ShipYOLO: An Enhanced Model for Ship Detection

The application of ship detection for assistant intelligent ship navigation has stringent requirements for the model’s detection speed and accuracy. In response to this problem, this study uses an improved YOLO-V4 detection model (ShipYOLO) to detect ships. Compared to YOLO-V4, the model has three main improvements. Firstly, the backbone network (CSPDarknet) of YOLO-V4 is optimized. In the training process, the 3 × 3 convolution, 1 × 1 convolution, and identity parallel mode are used to replace the original feature extraction component (ResUnit) and more features are extracted. In the inference process, the branch parameters are combined to form a new backbone network named RCSPDarknet, which improves the inference speed of the model while improving the accuracy. Secondly, in order to solve the problem of missed detection of the small-scale ships, we designed a new amplified receptive field module named DSPP with dilated convolution and Max-Pooling, which improves the model’s acquisition of small-scale ship spatial information and robustness of ship target space displacement. Finally, we use the attention mechanism and Resnet’s shortcut idea to improve the feature pyramid structure (PAFPN) of YOLO-V4 and get a new feature pyramid structure named AtFPN. The structure effectively improves the model’s feature extraction effect for ships of different scales and reduces the number of model parameters, further improving the model’s inference speed and detection accuracy. In addition, we have created a ship dataset with a total of 2238 images, which is a single-category dataset. The experimental results show that ShipYOLO has the advantage of faster speed and higher accuracy even in different input sizes. Considering the input size of 320 × 320 on the PC equipped with NVIDIA 1080Ti GPU, the FPS and mAP@5 : 5:95 (mAP90) of ShipYOLO are increased by 23.7% and 13.6% (10.6%), respectively, with an input size of 320 × 320, ShipYOLO, compared to YOLO-V4.

Download Full-text

Improved SSD-assisted algorithm for surface defect detection of electromagnetic luminescence

Proceedings of the Institution of Mechanical Engineers Part O Journal of Risk and Reliability ◽

10.1177/1748006x21995388 ◽

2021 ◽

pp. 1748006X2199538

Author(s):

Zhenying Xu ◽

Ziqian Wu ◽

Wei Fan

Keyword(s):

Defect Detection ◽

Feature Fusion ◽

Recognition Rate ◽

Detection Methods ◽

Small Scale ◽

Detection Accuracy ◽

Single Shot ◽

Surface Defect Detection ◽

Feature Pyramid ◽

Small Feature

Defect detection of electromagnetic luminescence (EL) cells is the core step in the production and preparation of solar cell modules to ensure conversion efficiency and long service life of batteries. However, due to the lack of feature extraction capability for small feature defects, the traditional single shot multibox detector (SSD) algorithm performs not well in EL defect detection with high accuracy. Consequently, an improved SSD algorithm with modification in feature fusion in the framework of deep learning is proposed to improve the recognition rate of EL multi-class defects. A dataset containing images with four different types of defects through rotation, denoising, and binarization is established for the EL. The proposed algorithm can greatly improve the detection accuracy of the small-scale defect with the idea of feature pyramid networks. An experimental study on the detection of the EL defects shows the effectiveness of the proposed algorithm. Moreover, a comparison study shows the proposed method outperforms other traditional detection methods, such as the SIFT, Faster R-CNN, and YOLOv3, in detecting the EL defect.

Download Full-text

Automatic Ship Detection Based on RetinaNet Using Multi-Resolution Gaofen-3 Imagery

Remote Sensing ◽

10.3390/rs11050531 ◽

2019 ◽

Vol 11 (5) ◽

pp. 531 ◽

Cited By ~ 34

Author(s):

Yuanyuan Wang ◽

Chao Wang ◽

Hong Zhang ◽

Yingbo Dong ◽

Sisi Wei

Keyword(s):

Class Imbalance ◽

Weather Conditions ◽

Detection Methods ◽

Detection Accuracy ◽

Ship Detection ◽

Multi Scale ◽

Resolution Imaging ◽

Feature Pyramid ◽

Sar Imagery ◽

Ship Classification

Independent of daylight and weather conditions, synthetic aperture radar (SAR) imagery is widely applied to detect ships in marine surveillance. The shapes of ships are multi-scale in SAR imagery due to multi-resolution imaging modes and their various shapes. Conventional ship detection methods are highly dependent on the statistical models of sea clutter or the extracted features, and their robustness need to be strengthened. Being an automatic learning representation, the RetinaNet object detector, one kind of deep learning model, is proposed to crack this obstacle. Firstly, feature pyramid networks (FPN) are used to extract multi-scale features for both ship classification and location. Then, focal loss is used to address the class imbalance and to increase the importance of the hard examples during training. There are 86 scenes of Chinese Gaofen-3 Imagery at four resolutions, i.e., 3 m, 5 m, 8 m, and 10 m, used to evaluate our approach. Two Gaofen-3 images and one Constellation of Small Satellite for Mediterranean basin Observation (Cosmo-SkyMed) image are used to evaluate the robustness. The experimental results reveal that (1) RetinaNet not only can efficiently detect multi-scale ships but also has a high detection accuracy; (2) compared with other object detectors, RetinaNet achieves more than a 96% mean average precision (mAP). These results demonstrate the effectiveness of our proposed method.

