AquaFeat+: an Underwater Vision Learning-based Enhancement Method for Object Detection, Classification, and Tracking

📅 2025-12-02
🏛️ International Conference on Advanced Robotics
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
Underwater videos are often degraded by insufficient lighting, color distortion, and turbidity, which significantly impair robotic perception performance. To address this challenge, this work proposes AquaFeat+, a task-oriented, plug-and-play, end-to-end enhancement framework that, for the first time, jointly optimizes underwater visual enhancement and downstream perception tasks—specifically designed for machine perception rather than human vision. AquaFeat+ integrates color correction, hierarchical feature enhancement, and an adaptive residual output module, with training directly guided by task-specific loss functions. Evaluated on the FishTrack23 dataset, AquaFeat+ substantially improves performance in object detection, classification, and tracking, demonstrating its effectiveness in enhancing underwater robotic perception.

Technology Category

Application Category

📝 Abstract
Underwater video analysis is particularly challenging due to factors such as low lighting, color distortion, and turbidity, which compromise visual data quality and directly impact the performance of perception modules in robotic applications. This work proposes AquaFeat+, a plug-and-play pipeline designed to enhance features specifically for automated vision tasks, rather than for human perceptual quality. The architecture includes modules for color correction, hierarchical feature enhancement, and an adaptive residual output, which are trained end-to-end and guided directly by the loss function of the final application. Trained and evaluated in the FishTrack23 dataset, AquaFeat+ achieves significant improvements in object detection, classification, and tracking metrics, validating its effectiveness for enhancing perception tasks in underwater robotic applications.
Problem

Research questions and friction points this paper is trying to address.

underwater vision
object detection
color distortion
turbidity
visual data quality
Innovation

Methods, ideas, or system contributions that make the work stand out.

underwater vision enhancement
task-driven feature enhancement
end-to-end trainable pipeline
adaptive residual learning
plug-and-play perception module
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
E
Emanuel C. Silva
Centro de Ciências Computacionais (C3), Universidade Federal do Rio Grande (FURG), Brazil
T
T. T. Schein
Centro de Ciências Computacionais (C3), Universidade Federal do Rio Grande (FURG), Brazil
J
José David Garcí Ramos
Centro de Ciências Computacionais (C3), Universidade Federal do Rio Grande (FURG), Brazil
E
Eduardo Lawson da Silva
Centro de Ciências Computacionais (C3), Universidade Federal do Rio Grande (FURG), Brazil
S
S. L. Brião
Centro de Ciências Computacionais (C3), Universidade Federal do Rio Grande (FURG), Brazil
F
Felipe Gomes de Oliveira
Instituto de Ciências Exatas e Tecnologia (ICET), Universidade Federal do Amazonas (UFAM), Brazil
P
P. L. J. Drews-Jr
Centro de Ciências Computacionais (C3), Universidade Federal do Rio Grande (FURG), Brazil