Frontiers of Information Technology & Electronic Engineering
>> 2023,
Volume 24,
Issue 6
doi:
10.1631/FITEE.2200429
Underwater object detection by fusing features from different representations of sonar data
Affiliation(s): College of Information Science and Technology, Dalian Maritime University, Dalian 116026, China; College of Transportation Engineering, Dalian Maritime University, Dalian 116026, China; less
Received: 2022-10-03
Accepted: 2023-07-03
Available online: 2023-07-03
Next
Previous
Abstract
Modern methods recognize objects from sonar data based on their geometric shapes. However, the distortion of objects during data acquisition and representation is seldom considered. In this paper, we present a detailed summary of representations for sonar data and a concrete analysis of the geometric characteristics of different data representations. Based on this, a framework is proposed to fully use the intensity features extracted from the polar image representation and the geometric features learned from the point cloud representation of sonar data. Three strategies are presented to investigate the impact of on different components of the detection pipeline. In addition, the fusion strategies can be easily integrated into other detectors, such as the You Only Look Once (YOLO) series. The effectiveness of our proposed framework and strategies is demonstrated on a public sonar dataset captured in real-world underwater environments. Experimental results show that our method benefits both the region proposal and the object classification modules in the detectors.