Download Full-text

Elongated Small Object Detection from Remote Sensing Images Using Hierarchical Scale-Sensitive Networks

Remote Sensing ◽

10.3390/rs13163182 ◽

2021 ◽

Vol 13 (16) ◽

pp. 3182

Author(s):

Zheng He ◽

Li Huang ◽

Weijiang Zeng ◽

Xining Zhang ◽

Yongxin Jiang ◽

...

Keyword(s):

Remote Sensing ◽

Object Detection ◽

Large Scale ◽

Small Scale ◽

Detection Accuracy ◽

Small Object ◽

Direction Vector ◽

Remote Sensing Images ◽

Ship Detection ◽

Hierarchical Scale

The detection of elongated objects, such as ships, from satellite images has very important application prospects in marine transportation, shipping management, and many other scenarios. At present, the research of general object detection using neural networks has made significant progress. However, in the context of ship detection from remote sensing images, due to the elongated shape of ship structure and the wide variety of ship size, the detection accuracy is often unsatisfactory. In particular, the detection accuracy of small-scale ships is much lower than that of the large-scale ones. To this end, in this paper, we propose a hierarchical scale sensitive CenterNet (HSSCenterNet) for ship detection from remote sensing images. HSSCenterNet adopts a multi-task learning strategy. First, it presents a dual-direction vector to represent the posture or direction of the tilted bounding box, and employs a two-layer network to predict the dual direction vector, which improves the detection block of CenterNet, and cultivates the ability of detecting targets with tilted posture. Second, it divides the full-scale detection task into three parallel sub-tasks for large-scale, medium-scale, and small-scale ship detection, respectively, and obtains the final results with non-maximum suppression. Experimental results show that, HSSCenterNet achieves a significant improved performance in detecting small-scale ship targets while maintaining a high performance at medium and large scales.

Download Full-text

Real-Time Detection of Railway Track Component via One-Stage Deep Learning Networks

Sensors ◽

10.3390/s20154325 ◽

2020 ◽

Vol 20 (15) ◽

pp. 4325

Author(s):

Tiange Wang ◽

Fangfang Yang ◽

Kwok-Leung Tsui

Keyword(s):

Deep Learning ◽

Learning Technologies ◽

Railway Track ◽

Detection Accuracy ◽

Learning Approaches ◽

Learning Networks ◽

Railway Transportation ◽

One Stage ◽

Input Size ◽

Feature Pyramid

Railway inspection has always been a critical task to guarantee the safety of the railway transportation. The development of deep learning technologies brings new breakthroughs in the accuracy and speed of image-based railway inspection application. In this work, a series of one-stage deep learning approaches, which are fast and accurate at the same time, are proposed to inspect the key components of railway track including rail, bolt, and clip. The inspection results show that the enhanced model, the second version of you only look once (YOLOv2), presents the best component detection performance with 93% mean average precision (mAP) at 35 image per second (IPS), whereas the feature pyramid network (FPN) based model provides a smaller mAP and much longer inference time. Besides, the detection performances of more deep learning approaches are evaluated under varying input sizes, where larger input size usually improves the detection accuracy but results in a longer inference time. Overall, the YOLO series models could achieve faster speed under the same detection accuracy.

Download Full-text

YOLOv3-Lite: A Lightweight Crack Detection Network for Aircraft Structure Based on Depthwise Separable Convolutions

Applied Sciences ◽

10.3390/app9183781 ◽

2019 ◽

Vol 9 (18) ◽

pp. 3781 ◽

Cited By ~ 5

Author(s):

Yadan Li ◽

Zhenqi Han ◽

Haoyu Xu ◽

Lizhuang Liu ◽

Xiaoqiang Li ◽

...

