A Bayesian Nonparametric Model Coupled with a Markov Random Field for Change Detection in Heterogeneous Remote Sensing Images

Remote sensing images are commonly used to monitor the earth surface evolution. This surveillance can be conducted by detecting changes between images acquired at different times and possibly by different kinds of sensors. A representative case is when an optical image of a given area is available and a new image is acquired in an emergency situation (resulting from a natural disaster for instance) by a radar satellite. In such a case, images with heterogeneous properties have to be compared for change detection. This paper proposes a new approach for similarity measurement between images acquired by heterogeneous sensors. The approach exploits the considered sensor physical properties and specially the associated measurement noise models and local joint distributions. These properties are inferred through manifold learning. The resulting similarity measure has been successfully applied to detect changes between many kinds of images, including pairs of optical images and pairs of optical-radar images.

AN ASSESSMENT OF SPATIAL VARIATION OF LAND SURFACE CHARACTERISTICS OF MINNA, NIGER STATE NIGERIA FOR SUSTAINABLE URBANIZATION USING GEOSPATIAL TECHNIQUES

Sensor fusion is a fundamental issue in developing intelligent systems that recognize the scene around them precisely and robustly. Previous approaches of sensor fusion combined a different kind of sensor after feature extraction and abstraction (task-level fusion). This paper proposes a new approach that combines sensory signals from a different kind of sensor before abstraction (signal-level fusion). By formalizing sensory fusion as an optimization that maximizes mutual information between sensory signals, a target in a changing scene is detected by a heuristic search algorithm. As an example, experimental results of sound source detection with one video camera and one microphone are shown.

Change detection (CD) in multispectral remote sensing (RS) imagery suffers from low spectral resolution which can lead to degraded recognition of change information from land cover objects. Considering that natural hyperspectral imagery (HSI) is much higher in spectral resolution and more accessible, using it to enhance the spectral information of RS multispectral imagery for CD can improve performance. To achieve this, we propose a spectral knowledge transfer (SKT) framework to allow the creation of pseudo-hyperspectral RS images from the available RS multispectral ones without the need for the real pairs of RS multispectral and hyperspectral images, typically required by existing RS spectral enhancement methods. Specifically, an autoencoder is first trained based on the available pairs of natural HSI and its multispectral counterparts and then calibrated via the available RS multispectral images. The finally obtained decoder module is used to generate the pseudo-hyperspectral image from an input RS multispectral image. We further propose a multispectrum collaborative CD (MCCD) framework that leverages both the real multispectral images and the pseudo hyperspectral images generated from them in a collaborative way to achieve performance improvement. Extensive experiments on two large-scale RS CD datasets and eight existing deep learning-based CD methods demonstrate the stronger efficacy of the proposed method.

Detection of structural changes in images is one of the important tasks of remote sensing (RS) data thematic analysis. The effective way to solve it is applying the Pyt'ev’s morphological projector to the pair of images of the same scene acquired on different dates. The main advantage of this method is its invariance to global brightness transformations, which in the case of RS images correspond to different parameters of the atmosphere or the different values of the brightness-contrast ratio of the scene. However, the classical Pyt'ev’s morphological projector and its regularized versions do not take into account the spatial connectivity of image samples. As a result, they ignore the textural features of images. In this article, we suggest the algorithm of structural changes detection based on superpixel segmentation and Pyt'ev’s morphological projector that takes into account local characteristics of the image pixels. In the experimental research, we analyzed the accuracies of the proposed and classical Pyt'ev’s structural change detection methods using simulated and real RS images. The comparison of two algorithms showed that the proposed method is more robust to the additive white Gaussian noise (AWGN) at different values of signal-to-noise (SNR) ratio. Additionally, the experiments with nonlinear brightness distortions (vignetting) of one of the pair of images demonstrated that the proposed method has lower false positive rates than the classical one.

