A Lightweight Hyperspectral Image Anomaly Detector for Real-Time Mission

In real-time onboard hyperspectral-image(HSI) anomalous targets detection, processing speed and accuracy are equivalently desirable which is hard to satisfy at the same time. To improve detection accuracy, deep learning based HSI anomaly detectors (ADs) are widely studied. However, their large scale network results in a massive computational burden. In this paper, to improve the detection throughput without sacrificing the accuracy, a pruning–quantization–anomaly–detector (P-Q-AD) is proposed by building an underlying constraint formulation to make a trade-off between accuracy and throughput. To solve this formulation, multi-objective optimization with nondominated sorting genetic algorithm II (NSGA-II) is employed to shrink the network. As a result, the redundant neurons are removed. A mixed precision network is implemented with a delicate customized fixed-point data expression to further improve the efficiency. In the experiments, the proposed P-Q-AD is implemented on two real HSI data sets and compared with three types of detectors. The results show that the performance of the proposed approach is no worse than those comparison detectors in terms of the receiver operating characteristic curve (ROC) and area under curve (AUC) value. For the onboard mission, the proposed P-Q-AD reaches over 4 . 5 × speedup with less than 0 . 5 % AUC loss compared with the floating-based detector. The pruning and the quantization approach in this paper can be referenced for designing the anomalous targets detectors for high efficiency.

Download Full-text

Real Time Power Quality Phenomenon for Various Distribution Feeders

Indonesian Journal of Electrical Engineering and Computer Science ◽

10.11591/ijeecs.v3.i1.pp10-16 ◽

2016 ◽

Vol 3 (1) ◽

pp. 10 ◽

Cited By ~ 1

Author(s):

C. Bharatiraja ◽

Harish Chowdary V

Keyword(s):

Real Time ◽

Power Quality ◽

Large Scale ◽

High Efficiency ◽

Reactive Power ◽

Electronic Device ◽

Supply Voltage ◽

Load Condition ◽

Total Power ◽

Energy Devices

Power Quality (PQ) brings more challenges to the large- scale and medium scale industries because in the recent years most of them use high efficiency and low energy devices which cause vulnerable PQ disturbances at Point of Common Coupling (PCC). In this paper, the measurement at different times during load condition and analysis of all types of disturbances occurred has been done. When large rated equipments run, the disturbance (harmonics, RMS variations, and switching transients) levels are very high and poor power factor (PF) has also appeared. Due to this poor PF, reactive power consumption in load increases and accordingly total power increases. An electronic device such as LED lights, fluorescent lamps, computers, copy machines, and laser printers also disturb the supply voltage. We are very well known that every PQ problem directly or indirectly must affect economically. Many researchers have investigated PQ audit for over three decades. However these studies and analysis have been done only at simulation level. Hence, the PQ analyzer based study is required to find out the PQ issues at distribution feeders. It will be a valuable guide for researchers, who are interested in the domain of PQ and wish to explore the opportunities offered by these techniques for further improvement in the field of PQ. This paper gives a brief Real Time PQ measurement using PQ analyzer HIOKI PW3198 at Distribution Feeders and it gives an idea to the researcher to optimize problems-related to PQ with respect to the high rated and low rated electric machinery of different feeders at PCC level. This study further extends to analyze the grid disturbances and looks forward to the optimization methods for each individual PQ disturbance.

Download Full-text

A Design of Position Terminal Based on BDS

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.635-637.1128 ◽

2014 ◽

Vol 635-637 ◽

pp. 1128-1131

Author(s):

Xing Hong Kuang ◽

Zhe Yi Yao ◽

Shi Ming Wang

Keyword(s):

Data Collection ◽

Real Time ◽

High Precision ◽

High Speed ◽

Large Scale ◽

High Efficiency ◽

Satellite Navigation ◽

Navigation Systems ◽

Time Data ◽

High Precision Measurement

With the development of economy, the global satellite navigation system with its high speed, high efficiency, high precision measurement and positioning a series of significant advantages, favored by various industry data collection and monitoring of personnel resources , the advent of satellite navigation systems to solve a large-scale, rapid and high-precision global positioning problem. Its scope of application has penetrated to the various departments of the national economic and social development in various fields and industries. To be able to monitor the progressive realization of automated data collection and transmission, the urgent need to adopt advanced positioning technology to build real-time location monitoring system PC Based Development Background navigation receiver , an overview of the inter Beidou BD-126 systems and microcontrollers can be serially the basic principle of mouth communication describes the communication protocol Compass BD-126 positioning module and the next crew between the microcontroller to control development in the use of PC positioning system for a detailed description , including the BDS Beidou satellite navigation module and microcontroller serial data communications, microprocessor controlled real-time data display , and so on

Download Full-text

Telescope performance real-time monitoring based on machine learning

Monthly Notices of the Royal Astronomical Society ◽

10.1093/mnras/staa3087 ◽

2020 ◽

Vol 500 (1) ◽

pp. 388-396

Author(s):

Tian Z Hu ◽

Yong Zhang ◽

Xiang Q Cui ◽

Qing Y Zhang ◽

Ye P Li ◽

...

