Robust and Fair Undersea Target Detection with Automated Underwater Vehicles for Biodiversity Data Collection

Dinakaranr, Ranjith; Zhang, Li; Li, Chang-Tsun; Bouridane, Ahmed; Jiang, Richard

doi:10.3390/rs14153680

Cited by 22 publications

(5 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hyperparameters are the parameters that manages the learning process of the Deep Learning model, including the number of layers, the learning rate, and the batch size. For a sample of study that handled their hyperparameter issue, the paper by Dinakaran et al, [53] has it covered. An effective way to choose hyperparameters is through Bayesian optimization, a statistical method that maximizes the expected improvement of the model.…”

Section: Statistical Methodologies With Deep Learningmentioning

confidence: 99%

A Review on Occluded Object Detection and Deep Learning-Based Approach in Medical Imaging-Related Research

Khairul Rohaizzat Jamaluddin,

Shafaf Ibrahim

2023

ARASET

View full text Add to dashboard Cite

Medical image occlusions can arise due to several factors, including anatomical features, imaging modality, and acquisition settings. Object occlusion occurrence has a very significant effect on detection accuracy in general and in medical cases, these effects hinder proper diagnosis and treatment plans that may be fatal for the patients. Thus, precise occluded object detection is imperative. This paper aims to review the various state-of-the-art models and approaches that had been proposed for the occluded object detection. The coverage of this paper includes occluded object detection models in other applications and medical imaging, its proposed Deep Learning implementations, hybrid Deep Learning, and statistical analysis that were integrated into Deep Learning models. It is found that, in overall, more annotated medical image datasets are required to reduce overfitting occurrence, numerous Deep Learning models and its hybrid combination’s applications yet to be tested of its limitations, and the extent of statistical analysis integration on Deep Learning models.

show abstract

Section: Statistical Methodologies With Deep Learningmentioning

confidence: 99%

A Review on Occluded Object Detection and Deep Learning-Based Approach in Medical Imaging-Related Research

Khairul Rohaizzat Jamaluddin,

Shafaf Ibrahim

2023

ARASET

View full text Add to dashboard Cite

show abstract

“…The commercialization of UV-C applications can be achieved through tested technologies like autonomous underwater vehicles (AUVs) [ 94 ], suitable for aquatic environments. Additionally, UV-C applications can effectively target submerged weeds by installing radiation sources onto boat bottoms or floating equipment, particularly in lake environments.…”

Section: Conclusion and Prospectsmentioning

confidence: 99%

Nonchemical Aquatic Weed Control Methods: Exploring the Efficacy of UV-C Radiation as a Novel Weed Control Tool

Udugamasuriyage,

Kahandawa,

Tennakoon

2024

Plants

View full text Add to dashboard Cite

Aquatic weeds, including invasive species, are a worldwide problem. The presence of aquatic weeds poses several critical issues, such as hindering the continuous flow of water in irrigation channels and preventing the proper distribution of adequate water quantities. Therefore, effective control measures are vital for agriculture and numerous downstream industries. Numerous methods for controlling aquatic weeds have emerged over time, with herbicide application being a widely used established method of weed management, although it imposes significant environmental risks. Therefore, it is important to explore nonchemical alternative methods to control existing and emerging aquatic weeds, potentially posing fewer environmental hazards compared with conventional chemical methods. In this review, we focus on nonchemical methods, encompassing mechanical, physical, biological, and other alternative approaches. We primarily evaluated the different nonchemical control methods discussed in this review based on two main criteria: (1) efficiency in alleviating aquatic weed problems in location-specified scenarios and (2) impacts on the environment, as well as potential health and safety risks. We compared the nonchemical treatments with the UV-C-radiation-mediated aquatic weed control method, which is considered a potential novel technique. Since there is limited published literature available on the application of UV-C radiation used exclusively for aquatic weed control, our review is based on previous reports of UV-C radiation used to successfully control terrestrial weeds and algal populations. In order to compare the mechanisms involved with nonchemical weed control methods, we reviewed respective pathways leading to plant cell death, plant growth inhibition, and diminishing reemergence to justify the potential use of UV-C treatment in aquatic habitats as a viable novel source for aquatic weed control.

show abstract

“…Various image enhancement techniques have been investigated in the literature for improving contrast, correcting color shifts, and sharpening edges in underwater images [7][8][9]. Furthermore, other studies aim to counteract the negative effects of image blur by enhancing the network architecture [10][11][12] and refining training strategies [13]. Conversely, there is a high level of interest in improving the accuracy and expeditiousness of generic detection models.…”

Section: Underwater Object Detectionmentioning

confidence: 99%

YOLOv7-CHS: An Emerging Model for Underwater Object Detection

Zhao,

Yun,

Yuan

et al. 2023

JMSE

View full text Add to dashboard Cite

Underwater target detection plays a crucial role in marine environmental monitoring and early warning systems. It involves utilizing optical images acquired from underwater imaging devices to locate and identify aquatic organisms in challenging environments. However, the color deviation and low illumination in these images, caused by harsh working conditions, pose significant challenges to an effective target detection. Moreover, the detection of numerous small or tiny aquatic targets becomes even more demanding, considering the limited storage and computing power of detection devices. To address these problems, we propose the YOLOv7-CHS model for underwater target detection, which introduces several innovative approaches. Firstly, we replace efficient layer aggregation networks (ELAN) with the high-order spatial interaction (HOSI) module as the backbone of the model. This change reduces the model size while preserving accuracy. Secondly, we integrate the contextual transformer (CT) module into the head of the model, which combines static and dynamic contextual representations to effectively improve the model’s ability to detect small targets. Lastly, we incorporate the simple parameter-free attention (SPFA) module at the head of the detection network, implementing a combined channel-domain and spatial-domain attention mechanism. This integration significantly improves the representation capabilities of the network. To validate the implications of our model, we conduct a series of experiments. The results demonstrate that our proposed model achieves higher mean average precision (mAP) values on the Starfish and DUO datasets compared to the original YOLOv7, with improvements of 4.5% and 4.2%, respectively. Additionally, our model achieves a real-time detection speed of 32 frames per second (FPS). Furthermore, the floating point operations (FLOPs) of our model are 62.9 G smaller than those of YOLOv7, facilitating the deployment of the model. Its innovative design and experimental results highlight its effectiveness in addressing the challenges associated with underwater object detection.

show abstract

Robust and Fair Undersea Target Detection with Automated Underwater Vehicles for Biodiversity Data Collection

Cited by 22 publications

References 40 publications

A Review on Occluded Object Detection and Deep Learning-Based Approach in Medical Imaging-Related Research

A Review on Occluded Object Detection and Deep Learning-Based Approach in Medical Imaging-Related Research

Nonchemical Aquatic Weed Control Methods: Exploring the Efficacy of UV-C Radiation as a Novel Weed Control Tool

YOLOv7-CHS: An Emerging Model for Underwater Object Detection

Contact Info

Product

Resources

About