Accurate detection of underwater bubble plumes is essential for stable target tracking and quantitative analysis in marine engineering safety monitoring, gas leakage assessment, and environmental studies. However, challenging optical conditions in controlled underwater experiments cause bubble targets to exhibit low contrast, weak boundaries, and large-scale variations, which significantly hinder detection accuracy. To address these challenges, this paper proposes an integrated detection and tracking-based quantitative analysis framework for underwater bubble plumes, termed BubbleQuantTrack, and develops an improved bubble detection model named BubbleDet Y11 based on the YOLOv11 framework. BubbleDet Y11 employs a lightweight reparameterized backbone network, RepViT, to enhance feature representation while maintaining high inference efficiency. In addition, an attentional scale fusion (ASF) module is introduced to fuse multiscale features and apply attention-based reweighting, thereby improving the detection of small-scale bubbles and weak boundary targets and reducing missed detections in complex scenes. Furthermore, a two-stage association tracking strategy based on ByteTrack is used for cross-frame target association, enabling trajectory-level quantitative analysis of bubble motion characteristics. Experimental results show that BubbleDet Y11 achieves 90.8% mAP at IoU 0.5, outperforming the baseline YOLOv11 model while preserving real-time performance, which demonstrates the effectiveness and practical applicability of the proposed method.
Zong et al. (Thu,) studied this question.