Keyword(s):

Machine Learning ◽

Real Time ◽

System Performance ◽

High Performance ◽

High Efficiency ◽

Peak Performance ◽

Source Image ◽

Detection Accuracy ◽

Real Time Monitoring ◽

Active Optics

ABSTRACT In astronomy, the demand for high-resolution imaging and high-efficiency observation requires telescopes that are maintained at peak performance. To improve telescope performance, it is useful to conduct real-time monitoring of the telescope status and detailed recordings of the operational data of the telescope. In this paper, we provide a method based on machine learning to monitor the telescope performance in real-time. First, we use picture features and the random forest algorithm to select normal pictures captured by the acquisition camera or science camera. Next, we cut out the source image of the picture and use convolutional neural networks to recognize star shapes. Finally, we monitor the telescope performance based on the relationship between the source image shape and telescope performance. Through this method, we achieve high-performance real-time monitoring with the Large Sky Area Multi-Object Fibre Spectroscopic Telescope, including guiding system performance, focal surface defocus, submirror performance, and active optics system performance. The ultimate performance detection accuracy can reach up to 96.7 per cent.

Download Full-text

SSD7-FFAM: A Real-Time Object Detection Network Friendly to Embedded Devices from Scratch

Applied Sciences ◽

10.3390/app11031096 ◽

2021 ◽

Vol 11 (3) ◽

pp. 1096

Author(s):

Qing Li ◽

Yingcheng Lin ◽

Wei He

Keyword(s):

Object Detection ◽

Real Time ◽

Large Scale ◽

Feature Fusion ◽

Contextual Information ◽

Attention Mechanism ◽

Detection Accuracy ◽

Single Shot ◽

Feature Maps ◽

Embedded Devices

The high requirements for computing and memory are the biggest challenges in deploying existing object detection networks to embedded devices. Living lightweight object detectors directly use lightweight neural network architectures such as MobileNet or ShuffleNet pre-trained on large-scale classification datasets, which results in poor network structure flexibility and is not suitable for some specific scenarios. In this paper, we propose a lightweight object detection network Single-Shot MultiBox Detector (SSD)7-Feature Fusion and Attention Mechanism (FFAM), which saves storage space and reduces the amount of calculation by reducing the number of convolutional layers. We offer a novel Feature Fusion and Attention Mechanism (FFAM) method to improve detection accuracy. Firstly, the FFAM method fuses high-level semantic information-rich feature maps with low-level feature maps to improve small objects’ detection accuracy. The lightweight attention mechanism cascaded by channels and spatial attention modules is employed to enhance the target’s contextual information and guide the network to focus on its easy-to-recognize features. The SSD7-FFAM achieves 83.7% mean Average Precision (mAP), 1.66 MB parameters, and 0.033 s average running time on the NWPU VHR-10 dataset. The results indicate that the proposed SSD7-FFAM is more suitable for deployment to embedded devices for real-time object detection.

Download Full-text

Encoding Spectral-Spatial Features for Hyperspectral Image Classification in the Satellite Internet of Things System

Remote Sensing ◽

10.3390/rs13183561 ◽

2021 ◽

Vol 13 (18) ◽

pp. 3561

Author(s):

Ning Lv ◽

Zhen Han ◽

Chen Chen ◽

Yijia Feng ◽

Tao Su ◽

...

Keyword(s):

Internet Of Things ◽

Land Cover ◽

Image Classification ◽

Large Scale ◽

High Efficiency ◽

Hyperspectral Image ◽

Remote Sensing Data ◽

Hyperspectral Images ◽

Hyperspectral Image Classification ◽

Spatial Features

Hyperspectral image classification is essential for satellite Internet of Things (IoT) to build a large scale land-cover surveillance system. After acquiring real-time land-cover information, the edge of the network transmits all the hyperspectral images by satellites with low-latency and high-efficiency to the cloud computing center, which are provided by satellite IoT. A gigantic amount of remote sensing data bring challenges to the storage and processing capacity of traditional satellite systems. When hyperspectral images are used in annotation of land-cover application, data dimension reduction for classifier efficiency often leads to the decrease of classifier accuracy, especially the region to be annotated consists of natural landform and artificial structure. This paper proposes encoding spectral-spatial features for hyperspectral image classification in the satellite Internet of Things system to extract features effectively, namely attribute profile stacked autoencoder (AP-SAE). Firstly, extended morphology attribute profiles EMAP is used to obtain spatial features of different attribute scales. Secondly, AP-SAE is used to extract spectral features with similar spatial attributes. In this stage the program can learn feature mappings, on which the pixels from the same land-cover class are mapped as closely as possible and the pixels from different land-cover categories are separated by a large margin. Finally, the program trains an effective classifier by using the network of the AP-SAE. Experimental results on three widely-used hyperspectral image (HSI) datasets and comprehensive comparisons with existing methods demonstrate that our proposed method can be used effectively in hyperspectral image classification.

