SAR Target Detection Based on Improved SSD with Saliency Map and Residual Network

A target detection method based on an improved single shot multibox detector (SSD) is proposed to solve insufficient training samples for synthetic aperture radar (SAR) target detection. We propose two strategies to improve the SSD: model structure optimization and small sample augmentation. For model structure optimization, the first approach is to extract deep features of the target with residual networks instead of with VGGNet. Then, the aspect ratios of the default boxes are redesigned to match the different targets’ sizes. For small sample augmentation, besides the routine image processing methods, such as rotating, translating, and mirroring, enough training samples are obtained based on the saliency map theory in machine vision. Lastly, a simulated SAR image dataset called Geometric Objects (GO) is constructed, which contains dihedral angles, surface plates and cylinders. The experimental results on the GO-simulated image dataset and the MSTAR real image dataset demonstrate that the proposed method has better performance in SAR target detection than other detection methods.

Download Full-text

TWC-Net: A SAR Ship Detection Using Two-Way Convolution and Multiscale Feature Mapping

Remote Sensing ◽

10.3390/rs13132558 ◽

2021 ◽

Vol 13 (13) ◽

pp. 2558

Author(s):

Lei Yu ◽

Haoyu Wu ◽

Zhi Zhong ◽

Liying Zheng ◽

Qiuyue Deng ◽

...

Keyword(s):

Target Detection ◽

Detection Methods ◽

Observation System ◽

Single Shot ◽

Small Target ◽

Feature Mapping ◽

Sar Images ◽

Two Stage ◽

Ship Detection ◽

Deep Feature

Synthetic aperture radar (SAR) is an active earth observation system with a certain surface penetration capability and can be employed to observations all-day and all-weather. Ship detection using SAR is of great significance to maritime safety and port management. With the wide application of in-depth learning in ordinary images and good results, an increasing number of detection algorithms began entering the field of remote sensing images. SAR image has the characteristics of small targets, high noise, and sparse targets. Two-stage detection methods, such as faster regions with convolution neural network (Faster RCNN), have good results when applied to ship target detection based on the SAR graph, but their efficiency is low and their structure requires many computing resources, so they are not suitable for real-time detection. One-stage target detection methods, such as single shot multibox detector (SSD), make up for the shortage of the two-stage algorithm in speed but lack effective use of information from different layers, so it is not as good as the two-stage algorithm in small target detection. We propose the two-way convolution network (TWC-Net) based on a two-way convolution structure and use multiscale feature mapping to process SAR images. The two-way convolution module can effectively extract the feature from SAR images, and the multiscale mapping module can effectively process shallow and deep feature information. TWC-Net can avoid the loss of small target information during the feature extraction, while guaranteeing good perception of a large target by the deep feature map. We tested the performance of our proposed method using a common SAR ship dataset SSDD. The experimental results show that our proposed method has a higher recall rate and precision, and the F-Measure is 93.32%. It has smaller parameters and memory consumption than other methods and is superior to other methods.

Download Full-text

DBA_SSD: A Novel End-to-End Object Detection Algorithm Applied to Plant Disease Detection

Information ◽

10.3390/info12110474 ◽

2021 ◽

Vol 12 (11) ◽

pp. 474

Author(s):

Jun Wang ◽

Liya Yu ◽

Jing Yang ◽

Hao Dong

Keyword(s):

