Underwater Target Detection Based on Improved YOLOv7

Abstract

Underwater target detection is a crucial aspect of ocean exploration. However, conventional underwater target detection methods face several challenges such as inaccurate feature extraction, slow detection speed, and lack of robustness in complex underwater environments. To address these limitations, this study proposes an improved YOLOv7 network (YOLOv7-AC) for underwater target detection. The proposed network utilizes an ACmixBlock module to replace the 3 × 3 convolution block in the E-ELAN structure, and incorporates jump connections and 1 × 1 convolution architecture between ACmixBlock modules to improve feature extraction and network reasoning speed. Additionally, a ResNet-ACmix module is designed to avoid feature information loss and reduce computation, while a Global Attention Mechanism (GAM) is inserted in the backbone and head parts of the model to improve feature extraction. Furthermore, the K-means++ algorithm is used instead of K-means to obtain anchor boxes and enhance model accuracy. Experimental results show that the improved YOLOv7 network outperforms the original YOLOv7 model and other popular underwater target detection methods. The proposed network achieved a mean average precision (mAP) value of 89.6% and 97.4% on the URPC dataset and Brackish dataset, respectively, and demonstrated a higher frame per second (FPS) compared to the original YOLOv7 model. In conclusion, the improved YOLOv7 network proposed in this study represents a promising solution for underwater target detection and holds great potential for practical applications in various underwater tasks.

Comparative Evaluation of Color Correction as Image Preprocessing for Olive Identification under Natural Light Using Cell Phones

“…This advancement has been well-documented in several key publications [52][53][54]. Wang et al [32] and Liu et al [55] describe the YOLOv7 as comprising an input, backbone, and head network, and a prediction network, as explained below (Figure 3): Input module: To ensure that the input color images are uniformly scaled to a 640 × 640 size and meet the requirements for the input size of the backbone network, the preprocessing stage of the YOLOv7 model uses mosaic and hybrid data enhancement techniques. It also uses the adaptive anchor frame calculation method established by YOLOv5.…”

Underwater Small Target Detection Based on Improved YOLOv7 Model

“…Considering the morphological diversity and scale changes of underwater targets, the USTD network proposed by Qi et al adopts deformable convolutional layers and convolutional pyramids to effectively handle targets of different sizes, but faces accuracy loss when dealing with non integer coordinate points 22 . In addition, Sun et al have incorporated the ACmix module into the YOLOv7 framework, leveraging both convolution and attention mechanisms to refine feature capture accuracy, thereby augmenting underwater object detection performance 23 .…”

High resolution underwater object detection network based on multi-scale attention feature fusion

“…Liang et al [9] proposed an underwater object detection method called RoIAttn, which introduces a RoI attention module to compute similarities between RoI features and reconstruct features based on an attention matrix, to obtain relational information between RoI features. Liu et al [10] improved YOLOv7 for underwater object detection by introducing modules like ACmix, ResNet-ACmix, global attention mechanism, and K-means++ algorithm, achieving better performance than original YOLOv7 and other methods. The above methods effectively alleviate issues in underwater object detection, but do not consider the application of multi-scale features for underwater object detection.…”