A Water Surface Contaminants Monitoring Method Based on Airborne Depth Reasoning

Abstract

Water surface plastic pollution turns out to be a global issue, having aroused rising attention worldwide. How to monitor water surface plastic waste in real time and accurately collect and analyze the relevant numerical data has become a hotspot in water environment research. (1) Background: Over the past few years, unmanned aerial vehicles (UAVs) have been progressively adopted to conduct studies on the monitoring of water surface plastic waste. On the whole, the monitored data are stored in the UAVS to be subsequently retrieved and analyzed, thereby probably causing the loss of real-time information and hindering the whole monitoring process from being fully automated. (2) Methods: An investigation was conducted on the relationship, function and relevant mechanism between various types of plastic waste in the water surface system. On that basis, this study built a deep learning-based lightweight water surface plastic waste detection model, which was capable of automatically detecting and locating different water surface plastic waste. Moreover, a UAV platform-based edge computing architecture was built. (3) Results: The delay of return task data and UAV energy consumption were effectively reduced, and computing and network resources were optimally allocated. (4) Conclusions: The UAV platform based on airborne depth reasoning is expected to be the mainstream means of water environment monitoring in the future.

Intelligent Grazing UAV Based on Airborne Depth Reasoning

“…Many public datasets have been verified to confirm its accuracy, which is the same as that of the Efficient Det and the YOLOv4, but its model size only takes up 1/10 of the latter two approaches [41]. YOLOv5 with edge computing shall be ideally conducted on UAVs and unmanned ships, as well as other platforms [42]. Such architecture achieved the light-weight onboard operation on the one hand and ensured higher efficiency networks that exhibit larger computational room on the other hand.…”

“…Common attention models are the SE model, ECA model, CBAM model and so on. CBAM is a lightweight convolutional attention model that improves model performance at a fraction of the cost while being easily integrated into the existing network structures [42]. The CBAM model is combined with the two submodels of CAM and SAM, which can generate an attention feature map information in both the channel and space dimensions, and then multiply it with the previous feature map information to adaptively adjust the features and generate a more accurate feature map.…”

An Improved Lightweight Deep Learning Model and Implementation for Track Fastener Defect Detection with Unmanned Aerial Vehicles

“…Due to its low cost, high flexibility, and ease of control, UAV-based detection is widely employed across various fields. For instance, in agriculture, it is utilized for tree detection [27,28]; in transportation, it is employed for vehicle tracking [29,30]; in environmental conservation, it is used for inspections [31]; in industry, it is applied for power facility inspections [32]; and in infrastructure, it is employed for bridge crack inspections [33]. In the field of railway inspection, utilizing UAVs can reduce labor costs, improve efficiency, and enhance safety.…”

A Survey on Applications of Unmanned Aerial Vehicles Using Machine Learning

“…Due to this feature, YOLO is able to achieve a higher detection speed than techniques such as R-CNN or Faster R-CNN [311]. As shown in Table 22, Classification of Maturity of Plantations [312], Fruit Count [313], [314], Tree Counting [280], Land Vehicle Count [315], Aquatic Animal Detection [216], Garbage Detection [316]- [318], Plant Detection [319]- [321], Plant Disease Detection [322], Vehicle Detection [323], [324], Victim Detection [325], Yield Estimate [326], Inspection of Transmission Lines [327], Traffic Monitoring [328], Recognition Electrical Equipment Recognition [329] and Engineering Vehicle Recognition [330] are some of the applications related to the Detection, Recognition or Counting tasks.…”