Feature Extraction ◽

Target Detection ◽

Attention Mechanism ◽

Detection Methods ◽

Disease Detection ◽

Plant Leaves ◽

Plant Leaf ◽

Detection Algorithms ◽

Leaf Disease ◽

Image Dataset

In response to the difficulty of plant leaf disease detection and classification, this study proposes a novel plant leaf disease detection method called deep block attention SSD (DBA_SSD) for disease identification and disease degree classification of plant leaves. We propose three plant leaf detection methods, namely, squeeze-and-excitation SSD (Se_SSD), deep block SSD (DB_SSD), and DBA_SSD. Se_SSD fuses SSD feature extraction network and attention mechanism channel, DB_SSD improves VGG feature extraction network, and DBA_SSD fuses the improved VGG network and channel attention mechanism. To reduce the training time and accelerate the training process, the convolutional layers trained in the Image Net image dataset by the VGG model are migrated to this model, whereas the collected plant leaves disease image dataset is randomly divided into training set, validation set, and test set in the ratio of 8:1:1. We chose the PlantVillage dataset after careful consideration because it contains images related to the domain of interest. This dataset consists of images of 14 plants, including images of apples, tomatoes, strawberries, peppers, and potatoes, as well as the leaves of other plants. In addition, data enhancement methods, such as histogram equalization and horizontal flip were used to expand the image data. The performance of the three improved algorithms is compared and analyzed in the same environment and with the classical target detection algorithms YOLOv4, YOLOv3, Faster RCNN, and YOLOv4 tiny. Experiments show that DBA_SSD outperforms the two other improved algorithms, and its performance in comparative analysis is superior to other target detection algorithms.

Download Full-text

DBA_SSD ： A Novel End-to-End Object Detection Using Deep Attention Module for Helping Smart Device with Vegetable and Fruit Leaf Plant Disease Detection

10.21203/rs.3.rs-166579/v1 ◽

2021 ◽

Author(s):

Jun Wang ◽

Jing Yang ◽

Liya Yu ◽

Hao Dong ◽

Kun Yun ◽

...

Keyword(s):

Feature Extraction ◽

Target Detection ◽

Attention Mechanism ◽

Detection Methods ◽

Smart Device ◽

Training Time ◽

Pests And Diseases ◽

Detection Algorithms ◽

Image Dataset ◽

Pest Detection

Abstract In response to the difficulty of detecting and classifying pests and vegetable and fruit leaves with pests and diseases, this study proposes a novel vegetable and fruit leaf pest detection method called deep block attention SSD (DBA_SSD) for the identification of pests and diseases and classification of the degree of pests and diseases of vegetable and fruit leaves. We propose three vegetable and fruit leaf pest detection methods, namely, squeeze-and excitation SSD (Se_SSD), DB_SSD, and DBA_SSD. Se_SSD fuses SSD feature extraction network and attention mechanism channel, DB_SSD improves VGG feature extraction network, and DBA_SSD fuses the improved VGG network and channel attention mechanism. To reduce the training time and accelerate the training process, the convolutional layers trained in the Image Net image dataset by the VGG model are migrated to this model, whereas the collected vegetable and fruit disease image dataset is randomly divided into training set, validation set, and test set in the ratio of 8:1:1. In addition, data enhancement methods, such as histogram equalization and horizontal flip were used to expand the image data. The performance of the three improved algorithms is compared and analyzed in the same environment and with the classical target detection algorithms YOLOv4, YOLOv3, Faster RCNN, and YOLOv4 tiny. Experiments show that DBA_SSD outperforms the two other improved algorithms, and its performance in comparative analysis is superior to other target detection algorithms.

Download Full-text

CISPNet: Automatic Detection of Remote Sensing Images from Google Earth in Complex Scenes Based on Context Information Scene Perception

Applied Sciences ◽

10.3390/app9224836 ◽

2019 ◽

Vol 9 (22) ◽

pp. 4836 ◽

Cited By ~ 3

Author(s):

Wenxu Shi ◽

Jinhong Jiang ◽

Shengli Bao ◽

Dailun Tan

Keyword(s):

