Lightweight Mask RCNN for Warship Detection and Segmentation

Park, Jin‐Young; Moon, Hoseok

doi:10.1109/access.2022.3149297

Cited by 15 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Mask-RCNN represents an amalgamation of object detection and image segmentation methodologies founded on CNNs. Its fundamental concept entails the integration of these two tasks to achieve precision at the pixel level [ 41 , 42 ]. Through the employment of the Mask-RCNN algorithm, the image of the basement concrete structure can be meticulously segmented during the crack identification process, thereby facilitating the precise determination of each crack’s spatial location and morphology.…”

Section: Methodsmentioning

confidence: 99%

Crack control optimization of basement concrete structures using the Mask-RCNN and temperature effect analysis

Wu,

2023

PLoS ONE

View full text Add to dashboard Cite

In order to enhance the mitigation of crack occurrence and propagation within basement concrete structures, this research endeavors to propose an optimization methodology grounded in the Mask Region-based Convolutional Neural Network (Mask-RCNN) and an analysis of temperature effects. Initially, the Mask-RCNN algorithm is employed to perform image segmentation of the basement concrete structure, facilitating the precise identification of crack locations and shapes within the structure. Subsequently, the finite element analysis method is harnessed to simulate the structural stress and deformation in response to temperature variations. An optimization algorithm is introduced to adjust geometric parameters and material properties using insights from the temperature effect analysis. This algorithm aims to minimize stress concentration and deformation within the structure, thus diminishing the incidence and proliferation of cracks. In order to assess the efficacy of the optimization approach, an authentic basement concrete structure is selected for scrutiny, and the structure is monitored in real-time through the installation of strain gauges and monitoring equipment. These instruments track structural stress and deformation under diverse temperature conditions, and the evolution of cracks is meticulously documented. The outcomes demonstrate that by adjusting the structural geometric parameters and material properties, the crack density experiences a notable reduction of 60.22%. Moreover, the average crack length and width witness reductions of 40.24% and 35.43%, respectively, thereby corroborating the efficacy of the optimization method. Furthermore, an assessment of stress concentration and deformation within the structure is conducted. Through the optimization process, the maximum stress concentration in the structure diminishes by 25.22%, while the maximum deformation is curtailed by 30.32%. These results signify a substantial enhancement in structural stability. It is evident that the optimization algorithm exhibits robustness and stability in the context of crack control, consistently delivering favorable outcomes across diverse parameter configurations.

show abstract

Section: Methodsmentioning

confidence: 99%

Crack control optimization of basement concrete structures using the Mask-RCNN and temperature effect analysis

Wu,

2023

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…As a result of this, the segmentation stream improved greatly while the network needed fewer annotated, labelled images to train. Park et al [205] proposed a lightweight Mask-RCNN by using an efficient backbone, i.e., MobileNetV2, to jointly perform warship detection and segmentation. To reduce the cost of dense pixel-level annotation, Zust et al [206] proposed a weakly supervised method to train a semantic segmentation network for maritime obstacle detection.…”

Section: Leveraging Segmentation Methodsmentioning

confidence: 99%

A Guide to Image and Video based Small Object Detection using Deep Learning : Case Study of Maritime Surveillance

Rekavandi¹,

Liu²,

Boussaid³

et al. 2022

Preprint

View full text Add to dashboard Cite

Small object detection (SOD) in optical images and videos is a challenging problem that even state-of-the-art generic object detection methods fail to accurately localize and identify such objects. Typically, small objects appear in real-world due to large camera-object distance. Because small objects occupy only a small area in the input image (e.g., less than 10%), the information extracted from such a small area is not always rich enough to support decision making. Multidisciplinary strategies are being developed by researchers working at the interface of deep learning and computer vision to enhance the performance of SOD deep learning based methods. In this paper, we provide a comprehensive review of over 160 research papers published between 2017 and 2022 in order to survey this growing subject. This paper summarizes the existing literature and provide a taxonomy that illustrates the broad picture of current research. We investigate how to improve the performance of small object detection in maritime environments, where increasing performance is critical. By establishing a connection between generic and maritime SOD research, future directions have been identified. In addition, the popular datasets that have been used for SOD for generic and maritime applications are discussed, and also well-known evaluation metrics for the state-of-the-art methods on some of the datasets are provided.

show abstract

“…The GSConv module integrates spa-tial convolution (SC), depthwise separable convolution (DSC), and shuffle operations [25]. The parameter quantity and computational complexity of the convolutional layer can be expressed using Formulas (9) and (10).…”

Section: Slim-neck Constructionmentioning

confidence: 99%

CSD-YOLO: A Ship Detection Algorithm Based on a Deformable Large Kernel Attention Mechanism

Wang,

Zhang,

Jiang

2024

Mathematics

View full text Add to dashboard Cite

Ship detection and identification play pivotal roles in ensuring navigation safety and facilitating efficient maritime traffic management. Aiming at ship detection in complex environments, which often faces problems such as the dense occlusion of ship targets, low detection accuracy, and variable environmental conditions, in this paper, we propose a ship detection algorithm CSD-YOLO (Context guided block module, Slim-neck, Deformable large kernel attention-You Only Look Once) based on the deformable large kernel attention (D-LKA) mechanism, which was improved based on YOLOv8 to enhance its performance. This approach integrates several innovations to bolster its performance. Initially, the utilization of the Context Guided Block module (CG block) enhanced the c2f module of the backbone network, thereby augmenting the feature extraction capabilities and enabling a more precise capture of the key image information. Subsequently, the introduction of a novel neck architecture and the incorporation of the slim-neck module facilitated more effective feature fusion, thereby enhancing both the accuracy and efficiency of detection. Furthermore, the algorithm incorporates a D-LKA mechanism to dynamically adjust the convolution kernel shape and size, thereby enhancing the model’s adaptability to varying ship target shapes and sizes. To address data scarcity in complex marine environments, the experiments utilized a fused dataset comprising the SeaShips dataset and a proprietary dataset. The experimental results demonstrate that the CSD-YOLO algorithm outperformed the YOLOv8n algorithm across all model evaluation metrics. Specifically, the precision rate (precision) was 91.5%, the recall rate (recall) was 89.5%, and the mean accuracy (mAP) was 91.5%. Compared to the benchmark algorithm, the Recall was improved by 0.7% and the mAP was improved by 0.4%. These results indicate that the CSD-YOLO algorithm can effectively meet the requirements for ship target recognition and tracking in complex marine environments.

show abstract

Lightweight Mask RCNN for Warship Detection and Segmentation

Cited by 15 publications

References 33 publications

Crack control optimization of basement concrete structures using the Mask-RCNN and temperature effect analysis

Crack control optimization of basement concrete structures using the Mask-RCNN and temperature effect analysis

A Guide to Image and Video based Small Object Detection using Deep Learning : Case Study of Maritime Surveillance

CSD-YOLO: A Ship Detection Algorithm Based on a Deformable Large Kernel Attention Mechanism

Contact Info

Product

Resources

About