Depthwise Separable Convolution Neural Network for High-Speed SAR Ship Detection

As an active microwave imaging sensor for the high-resolution earth observation, synthetic aperture radar (SAR) has been extensively applied in military, agriculture, geology, ecology, oceanography, etc., due to its prominent advantages of all-weather and all-time working capacity. Especially, in the marine field, SAR can provide numerous high-quality services for fishery management, traffic control, sea-ice monitoring, marine environmental protection, etc. Among them, ship detection in SAR images has attracted more and more attention on account of the urgent requirements of maritime rescue and military strategy formulation. Nowadays, most researches are focusing on improving the ship detection accuracy, while the detection speed is frequently neglected, regardless of traditional feature extraction methods or modern deep learning (DL) methods. However, the high-speed SAR ship detection is of great practical value, because it can provide real-time maritime disaster rescue and emergency military planning. Therefore, in order to address this problem, we proposed a novel high-speed SAR ship detection approach by mainly using depthwise separable convolution neural network (DS-CNN). In this approach, we integrated multi-scale detection mechanism, concatenation mechanism and anchor box mechanism to establish a brand-new light-weight network architecture for the high-speed SAR ship detection. We used DS-CNN, which consists of a depthwise convolution (D-Conv2D) and a pointwise convolution (P-Conv2D), to substitute for the conventional convolution neural network (C-CNN). In this way, the number of network parameters gets obviously decreased, and the ship detection speed gets dramatically improved. We experimented on an open SAR ship detection dataset (SSDD) to validate the correctness and feasibility of the proposed method. To verify the strong migration capacity of our method, we also carried out actual ship detection on a wide-region large-size Sentinel-1 SAR image. Ultimately, under the same hardware platform with NVIDIA RTX2080Ti GPU, the experimental results indicated that the ship detection speed of our proposed method is faster than other methods, meanwhile the detection accuracy is only lightly sacrificed compared with the state-of-art object detectors. Our method has great application value in real-time maritime disaster rescue and emergency military planning.

Download Full-text

High-Speed Ship Detection in SAR Images Based on a Grid Convolutional Neural Network

Remote Sensing ◽

10.3390/rs11101206 ◽

2019 ◽

Vol 11 (10) ◽

pp. 1206 ◽

Cited By ~ 16

Author(s):

Tianwen Zhang ◽

Xiaoling Zhang

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Real Time ◽

High Speed ◽

Earth Observation ◽

Detection Accuracy ◽

Processing Unit ◽

Sar Images ◽

Ship Detection ◽

Detection Speed

As an active microwave sensor, synthetic aperture radar (SAR) has the characteristic of all-day and all-weather earth observation, which has become one of the most important means for high-resolution earth observation and global resource management. Ship detection in SAR images is also playing an increasingly important role in ocean observation and disaster relief. Nowadays, both traditional feature extraction methods and deep learning (DL) methods almost focus on improving ship detection accuracy, and the detection speed is neglected. However, the speed of SAR ship detection is extraordinarily significant, especially in real-time maritime rescue and emergency military decision-making. In order to solve this problem, this paper proposes a novel approach for high-speed ship detection in SAR images based on a grid convolutional neural network (G-CNN). This method improves the detection speed by meshing the input image, inspired by the basic thought of you only look once (YOLO), and using depthwise separable convolution. G-CNN is a brand new network structure proposed by us and it is mainly composed of a backbone convolutional neural network (B-CNN) and a detection convolutional neural network (D-CNN). First, SAR images to be detected are divided into grid cells and each grid cell is responsible for detection of specific ships. Then, the whole image is input into B-CNN to extract features. Finally, ship detection is completed in D-CNN under three scales. We experimented on an open SAR Ship Detection Dataset (SSDD) used by many other scholars and then validated the migration ability of G-CNN on two SAR images from RadarSat-1 and Gaofen-3. The experimental results show that the detection speed of our proposed method is faster than the existing other methods, such as faster-regions convolutional neural network (Faster R-CNN), single shot multi-box detector (SSD), and YOLO, under the same hardware environment with NVIDIA GTX1080 graphics processing unit (GPU) and the detection accuracy is kept within an acceptable range. Our proposed G-CNN ship detection system has great application values in real-time maritime disaster rescue and emergency military strategy formulation.