Remote Sensing ◽

Scene Perception ◽

Remote Sensing Image ◽

Google Earth ◽

Visual Object ◽

Context Information ◽

Single Shot ◽

Aspect Ratios ◽

Image Dataset ◽

Better Than

The ability to detect small targets and the speed of the target detector are very important for the application of remote sensing image detection, and in this paper, we propose an effective and efficient method (named CISPNet) with high detection accuracy and compact architecture. In particular, according to the characteristics of the data, we apply a context information scene perception (CISP) module to obtain the contextual information for targets of different scales and use k-means clustering to set the aspect ratios and size of the default boxes. The proposed method inherits the network structure of Single Shot MultiBox Detector (SSD) and introduces the CISP module into it. We create a dataset in the Pascal Visual Object Classes (VOC) format, annotated with the three types of detection targets, aircraft, ship, and oiltanker. Experimental results on our remote sensing image dataset as well as the Northwestern Polytechnical University very-high-resolution (NWPU VRH-10) dataset demonstrate that the proposed CISPNet performs much better than the original SSD and other detectors especially for small objects. Specifically, our network can achieve 80.34% mean average precision (mAP) at the speed of 50.7 frames per second (FPS) with the input size 300 × 300 pixels on the remote sensing image dataset. On extended experiments, the performance of CISPNet in fuzzy target detection in remote sensing image is better than that of SSD.

Download Full-text

A Pipeline Abnormal Signal Detection Method Based on 1D-Faster R-CNN

Fuzzy Systems and Data Mining VI - Frontiers in Artificial Intelligence and Applications ◽

10.3233/faia200712 ◽

2020 ◽

Author(s):

Zhen Zhang ◽

Weiguo Lin

Keyword(s):

Target Detection ◽

Small Sample ◽

Experimental Results ◽

New Method ◽

False Alarms ◽

Original Sample ◽

Abnormal Signal ◽

Location Method ◽

Training Samples ◽

Recognition Errors

Aimed at the detection difficulty of local abnormal signals during pipeline operation, this paper takes the local abnormal signals as the detected targets, and proposes a new method based on target detection to extract abnormal signals with different amplitude and shape; and for the case where there are few actual leak samples, combined with the characteristics that the training samples of each module of the model itself are derivative samples of the original sample, so as to realize the small sample training of the model. Finally, a new pipeline leak detection and location method is proposed by combining the 1D-faster R-CNN with the cross-correlation location method based on signal matching. The experimental results show that the proposed method effectively extracts local abnormal signals, accurately alarms leak signals, and eliminates the false alarms caused by the recognition errors of normal signals.

Download Full-text

Building Damage Detection from Post-Event Aerial Imagery Using Single Shot Multibox Detector

Applied Sciences ◽

10.3390/app9061128 ◽

2019 ◽

Vol 9 (6) ◽

pp. 1128 ◽

Cited By ~ 12

Author(s):

Yundong Li ◽

Wei Hu ◽

Han Dong ◽

Xueyan Zhang

Keyword(s):

Machine Learning ◽

Data Augmentation ◽

Hurricane Sandy ◽

Training Data ◽

Aerial Images ◽

Detection Methods ◽

Single Shot ◽

Data Set ◽

Augmentation Strategies ◽

Post Disaster

Using aerial cameras, satellite remote sensing or unmanned aerial vehicles (UAV) equipped with cameras can facilitate search and rescue tasks after disasters. The traditional manual interpretation of huge aerial images is inefficient and could be replaced by machine learning-based methods combined with image processing techniques. Given the development of machine learning, researchers find that convolutional neural networks can effectively extract features from images. Some target detection methods based on deep learning, such as the single-shot multibox detector (SSD) algorithm, can achieve better results than traditional methods. However, the impressive performance of machine learning-based methods results from the numerous labeled samples. Given the complexity of post-disaster scenarios, obtaining many samples in the aftermath of disasters is difficult. To address this issue, a damaged building assessment method using SSD with pretraining and data augmentation is proposed in the current study and highlights the following aspects. (1) Objects can be detected and classified into undamaged buildings, damaged buildings, and ruins. (2) A convolution auto-encoder (CAE) that consists of VGG16 is constructed and trained using unlabeled post-disaster images. As a transfer learning strategy, the weights of the SSD model are initialized using the weights of the CAE counterpart. (3) Data augmentation strategies, such as image mirroring, rotation, Gaussian blur, and Gaussian noise processing, are utilized to augment the training data set. As a case study, aerial images of Hurricane Sandy in 2012 were maximized to validate the proposed method’s effectiveness. Experiments show that the pretraining strategy can improve of 10% in terms of overall accuracy compared with the SSD trained from scratch. These experiments also demonstrate that using data augmentation strategies can improve mAP and mF1 by 72% and 20%, respectively. Finally, the experiment is further verified by another dataset of Hurricane Irma, and it is concluded that the paper method is feasible.

