Lightweight Deep Neural Network for Joint Learning of Underwater Object Detection and Color Conversion

Yeh, Chia Hung; Lin, Chu Han; Li, Kang; Huang, Chih Hsuan; Lin, Min; Chang, Chuan Yu; Wang, Chua‐Chin

doi:10.1109/tnnls.2021.3072414

Cited by 129 publications

(57 citation statements)

References 67 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In consequence, another solution for handling the image quality degradation problem is to integrate the image enhancement and object detection into a new model by multi-task learning [34]. In [35], a lightweight deep neural network is proposed for jointly learning color conversion and object detection on underwater images. As shown in Figure 10, to alleviate the problem of color distortion, the image color conversion module converts color pictures to their matching gray-scale images.…”

Section: Image Enhancement Integrated Into Object Detection Networkmentioning

confidence: 99%

Research Challenges, Recent Advances and Benchmark Datasets in Deep-Learning-Based Underwater Marine Object Detection: A Review

Er¹,

Chen²

2022

Preprint

View full text Add to dashboard Cite

Underwater marine object detection, as one of the most fundamental techniques in marine engineering, had been shown to exhibit tremendous potential for exploring the oceans in recent years. It has been applied widely in monitoring of underwater ecosystems, exploration of natural resources, management of commercial fishery, and so on. However, due to the complexity of the underwater environment, characteristics of marine objects, and limitations from exploration equipment, the detection performance in terms of speed, accuracy and robustness could be degraded dramatically using conventional approaches. Deep learning algorithms have found significant impact in many fields of engineering and science including marine engineering. In this context, We offer an overview of deep-learning-based underwater marine object detection techniques. We organize the present research challenges into three areas to assist a thorough knowledge of the subject matter, namely image quality degradation, small object detection, and poor generalization. We evaluate recent advances and emphasize the advantages and risks of existing solutions for each category of extant challenges. In addition, we examine the most extensively used benchmark datasets for underwater marine object detection in detail and critically. Comparisons between previous reviews and prospective advancements in the subject field, notably Artificial-Intelligence-based approaches, are also presented.

show abstract

Section: Image Enhancement Integrated Into Object Detection Networkmentioning

confidence: 99%

Research Challenges, Recent Advances and Benchmark Datasets in Deep-Learning-Based Underwater Marine Object Detection: A Review

Er¹,

Chen²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In consequence, another solution for handling the image quality degradation problem is to integrate the image enhancement and object detection into a new model by multi-task learning [47]. In [13], a lightweight deep neural network is proposed for jointly learning color conversion and object detection on underwater images. As shown in Figure 12, the image color conversion module aims at transforming color images to the corresponding gray-scale images to solve the problem of color distortion.…”

Section: Image Enhancement Integrated Into Object Detection Networkmentioning

confidence: 99%

“…Furthermore, the scattering caused by particles in water leads to strong haziness phenomenon. Meanwhile, complex sea-bed backgrounds and many other factors also will interfere with the imagery, such as movements of fish and aquatic plants almost cause motion blurring inevitably [13]. On the other hand, most underwater objects, especially marine organisms, are usually very small and tend to congregate in large numbers.…”

Section: Introductionmentioning

confidence: 99%

Research Challenges, Recent Advances and Benchmark Datasets in Deep-Learning-Based Underwater Marine Object Detection: A Review

Er¹,

Chen²

2022

Preprint

View full text Add to dashboard Cite

Underwater marine object detection, as one of the most fundamental techniques in marine engineering, has been shown to exhibit significant potential for exploring underwater environment in recent years. It has been applied widely in the monitoring of underwater ecosystems, exploration of natural resources, management of commercial fishery management, and other areas. However, due to the complexity of underwater environment, characteristics of marine object, and limitation from exploration equipment, the detection performance revolving around speed, accuracy and robustness could be degraded dramatically. In this context, we present a survey of deep-learning-based underwater marine object detection. To facilitate comprehensive understanding of the subject matter, we categorize the existing research challenges of underwater object detection into image quality degradation, small object detection, poor generalization and real-time detection. Corresponding to each category of the existing challenges, we review recent advances and highlight the pros and cons of existing techniques. Furthermore, we give a detailed and critical review of the most widely used benchmark datasets for underwater marine object detection. Comparisons with existing reviews and future trends of the subject matter, particularly AI-based techniques, are also presented.

show abstract

“…The exploration of the aquatic environment has recently become popular due to the growing scarcity of natural resources and the growth of the global economy [1]. Machine vision has been demonstrated to be a low-cost and dependable method with the benefits of noncontact monitoring, long-term steady operation, and a broad application range.…”

Section: Introductionmentioning

confidence: 99%

“…However, capturing underwater pictures with optical imaging systems has greater problems than in open-air conditions. More specifically, underwater images frequently suffer from degeneration due to color severe distortion, low contrast, non-uniform illumination, and noise from artificial lighting sources, which dramatically degrades image visibility and affects the detection accuracy of underwater object detection tasks [1]. In recent years, underwater image enhancement technologies, work as a pre-processing operation to boost the detection accuracy by improving the visual quality of underwater images.…”

Section: Introductionmentioning

confidence: 99%

A Novel Underwater Image Enhancement and Improved Underwater Biological Detection Pipeline

Liu¹,

Zhuang²,

Jia³

et al. 2022

Preprint

View full text Add to dashboard Cite

For aquaculture resource evaluation and ecological environment monitoring, automatic detection and identification of marine organisms is critical. However, due to the low quality of underwater images and the characteristics of underwater biological, a lack of abundant features may impede traditional hand-designed feature extraction approaches or CNN-based object detection algorithms, particularly in complex underwater environment. Therefore, the goal of this paper is to perform object detection in the underwater environment. This paper proposed a novel method for capturing feature information, which adds the convolutional block attention module (CBAM) to the YOLOv5 backbone. The interference of underwater creature characteristics on object characteristics is decreased, and the output of the backbone network to object information is enhanced. In addition, the self-adaptive global histogram stretching algorithm (SAGHS) is designed to eliminate the degradation problems such as low contrast and color loss caused by underwater environmental information to better restore image quality. Extensive experiments and comprehensive evaluation on the URPC2021 benchmark dataset demonstrate the effectiveness and adaptivity of our methods. Beyond that, this paper conducts an exhaustive analysis of the role of training data on performance.

show abstract

Lightweight Deep Neural Network for Joint Learning of Underwater Object Detection and Color Conversion

Cited by 129 publications

References 67 publications

Research Challenges, Recent Advances and Benchmark Datasets in Deep-Learning-Based Underwater Marine Object Detection: A Review

Research Challenges, Recent Advances and Benchmark Datasets in Deep-Learning-Based Underwater Marine Object Detection: A Review

Research Challenges, Recent Advances and Benchmark Datasets in Deep-Learning-Based Underwater Marine Object Detection: A Review

A Novel Underwater Image Enhancement and Improved Underwater Biological Detection Pipeline

Contact Info

Product

Resources

About