which leads to the increasingly heavy task of maritime Search and Rescue (SAR). Unmanned Aerial Vehicles (UAVs) have the advantages of flexible maneuvering, robust adaptability and extensive monitoring, which have become an essential means and tool for emergency rescue of maritime accidents. However, the current UAVs-based drowning people detection technology has insufficient detection ability and low precision for small targets in high-altitude images. Moreover, limited by the load capacity, UAVs do not have enough computing power and storage space, resulting in the existing object detection algorithms based on deep learning cannot be directly deployed on UAVs. To solve the two issues mentioned above, this paper proposes a lightweight deep learning detection model based on YOLOv5s, which is used in the SAR task of drowning people of UAVs at sea. First, an extended small object detection layer is added to improve the detection effect of small objects, including the extraction of shallow features, a new feature fusion layer and one more prediction head. Then, the Ghost module and the C3Ghost module are used to replace the Conv module and the C3 module in YOLOv5s, which enable lightweight network improvements that make the model more suitable for deployment on UAVs. The experimental results indicate that the improved model can effectively identify the rescue targets in the marine casualty. Specifically, compared with the original YOLOv5s, the improved model mAP@0.5 value increased by 2.3% and the mAP@0.5:0.95 value increased by 1.1%. Meanwhile, the improved model meets the needs of the lightweight model. Specifically, compared with the original YOLOv5s, the parameters decreased by 44.9%, the model weight size compressed by 39.4%, and Floating Point Operations (FLOPs) reduced by 22.8%.

Applications, Evolutions, and Challenges of Drones in Maritime Transport

“…Secondly, the processors carried by drones are typically small in size and possess limited computing power. Therefore, it is crucial to develop lightweight vision algorithms that can operate efficiently on these processors without compromising detection quality or speed [127,128]. The focus should be on optimising algorithms to ensure optimal performance with limited computing resources.…”

“…(2) Visual technology plays a primary role in drones' involvement in rescue operations by locating injured individuals. Nevertheless, maritime environments are frequently affected by adverse weather conditions such as rain and fog, which can impede visual detection efforts [127]. To overcome this challenge, there is a need for radar-equipped drones capable of penetrating clouds and rain to swiftly identify the location of targets [130].…”

SenseLite: A YOLO-Based Lightweight Model for Small Object Detection in Aerial Imagery

“…The model leverages efficient spatial pyramid pooling (ESPP) to emphasize small object feature subtleties. Moreover, it integrates an α-CIoU loss method to mitigate the bias between favorable and unfavorable samples in skyborne images [12]. Zhao, Lei, and their team proposed an innovative and lightweight method for spotting objects in aerial images, LAI-YOLOv5s, which demonstrated both high accuracy and reduced computational demands [13].…”

Low Contrast Challenge and Limitations of Thermal Drones in Maritime Search and Rescue—Pilot Study

“…At a temperature of 4.5 • C, a person can survive in water for less than an hour (Table 1). Therefore, there is a clear need for fast, reliable, and efficient systems for victim detection and verification during SAR operations [20,21]. Table 1.…”