A Detection Approach for Floating Debris Using Ground Images Based on Deep Learning

Abstract

Floating debris has a negative impact on the quality of the water as well as the aesthetics of surface waters. Traditional image processing techniques struggle to adapt to the complexity of water due to factors such as complex lighting conditions, significant scale disparities between far and near objects, and the abundance of small-scale floating debris in real existence. This makes the detection of floating debris extremely difficult. This study proposed a brand-new, effective floating debris detection approach based on YOLOv5. Specifically, the coordinate attention module is added into the YOLOv5 backbone network to help the model detect and recognize objects of interest more precisely so that feature information of small-sized and dense floating debris may be efficiently extracted. The previous feature pyramid network, on the other hand, summarizes the input features without taking into account their individual importance when fusing features. To address this issue, the YOLOv5 feature pyramidal network is changed to a bidirectional feature pyramid network with effective bidirectional cross-scale connection and weighted feature fusion, which enhances the model’s performance in terms of feature extraction. The method has been evaluated using a dataset of floating debris that we built ourselves (SWFD). Experiments show that the proposed method detects floating objects more precisely than earlier methods.

The Use of UAV for Measuring the Morphology of Ice Cover on the Surface of a River: A Case Study of the Low Head Dam and Fishway Inlet Area in the Odra River

“…The acquired image was taken in an orthogonal view, which is optimal for minimizing distortions caused by the perspective effect. However, studies (e.g., [33,34,[48][49][50]) indicate that this is not a necessary condition, and it is possible to obtain reliable results without orthorectification. Utilizing cameras permanently installed in the technical infrastructure of a facility is possible.…”

YOLOv5-FF: Detecting Floating Objects on the Surface of Fresh Water Environments

“…We conduct experiments to evaluate the detection accuracy and speed of YOLOv5-FF by comparing YOLOv5-FF with several important object detection solutions including the two lightest versions of YOLOv8 [32], i.e., YOLOv8n and YOLOv8s, YOLOv7 [33], YOLOv5 [26], YOLOX [34], YOLOv4 [35], YOLOv3 [36], SSD [37], Faster-RCNN [38] and YOLOv5-CB [39]. Faster-RCNN is a two-stage detection solution, while all the other solutions are single-stage detection solutions.…”

EC-YOLOX: A Deep-Learning Algorithm for Floating Objects Detection in Ground Images of Complex Water Environments

“…Finally, in the classification recognition stage, traditional image processing employs Support Vector Machines (SVM) or clustering methods to classify and recognize the extracted features, thereby accomplishing tasks such as detection, recognition, and tracking of the target [6], [7], [40]. However, traditional classifiers are typically based on artificial features and shallow models, making them less capable of handling complex image features and scenarios, and they often yield unsatisfactory results when dealing with non-linear problems [41].…”