An Approach on Image Processing of Deep Learning Based on Improved SSD

Jin, Liang; Liu, Guodong

doi:10.3390/sym13030495

Cited by 30 publications

(10 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nowadays, when using SSDD, many scholars in the SAR ship detection community adopt different input sizes in their different networks, e.g., 160 × 160 in Zhang et al [65], 300 × 300 in Wang et al [31], 500 × 500 in Jian et al [89], 512 × 512 in Zhang et al [73], 600 × 600 in Yu et al [97], 600 × 1000 in Wei et al [51], and so on. This leads to an unreasonable comparison of methods in accuracy.…”

Section: Discussionmentioning

confidence: 99%

SAR Ship Detection Dataset (SSDD): Official Release and Comprehensive Data Analysis

et al. 2021

View full text Add to dashboard Cite

SAR Ship Detection Dataset (SSDD) is the first open dataset that is widely used to research state-of-the-art technology of ship detection from synthetic aperture radar (SAR) imagery based on deep learning (DL). According to our investigation, up to 46.59% of the total 161 public reports confidently select SSDD to study DL-based SAR ship detection. Undoubtedly, this situation reveals the popularity and great influence of SSDD in the SAR remote sensing community. Nevertheless, the coarse annotations and ambiguous standards of use of its initial version both hinder fair methodological comparisons and effective academic exchanges. Additionally, its single-function horizontal-vertical rectangle bounding box (BBox) labels can no longer satisfy the current research needs of the rotatable bounding box (RBox) task and the pixel-level polygon segmentation task. Therefore, to address the above two dilemmas, in this review, advocated by the publisher of SSDD, we will make an official release of SSDD based on its initial version. SSDD’s official release version will cover three types: (1) a bounding box SSDD (BBox-SSDD), (2) a rotatable bounding box SSDD (RBox-SSDD), and (3) a polygon segmentation SSDD (PSeg-SSDD). We relabel ships in SSDD more carefully and finely, and then explicitly formulate some strict using standards, e.g., (1) the training-test division determination, (2) the inshore-offshore protocol, (3) the ship-size reasonable definition, (4) the determination of the densely distributed small ship samples, and (5) the determination of the densely parallel berthing at ports ship samples. These using standards are all formulated objectively based on the using differences of existing 75 (161 × 46.59%) public reports. They will be beneficial for fair method comparison and effective academic exchanges in the future. Most notably, we conduct a comprehensive data analysis on BBox-SSDD, RBox-SSDD, and PSeg-SSDD. Our analysis results can provide some valuable suggestions for possible future scholars to further elaborately design DL-based SAR ship detectors with higher accuracy and stronger robustness when using SSDD.

show abstract

Section: Discussionmentioning

confidence: 99%

SAR Ship Detection Dataset (SSDD): Official Release and Comprehensive Data Analysis

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Similarly, Lin Z, et al proposed a new fast R-CNN-based network structure based on high-resolution SAR images to further improve ship detection performance by using a squeeze excitation mechanism [16,17]. Jin L., et al used the SSD model and added a feature fusion module to the shallow feature layer to optimize the feature extraction capability for small objects, and then added the squeeze and excitation network (SE) module to each feature layer to introduce an attention mechanism for the network to achieve small-scale ship detection in remote sensing images [18,19]. Wang Y combined single-shot multibox detector (SSD) with migration learning to solve the ship detection problem in complex environments, such as oceans and islands [20].…”

Section: Related Workmentioning

confidence: 99%

Multi-Sensor-Based Hierarchical Detection and Tracking Method for Inland Waterway Ship Chimneys

Chen

Wen

et al. 2022

JMSE

View full text Add to dashboard Cite

In the field of automatic detection of ship exhaust behavior, a deep learning-based multi-sensor hierarchical detection method for tracking inland river ship chimneys is proposed to locate the ship exhaust behavior detection area quickly and accurately. Firstly, the primary detection uses a target detector based on a convolutional neural network to extract the shipping area in the visible image, and the secondary detection applies the Ostu binarization algorithm and image morphology operation, based on the infrared image and the primary detection results to obtain the chimney target by combining the location and area features; further, the improved DeepSORT algorithm is applied to achieve the ship chimney tracking. The results show that the multi-sensor-based hierarchical detection and tracking method can achieve real-time detection and tracking of ship chimneys, and can provide technical reference for the automatic detection of ship exhaust behavior.

show abstract

“…It is suitable for the real-time detector system. However, the SSD algorithm also has some flaws, facing small workpieces with insignificant features, stacked workpieces, workpieces of different types but similar shapes, weak robustness, high missed detection rate, and false detection rate, which cannot meet the requirements for accurate detection [9][10][11][12]. To improve the extraction capacity of the network features, Yang et al [13] proposed a DSSD algorithm based on the VGG backbone network.…”

Section: Introductionmentioning

confidence: 99%

Pipeline Multitype Artifact Recognition Method Based on Inception_Resnet _V2 Structure Improving SSD Network

Zheng

2022

Advances in Multimedia

View full text Add to dashboard Cite

A fast recognition method for assembly line workpieces based on an improved SSD model is proposed to address the problems of low detection accuracy and lack of real-time performance when existing target detection models face small-scale targets and stacked targets. Based on the SSD network, the optimized Inception_Resnet _V2 structure is used to improve its feature extraction layer and enhance the extraction capability of the network for small-scale targets. The repulsion loss (Reploss) is used to optimize the loss function of the SSD network to solve the problem of stacked workpieces. The issue of difficult detection is improved. The robustness of the algorithm is enhanced. The experimental results show that the improved SSD target detection method improves the detection accuracy by 9.69% over the traditional SSD map. The detection speed meets the real-time requirements, which is a better balance of detection real time and accuracy requirements. The algorithm can recognize small-scale and stacked targets with higher category confidence, better algorithm robustness, and better recognition performance compared to the same type of target detection algorithms.

show abstract

An Approach on Image Processing of Deep Learning Based on Improved SSD

Cited by 30 publications

References 39 publications

SAR Ship Detection Dataset (SSDD): Official Release and Comprehensive Data Analysis

SAR Ship Detection Dataset (SSDD): Official Release and Comprehensive Data Analysis

Multi-Sensor-Based Hierarchical Detection and Tracking Method for Inland Waterway Ship Chimneys

Pipeline Multitype Artifact Recognition Method Based on Inception_Resnet _V2 Structure Improving SSD Network

Contact Info

Product

Resources

About