Download Full-text

Evolutionary Multiobjective Optimization with Endmember Priori Strategy for Large-Scale Hyperspectral Sparse Unmixing

Electronics ◽

10.3390/electronics10172079 ◽

2021 ◽

Vol 10 (17) ◽

pp. 2079

Author(s):

Zhao Wang ◽

Jinxin Wei ◽

Jianzhao Li ◽

Peng Li ◽

Fei Xie

Keyword(s):

Multiobjective Optimization ◽

Large Scale ◽

High Efficiency ◽

Hyperspectral Image ◽

Simulated Data ◽

Reconstruction Error ◽

Initial Population ◽

Spectral Library ◽

Nondominated Solutions ◽

Mixed Pixels

Mixed pixels inevitably appear in the hyperspectral image due to the low resolution of the sensor and the mixing of ground objects. Sparse unmixing, as an emerging method to solve the problem of mixed pixels, has received extensive attention in recent years due to its robustness and high efficiency. In theory, sparse unmixing is essentially a multiobjective optimization problem. The sparse endmember term and the reconstruction error term can be regarded as two objectives to optimize simultaneously, and a series of nondominated solutions can be obtained as the final solution. However, the large-scale spectral library poses a challenge due to the high-dimensional number of spectra, it is difficult to accurately extract a few active endmembers and estimate their corresponding abundance from hundreds of spectral features. In order to solve this problem, we propose an evolutionary multiobjective hyperspectral sparse unmixing algorithm with endmember priori strategy (EMSU-EP) to solve the large-scale sparse unmixing problem. The single endmember in the spectral library is used to reconstruct the hyperspectral image, respectively, and the corresponding score of each endmember can be obtained. Then the endmember scores are used as a prior knowledge to guide the generation of the initial population and the new offspring. Finally, a series of nondominated solutions are obtained by the nondominated sorting and the crowding distances calculation. Experiments on two benchmark large-scale simulated data to demonstrate the effectiveness of the proposed algorithm.

Download Full-text

Hyperspectral Anomaly Detection Based on Separability-Aware Sample Cascade

Remote Sensing ◽

10.3390/rs11212537 ◽

2019 ◽

Vol 11 (21) ◽

pp. 2537 ◽

Cited By ~ 2

Author(s):

Dandan Ma ◽

Yuan Yuan ◽

Qi Wang

Keyword(s):

Anomaly Detection ◽

Large Scale ◽

Hyperspectral Image ◽

Superior Performance ◽

Detection Methods ◽

Background Information ◽

Detection Accuracy ◽

Layer By Layer ◽

Edge Preserving ◽

Image Pixels

A hyperspectral image usually covers a large scale of ground scene, which contains various materials with different spectral properties. When directly exploring the background information using all the image pixels, complex spectral interactions and inter-/intra-difference of different samples will significantly reduce the accuracy of background evaluation and further affect the detection performance. To address this problem, this paper proposes a novel hyperspectral anomaly detection method based on separability-aware sample cascade model. Through identifying separability of hyperspectral pixels, background samples are sifted out layer-by-layer according to their separable degrees from anomalies, which can ensure the accuracy and distinctiveness of background representation. First, as spatial structure is beneficial for recognizing target, a new spectral–spatial feature extraction technique is used in this work based on the PCA technique and edge-preserving filtering. Second, depending on different separability computed by sparse representation, samples are separated into different sets which can effectively and completely reflect various characteristics of background across all the cascade layers. Meanwhile, some potential abnormal targets are removed at each selection step to avoid their effects on subsequent layers. Finally, comprehensively taking different good properties of all the separability-aware layers into consideration, a simple multilayer anomaly detection strategy is adopted to obtain the final detection map. Extensive experimental results on five real-world hyperspectral images demonstrate our method’s superior performance. Compared with seven representative anomaly detection methods, our method improves the average detection accuracy with great advantages.

Download Full-text

A Real-Time Tree Crown Detection Approach for Large-Scale Remote Sensing Images on FPGAs

Remote Sensing ◽

10.3390/rs11091025 ◽

2019 ◽

Vol 11 (9) ◽

pp. 1025 ◽

Cited By ~ 3

Author(s):

Weijia Li ◽

Conghui He ◽

Haohuan Fu ◽

Juepeng Zheng ◽

Runmin Dong ◽

...

