As affected by limited information and the complex background, the accuracy of small-target water-floating garbage detection is low. To increase the detection accuracy, in this research, a small-target detection method based on APM-YOLOv7 (the improved YOLOv7 with ACanny PConv-ELAN and MGA attention) is proposed. Firstly, the adaptive algorithm ACanny (adaptive Canny) for river channel outline extraction is proposed to extract the river channel information from the complex background, mitigating interference of the complex background and more accurately extracting the features of small-target water-floating garbage. Secondly, the lightweight partial convolution (PConv) is introduced, and the partial convolution-efficient layer aggregation network module (PConv-ELAN) is designed in the YOLOv7 network to improve the feature extraction capability of the model from morphologically variable water-floating garbage. Finally, after analyzing the limitations of the YOLOv7 network in small-target detection, a multi-scale gated attention for adaptive weight allocation (MGA) is put forward, which highlights features of small-target garbage and decreases missed detection probability. The experimental results showed that compared with the benchmark YOLOv7, the detection accuracy in the form of the mean Average Precision (mAP) of APM-YOLOv7 was improved by 7.02%, that of mmAP (mAP0.5:0.95) was improved by 3.91%, and Recall was improved by 11.82%, all of which meet the requirements of high-precision and real-time water-floating garbage detection and provide reliable reference for the intelligent management of water-floating garbage.

Typically, the process of visual tracking and position prediction of floating garbage on water surfaces is significantly affected by illumination, water waves, or complex backgrounds, consequently lowering the localization accuracy of small targets. Herein, we propose a small-target localization method based on the neurobiological phenomenon of lateral inhibition (LI), discrete wavelet transform (DWT), and a parameter-designed fire-controlled modified simplified pulse-coupled neural network (PD-FC-MSPCNN) to track water-floating garbage floating. First, a network simulating LI is fused with the DWT to derive a denoising preprocessing algorithm that effectively reduces the interference of image noise and enhances target edge features. Subsequently, a new PD-FC-MSPCNN network is developed to improve the image segmentation accuracy, and an adaptive fine-tuned dynamic threshold magnitude parameter $V$ and auxiliary parameter $P$ are newly designed, while eliminating the link strength parameter. Finally, a multiscale morphological filtering postprocessing algorithm is developed to connect the edge contour breakpoints of segmented targets, smoothen the segmentation results, and improve the localization accuracy. An effective computer vision technology approach is adopted for the accurate localization and intelligent monitoring of water-floating garbage. The experimental results demonstrate that the proposed method outperforms other methods in terms of the overall comprehensive evaluation indexes, suggesting higher accuracy and reliability.