Keyword(s):

High Resolution ◽

Crack Detection ◽

Detection Method ◽

State Of The Art ◽

Aviation Industry ◽

Detection Accuracy ◽

Aircraft Structure ◽

Aircraft Structures ◽

Backbone Network ◽

Feature Pyramid

Due to the high proportion of aircraft faults caused by cracks in aircraft structures, crack inspection in aircraft structures has long played an important role in the aviation industry. The existing approaches, however, are time-consuming or have poor accuracy, given the complex background of aircraft structure images. In order to solve these problems, we propose the YOLOv3-Lite method, which combines depthwise separable convolution, feature pyramids, and YOLOv3. Depthwise separable convolution is employed to design the backbone network for reducing parameters and for extracting crack features effectively. Then, the feature pyramid joins together low-resolution, semantically strong features at a high-resolution for obtaining rich semantics. Finally, YOLOv3 is used for the bounding box regression. YOLOv3-Lite is a fast and accurate crack detection method, which can be used on aircraft structure such as fuselage or engine blades. The result shows that, with almost no loss of detection accuracy, the speed of YOLOv3-Lite is 50% more than that of YOLOv3. It can be concluded that YOLOv3-Lite can reach state-of-the-art performance.

Download Full-text

A Vehicle Detection Model Based on 5G-V2X for Smart City Security Perception

Wireless Communications and Mobile Computing ◽

10.1155/2021/5237568 ◽

2021 ◽

Vol 2021 ◽

pp. 1-11

Author(s):

Teng Liu ◽

Cheng Xu ◽

Hongzhe Liu ◽

Xuewei Li ◽

Pengfei Wang

Keyword(s):

Feature Extraction ◽

Smart City ◽

Feature Fusion ◽

Smart Cities ◽

Vehicle Detection ◽

Small Scale ◽

Detection Accuracy ◽

Data Set ◽

Prediction Ability ◽

Detection Speed

Security perception systems based on 5G-V2X have become an indispensable part of smart city construction. However, the detection speed of traditional deep learning models is slow, and the low-latency characteristics of 5G networks cannot be fully utilized. In order to improve the safety perception ability based on 5G-V2X, increase the detection speed in vehicle perception. A vehicle perception model is proposed. First, an adaptive feature extraction method is adopted to enhance the expression of small-scale features and improve the feature extraction ability of small-scale targets. Then, by improving the feature fusion method, the shallow information is fused layer by layer to solve the problem of feature loss. Finally, the attention enhancement method is introduced to increase the center point prediction ability and solve the problem of target occlusion. The experimental results show that the UA-DETRAC data set has a good detection effect. Compared with the vehicle detection capability before the improvement, the detection accuracy and speed have been greatly improved, which effectively improves the security perception capability based on the 5G-V2X system, thereby promoting the construction of smart cities.

Download Full-text

An Enhanced Feature Pyramid Object Detection Network for Autonomous Driving

Applied Sciences ◽

10.3390/app9204363 ◽

2019 ◽

Vol 9 (20) ◽

pp. 4363 ◽

Cited By ~ 3

Author(s):

Yutian Wu ◽

Shuming Tang ◽

Shuwei Zhang ◽

Harutoshi Ogai

Keyword(s):

Feature Extraction ◽

Object Detection ◽

Autonomous Driving ◽

Detection Accuracy ◽

Parallel Detection ◽

Occluded Objects ◽

Feature Weight ◽

Time Requirements ◽

Feature Pyramid ◽

High Level

Feature Pyramid Network (FPN) builds a high-level semantic feature pyramid and detects objects of different scales in corresponding pyramid levels. Usually, features within the same pyramid levels have the same weight for subsequent object detection, which ignores the feature requirements of different scale objects. As we know, for most detection networks, it is hard to detect small objects and occluded objects because there is little information to exploit. To solve the above problems, we propose an Enhanced Feature Pyramid Object Detection Network (EFPN), which innovatively constructs an enhanced feature extraction subnet and adaptive parallel detection subnet. Enhanced feature extraction subnet introduces Feature Weight Module (FWM) to enhance pyramid features by weighting the fusion feature map. Adaptive parallel detection subnet introduces Adaptive Context Expansion (ACE) and Parallel Detection Branch (PDB). ACE aims to generate the features of adaptively enlarged object context region and original region. PDB predicts classification and regression results separately with the two features. Experiments showed that EFPN outperforms FPN in detection accuracy on Pascal VOC and KITTI datasets. Furthermore, the performance of EFPN meets the real-time requirements of autonomous driving systems.

Download Full-text

Underwater Biological Detection Algorithm Based on Improved Faster-RCNN

Water ◽

10.3390/w13172420 ◽

2021 ◽

Vol 13 (17) ◽

pp. 2420

Author(s):

Pengfei Shi ◽

Xiwang Xu ◽

Jianjun Ni ◽

Yuanxue Xin ◽

Weisheng Huang ◽

...

