Multi-Scale Object Detection Model for Autonomous Ship Navigation in Maritime Environment

Abstract

Accurate detection of sea-surface objects is vital for the safe navigation of autonomous ships. With the continuous development of artificial intelligence, electro-optical (EO) sensors such as video cameras are used to supplement marine radar to improve the detection of objects that produce weak radar signals and small sizes. In this study, we propose an enhanced convolutional neural network (CNN) named VarifocalNet* that improves object detection in harsh maritime environments. Specifically, the feature representation and learning ability of the VarifocalNet model are improved by using a deformable convolution module, redesigning the loss function, introducing a soft non-maximum suppression algorithm, and incorporating multi-scale prediction methods. These strategies improve the accuracy and reliability of our CNN-based detection results under complex sea conditions, such as in turbulent waves, sea fog, and water reflection. Experimental results under different maritime conditions show that our method significantly outperforms similar methods (such as SSD, YOLOv3, RetinaNet, Faster R-CNN, Cascade R-CNN) in terms of the detection accuracy and robustness for small objects. The maritime obstacle detection results were obtained under harsh imaging conditions to demonstrate the performance of our network model.

Detection Technique Tailored for Small Targets on Water Surfaces in Unmanned Vessel Scenarios

“…Quantitatively, Table 4 emphasizes the enhancements of our method compared to Leveraging a proprietary dataset, we assess the viability of the proposed network enhancements and their effectiveness in detecting surface vessels. Precision and recall curves are depicted in Figures 10 and 11, while Figure 12 showcases the convergence curve for the mAP metric [22]. Figure 14 tracks the evolution of loss values during the training process.…”

“…Classic two-stage object detection algorithms like Faster R-CNN [6] and single-stage algorithms like SSD [11] have demonstrated good performance in terms of both accuracy and speed. Two-stage methods have introduced several improved algorithms addressing small target issues [12][13][14][15][16][17][18][19][20][21][22][23], while single-stage improvements [24][25][26] mainly focus on leveraging multi-scale feature fusion to fully utilize detailed information in low-level, high-resolution features. Additionally, techniques such as generative adversarial networks [27][28][29] and data augmentation [30,31] are employed to address small detection challenges.…”

Designing a Ship Autopilot System for Operation in a Disturbed Environment Using the Adaptive Neural Fuzzy Inference System

“…In this study, the proposed neural-fuzzy controller is a neural-fuzzy system based on Takagi and Sugeno's Approach. It is also an Adaptive Neuro-Fuzzy Inference System (ANFIS) [24][25][26][27][28][29][30][31][32][33]. The proposed controller has two inputs, I 1 and I 2 , and one output:…”

“…Layers 3, 4, and 5 all have 9 nodes, and, finally, layer 6 consists of 1 node that synthesizes the output signals from layer 5. The ith control law of the ANFIS [24][25][26][27][28][29][30][31][32][33] controller: According to the first-order Takagi-Sugeno model of fuzzy logic control: 𝑦 = 𝑎 𝐼 + 𝑏 𝐼 + 𝑐 (17) where: i = 1, 2, …, 9. 𝑎 , 𝑏 , 𝑐 are coefficients.…”

“…The distribution of the membership function of the input and output variables is shown in Figure 5. The ith control law of the ANFIS [24][25][26][27][28][29][30][31][32][33] controller: According to the first-order Takagi-Sugeno model of fuzzy logic control:…”