Download Full-text

REAL-TIME VIDEO SCALING BASED ON CONVOLUTION NEURAL NETWORK ARCHITECTURE

ICTACT Journal on Image and Video Processing ◽

10.21917/ijivp.2017.0218 ◽

2017 ◽

Vol 8 (1) ◽

pp. 1533-1542

Author(s):

S Safinaz ◽

◽

A V Ravi Kumar ◽

Keyword(s):

Neural Network ◽

Real Time ◽

Network Architecture ◽

Convolution Neural Network ◽

Neural Network Architecture

Download Full-text

Real-Time Video Scaling Based on Convolution Neural Network Architecture

Indonesian Journal of Electrical Engineering and Computer Science ◽

10.11591/ijeecs.v7.i2.pp381-394 ◽

2017 ◽

Vol 7 (2) ◽

pp. 381

Author(s):

S Safinaz ◽

AV Ravi kumar

Keyword(s):

Neural Network ◽

High Resolution ◽

Real Time ◽

Network Architecture ◽

High Efficiency ◽

Super Resolution ◽

Reconstruction Error ◽

Convolution Neural Network ◽

Neural Network Architecture ◽

Video Frames

In recent years, video super resolution techniques becomes mandatory requirements to get high resolution videos. Many super resolution techniques researched but still video super resolution or scaling is a vital challenge. In this paper, we have presented a real-time video scaling based on convolution neural network architecture to eliminate the blurriness in the images and video frames and to provide better reconstruction quality while scaling of large datasets from lower resolution frames to high resolution frames. We compare our outcomes with multiple exiting algorithms. Our extensive results of proposed technique RemCNN (Reconstruction error minimization Convolution Neural Network) shows that our model outperforms the existing technologies such as bicubic, bilinear, MCResNet and provide better reconstructed motioning images and video frames. The experimental results shows that our average PSNR result is 47.80474 considering upscale-2, 41.70209 for upscale-3 and 36.24503 for upscale-4 for Myanmar dataset which is very high in contrast to other existing techniques. This results proves our proposed model real-time video scaling based on convolution neural network architecture’s high efficiency and better performance.

Download Full-text

Design of Secure Blockchain Convolution Neural Network Architecture for Detection Malware Attacks

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.f8094.038620 ◽

2020 ◽

Vol 8 (6) ◽

pp. 3055-3060

Keyword(s):

Neural Network ◽

Deep Learning ◽

Network Architecture ◽

Information Privacy ◽

Convolution Neural Network ◽

Detection Accuracy ◽

Neural Network Architecture ◽

Network Method ◽

Advance Method ◽

Learning Concept

Nowadays, Cyberattack continues to target the applications and networks more than past with different and advance ways like programming complex format of malware that it executes unauthorized action on the targeted system, so it is needed to develop and deploy advance method to these kind of attacks for detecting correctly with a trusted and a better accuracy. Therefore, the recent solutions to detect malware attacks focuses on new advance technologies like Deep learning and Machine learning concepts. In this paper we have developed secure blockchain convolution (SBC) Algorithm that provides a better way of analyzing malware data with effectiveness and accuracy. The deep learning concept does not involve in a method to identify the trust while the process is led to extraction of the features as it can be infected by the intervention of human or a trained system. Therefore, According to research which is done towards blockchain, it features as authentication function, immutable property, information privacy and safety helps in deployment of Convolution Neural Network method with better detection. Blockchain has a decentralized structure which is able to record the data between various parties and it helps in preventing the manipulation when the deep learning concept is applied and the higher detection accuracy is received in the limited time.