Keyword(s):

Remote Sensing ◽

Real Time ◽

Large Scale ◽

Satellite Image ◽

Detection Accuracy ◽

Tree Crown ◽

Remote Sensing Images ◽

Time Data ◽

Original Algorithm ◽

Detection Approach

The on-board real-time tree crown detection from high-resolution remote sensing images is beneficial for avoiding the delay between data acquisition and processing, reducing the quantity of data transmission from the satellite to the ground, monitoring the growing condition of individual trees, and discovering the damage of trees as early as possible, etc. Existing high performance platform based tree crown detection studies either focus on processing images in a small size or suffer from high power consumption or slow processing speed. In this paper, we propose the first FPGA-based real-time tree crown detection approach for large-scale satellite images. A pipelined-friendly and resource-economic tree crown detection algorithm (PF-TCD) is designed through reconstructing and modifying the workflow of the original algorithm into three computational kernels on FPGAs. Compared with the well-optimized software implementation of the original algorithm on an Intel 12-core CPU, our proposed PF-TCD obtains the speedup of 18.75 times for a satellite image with a size of 12,188 × 12,576 pixels without reducing the detection accuracy. The image processing time for the large-scale remote sensing image is only 0.33 s, which satisfies the requirements of the on-board real-time data processing on satellites.

Download Full-text

A Lightweight Object Detection Framework for Remote Sensing Images

Remote Sensing ◽

10.3390/rs13040683 ◽

2021 ◽

Vol 13 (4) ◽

pp. 683

Author(s):

Lang Huyan ◽

Yunpeng Bai ◽

Ying Li ◽

Dongmei Jiang ◽

Yanning Zhang ◽

...

Keyword(s):

Remote Sensing ◽

Object Detection ◽

Real Time ◽

Large Scale ◽

Feature Fusion ◽

Computational Cost ◽

Feature Representation ◽

Detection Accuracy ◽

Remote Sensing Images ◽

Low Level

Onboard real-time object detection in remote sensing images is a crucial but challenging task in this computation-constrained scenario. This task not only requires the algorithm to yield excellent performance but also requests limited time and space complexity of the algorithm. However, previous convolutional neural networks (CNN) based object detectors for remote sensing images suffer from heavy computational cost, which hinders them from being deployed on satellites. Moreover, an onboard detector is desired to detect objects at vastly different scales. To address these issues, we proposed a lightweight one-stage multi-scale feature fusion detector called MSF-SNET for onboard real-time object detection of remote sensing images. Using lightweight SNET as the backbone network reduces the number of parameters and computational complexity. To strengthen the detection performance of small objects, three low-level features are extracted from the three stages of SNET respectively. In the detection part, another three convolutional layers are designed to further extract deep features with rich semantic information for large-scale object detection. To improve detection accuracy, the deep features and low-level features are fused to enhance the feature representation. Extensive experiments and comprehensive evaluations on the openly available NWPU VHR-10 dataset and DIOR dataset are conducted to evaluate the proposed method. Compared with other state-of-art detectors, the proposed detection framework has fewer parameters and calculations, while maintaining consistent accuracy.

Download Full-text

An FPGA-Based Four-Channel 128k-Point FFT Processor Suitable for Spaceborne SAR

Electronics ◽

10.3390/electronics10070816 ◽

2021 ◽

Vol 10 (7) ◽

pp. 816

Author(s):

Yongrui Li ◽

He Chen ◽

Yizhuang Xie

Keyword(s):

Real Time ◽

Large Scale ◽

High Efficiency ◽

Imaging System ◽

Path Delay ◽

Real Time Processing ◽

Time Processing ◽

Fft Processor ◽

Adjustment Strategy ◽

Field Programmable

Spaceborne synthetic aperture radar (SAR) plays an important role in many fields of national defense and the national economy, and the Fast Fourier Transform (FFT) processor is an important part of the spaceborne real-time SAR imaging system. How to meet the increasing demand for ultra-large-scale data processing and to reduce the scale of the hardware platform while ensuring real-time processing is a major problem for real-time processing of on-orbit SAR. To solve this problem, in this study, we propose a 128k-point fixed-point FFT processor based on Field-Programmable Gate Array (FPGA) with a four-channel Single-path Delay Feedback (SDF) structure. First, we combine the radix-23 and mixed-radix algorithms to propose a four-channel processor structure, to achieve high efficiency hardware resources and high real-time performance. Secondly, we adopt the SDF structure combined with the radix-23 algorithm to achieve efficient use of storage resources. Third, we propose a word length adjustment strategy to ensure the accuracy of calculations. The experimental results show that the relative error between the processor and the MATLAB calculation result is maintained at about 10−4, which has good calculation accuracy.

Download Full-text