Underwater Rescue Target Detection Based on Acoustic Images

Abstract

In order to effectively respond to floods and water emergencies that result in the drowning of missing persons, timely and effective search and rescue is a very critical step in underwater rescue. Due to the complex underwater environment and low visibility, unmanned underwater vehicles (UUVs) with sonar are more efficient than traditional manual search and rescue methods to conduct active searches using deep learning algorithms. In this paper, we constructed a sound-based rescue target dataset that encompasses both the source and target domains using deep transfer learning techniques. For the underwater acoustic rescue target detection of small targets, which lack image feature accuracy, this paper proposes a two-branch convolution module and improves the YOLOv5s algorithm model to design an acoustic rescue small target detection algorithm model. For an underwater rescue target dataset based on acoustic images with a small sample acoustic dataset, a direct fine-tuning using optical image pre-training lacks cross-domain adaptability due to the different statistical properties of optical and acoustic images. This paper therefore proposes a heterogeneous information hierarchical migration learning method. For the false detection of acoustic rescue targets in a complex underwater background, the network layer is frozen during the hierarchical migration of heterogeneous information to improve the detection accuracy. In addition, in order to be more applicable to the embedded devices carried by underwater UAVs, an underwater acoustic rescue target detection algorithm based on ShuffleNetv2 is proposed to improve the two-branch convolutional module and the backbone network of YOLOv5s algorithm, and to create a lightweight model based on hierarchical migration of heterogeneous information. Through extensive comparative experiments conducted on various acoustic images, we have thoroughly validated the feasibility and effectiveness of our method. Our approach has demonstrated state-of-the-art performance in underwater search and rescue target detection tasks.

Keywords: acoustic small target detection; deep learning; deep migration learning; lightweight network; underwater acoustic rescue target detection.

Figure 1

ShuffleNetv2-Db-YOLOv5 s network model structure.

Figure 2

Heterogeneous hierarchical migration learning based on YOLOv5s-DbConv.

Figure 3

Outdoor complex background underwater rescue target acoustic image detection effect.

Figure 4

(a) Schematic diagram of acoustic image data acquisition for underwater rescue targets, (b) The comprehensive experimental pool, and (c) Qingdao open sea terminal.

Figure 5

(a) Acoustic image of the pool underwater rescue target. (b) Acoustic image of outdoor underwater rescue target.

Figure 6

SAR data set and optical human dataset. (a,c) are the SAR dataset samples. (b,d) are the optical human dataset samples.

Figure 7

P–R curves for freezing different layers of YOLOv5s-DbConv model based on heterogeneous hierarchical migration learning. (a) Original unfrozen network layer and (b) Freeze layer 0.

Figure 8

P–R plot of ShuffleNetv2-YOLOv5s-DbConv algorithm based on heterogeneous hierarchical migration learning freezing layer 0.

Figure 9

Comparison of the detection effect of the proposed method on the complex background of underwater acoustics. (a) False detection and (b) Correct detection.