Download Full-text

Real-time facial emotion recognition using lightweight convolution neural network

Journal of Physics Conference Series ◽

10.1088/1742-6596/1827/1/012130 ◽

2021 ◽

Vol 1827 (1) ◽

pp. 012130

Author(s):

Qi Li ◽

Yun Qing Liu ◽

Yue Qi Peng ◽

Cong Liu ◽

Jun Shi ◽

...

Keyword(s):

Neural Network ◽

Emotion Recognition ◽

Real Time ◽

Convolution Neural Network ◽

Facial Emotion Recognition ◽

Facial Emotion

Download Full-text

Unmanned aerial vehicle reconnaissance image recognition based on convolutional neural network

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-219086 ◽

2021 ◽

pp. 1-10

Author(s):

Lipeng Si ◽

Baolong Liu ◽

Yanfang Fu

Keyword(s):

Neural Network ◽

Real Time ◽

Image Recognition ◽

Error Detection ◽

Convolution Neural Network ◽

Data Sets ◽

Small Target ◽

Network Algorithm ◽

Neural Network Algorithm ◽

Real Time Tracking

The important strategic position of military UAVs and the wide application of civil UAVs in many fields, they all mark the arrival of the era of unmanned aerial vehicles. At present, in the field of image research, recognition and real-time tracking of specific objects in images has been a technology that many scholars continue to study in depth and need to be further tackled. Image recognition and real-time tracking technology has been widely used in UAV aerial photography. Through the analysis of convolution neural network algorithm and the comparison of image recognition technology, the convolution neural network algorithm is improved to improve the image recognition effect. In this paper, a target detection technique based on improved Faster R-CNN is proposed. The algorithm model is implemented and the classification accuracy is improved through Faster R-CNN network optimization. Aiming at the problem of small target error detection and scale difference in aerial data sets, this paper designs the network structure of RPN and the optimization scheme of related algorithms. The structure of Faster R-CNN is adjusted by improving the embedding of CNN and OHEM algorithm, the accuracy of small target and multitarget detection is improved as a whole. The experimental results show that: compared with LENET-5, the recognition accuracy of the proposed algorithm is significantly improved. And with the increase of the number of samples, the accuracy of this algorithm is 98.9%.

Download Full-text

Robust Approach to Supervised Deep Neural Network Training for Real-Time Object Classification in Cluttered Indoor Environment

Applied Sciences ◽

10.3390/app11157148 ◽

2021 ◽

Vol 11 (15) ◽

pp. 7148

Author(s):

Bedada Endale ◽

Abera Tullu ◽

Hayoung Shi ◽

Beom-Soo Kang

Keyword(s):

Neural Network ◽

Deep Learning ◽

Real Time ◽

Network Architecture ◽

Input Data ◽

Deep Neural Network ◽

Data Augmentation ◽

Object Classification ◽

Training Data ◽

Gradient Descent Algorithm

Unmanned aerial vehicles (UAVs) are being widely utilized for various missions: in both civilian and military sectors. Many of these missions demand UAVs to acquire artificial intelligence about the environments they are navigating in. This perception can be realized by training a computing machine to classify objects in the environment. One of the well known machine training approaches is supervised deep learning, which enables a machine to classify objects. However, supervised deep learning comes with huge sacrifice in terms of time and computational resources. Collecting big input data, pre-training processes, such as labeling training data, and the need for a high performance computer for training are some of the challenges that supervised deep learning poses. To address these setbacks, this study proposes mission specific input data augmentation techniques and the design of light-weight deep neural network architecture that is capable of real-time object classification. Semi-direct visual odometry (SVO) data of augmented images are used to train the network for object classification. Ten classes of 10,000 different images in each class were used as input data where 80% were for training the network and the remaining 20% were used for network validation. For the optimization of the designed deep neural network, a sequential gradient descent algorithm was implemented. This algorithm has the advantage of handling redundancy in the data more efficiently than other algorithms.

Download Full-text