Quantifying Marine Macro Litter Abundance on a Sandy Beach Using Unmanned Aerial Systems and Object-Oriented Machine Learning Methods

Abstract

Unmanned aerial systems (UASs) have recently been proven to be valuable remote sensing tools for detecting marine macro litter (MML), with the potential of supporting pollution monitoring programs on coasts. Very low altitude images, acquired with a low-cost RGB camera onboard a UAS on a sandy beach, were used to characterize the abundance of stranded macro litter. We developed an object-oriented classification strategy for automatically identifying the marine macro litter items on a UAS-based orthomosaic. A comparison is presented among three automated object-oriented machine learning (OOML) techniques, namely random forest (RF), support vector machine (SVM), and k-nearest neighbor (KNN). Overall, the detection was satisfactory for the three techniques, with mean F-scores of 65% for KNN, 68% for SVM, and 72% for RF. A comparison with manual detection showed that the RF technique was the most accurate OOML macro litter detector, as it returned the best overall detection quality (F-score) with the lowest number of false positives. Because the number of tuning parameters varied among the three automated machine learning techniques and considering that the three generated abundance maps correlated similarly with the abundance map produced manually, the simplest KNN classifier was preferred to the more complex RF. This work contributes to advances in remote sensing marine litter surveys on coasts, optimizing the automated detection on UAS-derived orthomosaics. MML abundance maps, produced by UAS surveys, assist coastal managers and authorities through environmental pollution monitoring programs. In addition, they contribute to search and evaluation of the mitigation measures and improve clean-up operations on coastal environments.

A Citizen Science Unmanned Aerial System Data Acquisition Protocol and Deep Learning Techniques for the Automatic Detection and Mapping of Marine Litter Concentrations in the Coastal Zone

“…Monitoring programs have been implemented to map, spatially and temporally, the load and type of marine litter on beaches worldwide [2,[16][17][18][19][20]. State-of-the-art techniques were examined to detect and quantify floating marine litter [21][22][23][24][25][26][27][28].…”

Quantifying Floating Plastic Debris at Sea Using Vessel-Based Optical Data and Artificial Intelligence

“…This relatively new approach has seen recent successful developments on several applications. For example, unmanned aerial vehicles (UAVs) or airplanes equipped with optical cameras have successfully been used to quantify litter on beaches [19][20][21][22][23]. The mapping of floating litter is further pioneered by photography from airplanes [10,24] or satellite detection of large accumulated patches [25][26][27][28][29][30].…”

An Efficient Deep-Sea Debris Detection Method Using Deep Neural Networks

“…For now, some studies have been carried out around the classification and detection of marine debris. Traditional machine learning algorithms were used to classify marine plastic garbage on the beach [5]. A reversed linear spectral unmixing methodology has been applied to the detection of garbage floating in the ocean [6].…”