Download Full-text

ER rule classifier with an optimization operator recommendation

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-210629 ◽

2021 ◽

pp. 1-13

Author(s):

Xiaoyan Wang ◽

Jianbin Sun ◽

Qingsong Zhao ◽

Yaqian You ◽

Jiang Jiang

Keyword(s):

Classification Accuracy ◽

Comprehensive Analysis ◽

Small Sample ◽

Empirical Knowledge ◽

Classification Methods ◽

Turbofan Engine ◽

Training Samples ◽

Optimization Operator ◽

Recommendation Strategy

It is difficult for many classic classification methods to consider expert experience and classify small-sample datasets well. The evidential reasoning rule (ER rule) classifier can solve these problems. The ER rule has strong processing and comprehensive analysis abilities for diversified mixed information and can solve problems with expert experience effectively. Moreover, the initial parameters of the classifier constructed based on the ER rule can be set according to empirical knowledge instead of being trained by a large number of samples, which can help the classifier classify small-sample datasets well. However, the initial parameters of the ER rule classifier need to be optimized, and choosing the best optimization algorithm is still a challenge. Considering these problems, the ER rule classifier with an optimization operator recommendation is proposed in this paper. First, the initial ER rule classifier is constructed based on training samples and expert experience. Second, the adjustable parameters are optimized, in which the optimization operator recommendation strategy is applied to select the best algorithm by partial samples, and then experiments with full samples are carried out. Finally, a case study on a turbofan engine degradation simulation dataset is carried out, and the results indicate that the ER rule classifier has a higher classification accuracy than other classic classifiers, which demonstrates the capability and effectiveness of the proposed ER rule classifier with an optimization operator recommendation.

Download Full-text

On Combining DeepSnake and Global Saliency for Detection of Orchard Apples

Applied Sciences ◽

10.3390/app11146269 ◽

2021 ◽

Vol 11 (14) ◽

pp. 6269

Author(s):

Wang Jing ◽

Wang Leqi ◽

Han Yanling ◽

Zhang Yun ◽

Zhou Ruyan

Keyword(s):

Saliency Detection ◽

Color Difference ◽

Saliency Map ◽

Apple Fruit ◽

Initial Contour ◽

Detection Accuracy ◽

Natural Environments ◽

Fast Detection ◽

Single Target ◽

Training Samples

For the fast detection and recognition of apple fruit targets, based on the real-time DeepSnake deep learning instance segmentation model, this paper provided an algorithm basis for the practical application and promotion of apple picking robots. Since the initial detection results have an important impact on the subsequent edge prediction, this paper proposed an automatic detection method for apple fruit targets in natural environments based on saliency detection and traditional color difference methods. Combined with the original image, the histogram backprojection algorithm was used to further optimize the salient image results. A dynamic adaptive overlapping target separation algorithm was proposed to locate the single target fruit and further to determine the initial contour for DeepSnake, in view of the possible overlapping fruit regions in the saliency map. Finally, the target fruit was labeled based on the segmentation results of the examples. In the experiment, 300 training datasets were used to train the DeepSnake model, and the self-built dataset containing 1036 pictures of apples in various situations under natural environment was tested. The detection accuracy of target fruits under non-overlapping shaded fruits, overlapping fruits, shaded branches and leaves, and poor illumination conditions were 99.12%, 94.78%, 90.71%, and 94.46% respectively. The comprehensive detection accuracy was 95.66%, and the average processing time was 0.42 s in 1036 test images, which showed that the proposed algorithm can effectively separate the overlapping fruits through a not-very-large training samples and realize the rapid and accurate detection of apple targets.

