Comprehensive Underwater Object Tracking Benchmark Dataset and Underwater Image Enhancement With GAN

Abstract

Current state-of-the-art object tracking methods have largely benefited from the public availability of numerous benchmark datasets. However, the focus has been on open-air imagery and much less on underwater visual data. Inherent underwater distortions, such as color loss, poor contrast, and underexposure, caused by attenuation of light, refraction, and scattering, greatly affect the visual quality of underwater data, and as such, existing open-air trackers perform less efficiently on such data. To help bridge this gap, this article proposes a first comprehensive underwater object tracking (UOT100) benchmark dataset to facilitate the development of tracking algorithms well-suited for underwater environments. The proposed dataset consists of 104 underwater video sequences and more than 74 000 annotated frames derived from both natural and artificial underwater videos, with great varieties of distortions. We benchmark the performance of 20 state-of-the-art object tracking algorithms and further introduce a cascaded residual network for underwater image enhancement model to improve tracking accuracy and success rate of trackers. Our experimental results demonstrate the shortcomings of existing tracking algorithms on underwater data and how our generative adversarial network (GAN)-based enhancement model can be used to improve tracking performance. We also evaluate the visual quality of our model's output against existing GAN-based methods using well-accepted quality metrics and demonstrate that our model yields better visual data. Index Terms-Underwater benchmark dataset, underwater generative adversarial network (GAN), underwater image enhancement (UIE), underwater object tracking (UOT).

Virtual Underwater Datasets for Autonomous Inspections

“…The collected data were then tested on the custom Water-Net model to perform image enhancement. Furthermore, Panetta et al [34] went further in underwater object tracking and image enhancement and introduced a benchmark underwater dataset, UOT100. The dataset comprises 104 underwater videos, from which they generated a complete set of 74 K annotated image frames.…”

Adjust Sample Imbalance and Exclude Similar Object in Underwater Object Tracking

“…Before the presentation of the UOT100 dataset [4], due to the lack of unified underwater object tracking dataset benchmark, people mainly verified the effectiveness of their trackers by selecting some video or image sequences that reflect the challenges of underwater tracking tasks on Fish4knowledge (F4K) [5] or Underwater Change Detection (UWCD) [6] or other self -built datasets. After UOT100 and UTB180 [7] were proposed, the researchers pay more attention to the development of high performance underwater trackers.…”

Unsupervised Underwater Image Restoration: From a Homology Perspective

“…Underwater images suffer from color distortion and poor visibility (Akkaynak et al 2017) because the light is absorbed and scattered when it propagates through turbid water mediums. Such degradations will lead to poor performance in underwater computer vision applications, e.g., underwater object tracking (Panetta et al 2021), marine animal detection (Fan et al 2020) and robotic navigation. The degradations in underwater images can be described via the modified Koschmieder's light scattering model (Jaffe 1990) where the transmission map is changed into a channel-wise component and the atmospheric light is replaced by the global background light.…”