Keyword(s):

Feature Extraction ◽

Feature Fusion ◽

Detection Algorithm ◽

Training Data ◽

Ecological Environment ◽

Detection Accuracy ◽

Biological Detection ◽

Multi Scale ◽

Feature Pyramid ◽

Bounding Boxes

Underwater organisms are an important part of the underwater ecological environment. More and more attention has been paid to the perception of underwater ecological environment by intelligent means, such as machine vision. However, many objective reasons affect the accuracy of underwater biological detection, such as the low-quality image, different sizes or shapes, and overlapping or occlusion of underwater organisms. Therefore, this paper proposes an underwater biological detection algorithm based on improved Faster-RCNN. Firstly, the ResNet is used as the backbone feature extraction network of Faster-RCNN. Then, BiFPN (Bidirectional Feature Pyramid Network) is used to build a ResNet–BiFPN structure which can improve the capability of feature extraction and multi-scale feature fusion. Additionally, EIoU (Effective IoU) is used to replace IoU to reduce the proportion of redundant bounding boxes in the training data. Moreover, K-means++ clustering is used to generate more suitable anchor boxes to improve detection accuracy. Finally, the experimental results show that the detection accuracy of underwater biological detection algorithm based on improved Faster-RCNN on URPC2018 dataset is improved to 88.94%, which is 8.26% higher than Faster-RCNN. The results fully prove the effectiveness of the proposed algorithm.

Download Full-text

A Model-Based Tool for Assessing the Impact of Land Use Change Scenarios on Flood Risk in Small-Scale River Systems—Part 1: Pre-Processing of Scenario Based Flood Characteristics for the Current State of Land Use

Hydrology ◽

10.3390/hydrology8030102 ◽

2021 ◽

Vol 8 (3) ◽

pp. 102

Author(s):

Frauke Kachholz ◽

Jens Tränckner

Keyword(s):

Land Use ◽

River Flow ◽

Land Use Changes ◽

Small Rivers ◽

Small Scale ◽

Model Parameters ◽

Ungauged Catchments ◽

Model Based ◽

Current State ◽

The Impact

Land use changes influence the water balance and often increase surface runoff. The resulting impacts on river flow, water level, and flood should be identified beforehand in the phase of spatial planning. In two consecutive papers, we develop a model-based decision support system for quantifying the hydrological and stream hydraulic impacts of land use changes. Part 1 presents the semi-automatic set-up of physically based hydrological and hydraulic models on the basis of geodata analysis for the current state. Appropriate hydrological model parameters for ungauged catchments are derived by a transfer from a calibrated model. In the regarded lowland river basins, parameters of surface and groundwater inflow turned out to be particularly important. While the calibration delivers very good to good model results for flow (Evol =2.4%, R = 0.84, NSE = 0.84), the model performance is good to satisfactory (Evol = −9.6%, R = 0.88, NSE = 0.59) in a different river system parametrized with the transfer procedure. After transferring the concept to a larger area with various small rivers, the current state is analyzed by running simulations based on statistical rainfall scenarios. Results include watercourse section-specific capacities and excess volumes in case of flooding. The developed approach can relatively quickly generate physically reliable and spatially high-resolution results. Part 2 builds on the data generated in part 1 and presents the subsequent approach to assess hydrologic/hydrodynamic impacts of potential land use changes.

Download Full-text

A Research on Landslides Automatic Extraction Model Based on the Improved Mask R-CNN

ISPRS International Journal of Geo-Information ◽

10.3390/ijgi10030168 ◽

2021 ◽

Vol 10 (3) ◽

pp. 168

Author(s):

Peng Liu ◽

Yongming Wei ◽

Qinjun Wang ◽

Jingjing Xie ◽

Yu Chen ◽

...

Keyword(s):

Remote Sensing Data ◽

Extraction Methods ◽

New Method ◽

Detection Accuracy ◽

Sufficient Information ◽

Automatic Extraction ◽

Emergency Rescue ◽

Feature Pyramid ◽

High Level ◽

Extraction Model

Landslides are the most common and destructive secondary geological hazards caused by earthquakes. It is difficult to extract landslides automatically based on remote sensing data, which is import for the scenario of disaster emergency rescue. The literature review showed that the current landslides extraction methods mostly depend on expert interpretation which was low automation and thus was unable to provide sufficient information for earthquake rescue in time. To solve the above problem, an end-to-end improved Mask R-CNN model was proposed. The main innovations of this paper were (1) replacing the feature extraction layer with an effective ResNeXt module to extract the landslides. (2) Increasing the bottom-up channel in the feature pyramid network to make full use of low-level positioning and high-level semantic information. (3) Adding edge losses to the loss function to improve the accuracy of the landslide boundary detection accuracy. At the end of this paper, Jiuzhaigou County, Sichuan Province, was used as the study area to evaluate the new model. Results showed that the new method had a precision of 95.8%, a recall of 93.1%, and an overall accuracy (OA) of 94.7%. Compared with the traditional Mask R-CNN model, they have been significantly improved by 13.9%, 13.4%, and 9.9%, respectively. It was proved that the new method was effective in the landslides automatic extraction.

Download Full-text