Download Full-text

Target Detection Network for SAR Images Based on Semi-Supervised Learning and Attention Mechanism

Remote Sensing ◽

10.3390/rs13142686 ◽

2021 ◽

Vol 13 (14) ◽

pp. 2686

Author(s):

Di Wei ◽

Yuang Du ◽

Lan Du ◽

Lu Li

Keyword(s):

Feature Extraction ◽

Supervised Learning ◽

Target Detection ◽

Scene Recognition ◽

Attention Mechanism ◽

Sar Image ◽

Target Level ◽

Sar Images ◽

Training Samples ◽

Pass Through

The existing Synthetic Aperture Radar (SAR) image target detection methods based on convolutional neural networks (CNNs) have achieved remarkable performance, but these methods require a large number of target-level labeled training samples to train the network. Moreover, some clutter is very similar to targets in SAR images with complex scenes, making the target detection task very difficult. Therefore, a SAR target detection network based on a semi-supervised learning and attention mechanism is proposed in this paper. Since the image-level label simply marks whether the image contains the target of interest or not, which is easier to be labeled than the target-level label, the proposed method uses a small number of target-level labeled training samples and a large number of image-level labeled training samples to train the network with a semi-supervised learning algorithm. The proposed network consists of a detection branch and a scene recognition branch with a feature extraction module and an attention module shared between these two branches. The feature extraction module can extract the deep features of the input SAR images, and the attention module can guide the network to focus on the target of interest while suppressing the clutter. During the semi-supervised learning process, the target-level labeled training samples will pass through the detection branch, while the image-level labeled training samples will pass through the scene recognition branch. During the test process, considering the help of global scene information in SAR images for detection, a novel coarse-to-fine detection procedure is proposed. After the coarse scene recognition determining whether the input SAR image contains the target of interest or not, the fine target detection is performed on the image that may contain the target. The experimental results based on the measured SAR dataset demonstrate that the proposed method can achieve better performance than the existing methods.

Download Full-text

Robust and fast post-processing of single-shot spin qubit detection events with a neural network

Scientific Reports ◽

10.1038/s41598-021-95562-x ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Tom Struck ◽

Javed Lindner ◽

Arne Hollmann ◽

Floyd Schauer ◽

Andreas Schmidbauer ◽

...

Keyword(s):

Neural Network ◽

Neural Networks ◽

Bayesian Inference ◽

Rabi Oscillation ◽

Detection Methods ◽

Measured Signal ◽

Single Shot ◽

Post Processing ◽

Readout Signal ◽

Spin Qubit

AbstractEstablishing low-error and fast detection methods for qubit readout is crucial for efficient quantum error correction. Here, we test neural networks to classify a collection of single-shot spin detection events, which are the readout signal of our qubit measurements. This readout signal contains a stochastic peak, for which a Bayesian inference filter including Gaussian noise is theoretically optimal. Hence, we benchmark our neural networks trained by various strategies versus this latter algorithm. Training of the network with 106 experimentally recorded single-shot readout traces does not improve the post-processing performance. A network trained by synthetically generated measurement traces performs similar in terms of the detection error and the post-processing speed compared to the Bayesian inference filter. This neural network turns out to be more robust to fluctuations in the signal offset, length and delay as well as in the signal-to-noise ratio. Notably, we find an increase of 7% in the visibility of the Rabi oscillation when we employ a network trained by synthetic readout traces combined with measured signal noise of our setup. Our contribution thus represents an example of the beneficial role which software and hardware implementation of neural networks may play in scalable spin qubit processor architectures.

Download Full-text