This article presents a probabilistic model based on a bipartite convolutional architecture for unsupervised change detection. We aim to develop a robust change detection method that can adapt to different types of data and scenarios for multitemporal coregistered remote sensing images of the same spatial resolution. On the premise of coregistration, unsupervised change detection usually suffers from the distinct appearances (different intensities or data structures) of the same object in multitemporal images, such as images obtained in different climatic conditions (season, illumination, and so on), and by different and even heterogeneous sensors. Since change detection in heterogeneous images can also adapt to other scenarios, many methods have been proposed recently focusing on such data, but most of them are limited by the need for labeled data or by specific assumptions. With the excellent and flexible feature learning capability of neural networks, we model the change detection into a Gibbs probabilistic model based on a bipartite neural network. The model is driven by an energy function defined as the squared feature distance, which is the core of change detection. Via optimizing the model, the difference degree of each pixel is automatically obtained for further identification. The probabilistic model learns to capture the distribution in an unsupervised way. Therefore, the proposed method can adapt to various scenarios without being trained by labeled data. Experiments on different types of data and scenarios demonstrate the superiority of the proposed method.

Deep learning plays a highly essential role in the domain of remote sensing change detection (CD) due to its high efficiency. From some existing methods, we can observe that the fusion of information at each scale is quite vital for the accuracy of the CD results, especially for the common problems of pseudo-change and the difficult detection of change edges in the CD task. With this in mind, we propose a New Fusion network with Dual-branch Encoder and Triple-branch Decoder (DETDNet) that follows a codec structure as a whole, where the encoder adopts a siamese Res2Net-50 structure to extract the local features of the bitemporal images. As for the decoder in previous works, they usually employed a single branch, and this approach only preserved the fusion features of the encoder’s bitemporal images. Distinguished from these approaches, we adopt the triple-branch architecture in the decoder for the first time. The triple-branch structure preserves not only the dual-branch features from the encoder in the left and right branches, respectively, to learn the effective and powerful individual features of each temporal image but also the fusion features from the encoder in the middle branch. The middle branch utilizes triple-branch aggregation (TA) to realize the feature interaction of the three branches in the decoder, which enhances the integrated features and provides abundant and supplementary bitemporal feature information to improve the CD performance. The triple-branch architecture of the decoder ensures that the respective features of the bitemporal images as well as their fused features are preserved, making the feature extraction more integrated. In addition, the three branches employ a multiscale feature extraction module (MFE) per layer to extract multiscale contextual information and enhance the feature representation capability of the CD. We conducted comparison experiments on the BCDD, LEVIR-CD, and SYSU-CD datasets, which were created in New Zealand, the USA, and Hong Kong, respectively. The data were preprocessed to contain 7434, 10,192, and 20,000 image pairs, respectively. The experimental results show that DETDNet achieves F1 scores of 92.7%, 90.99%, and 81.13%, respectively, which shows better results compared to some recent works, which means that the model is more robust. In addition, the lower FP and FN indicate lower error and misdetection rates. Moreover, from the analysis of the experimental results, compared with some existing methods, the problem of pseudo-changes and the difficulty of detecting small change areas is better solved.

Change detection (CD) represents a critical task in the analysis of remote sensing (RS) images. In particular, the CD of heterogeneous images that integrate optical and synthetic aperture radar (SAR) modalities has attracted growing attention owing to their complementary characteristics. However, the optical and SAR images (OSIs) CD tasks face specific issues including structural inconsistency between modalities, speckle noise in SAR images, and insufficient utilization of complementary cross-modal features, resulting in limitations in feature representation, temporal causal modeling, and feature fusion for existing methods. Therefore, proposes an end-to-end causal attention and frequency-domain gating fusion enhanced dual-branch OSIs CD network (CAFGFNet). This network adopts a dual-branch encoding architecture with modality-specific designs, where the optical branch emphasizes preserving spectral and texture features, and the SAR branch integrates denoising with deformable convolution to mitigate speckle noise and geometric deformation. On this basis, the Causal Attention (CA) mechanism is introduced to model temporal dependencies to suppress false changes, and the Frequency-domain Gating Fusion Module (FGFM) is designed to adaptively fuse complementary frequency components from optical and SAR features, thus effectively boosting the accuracy and robustness of CD. Compared with six state-of-the-art (SOTA) methods, CAFGFNet has increased the relative suboptimal indicators of Precision by 2.2% and 8.93% on two public datasets. The experimental results show that CAFGFNet can achieve high-precision detection of changes in OSIs while ensuring the full expression and effective fusion of cross-modal features.

At present, most remote sensing change detection methods are applicable to bi-temporal image alignment scenarios, that is, assuming that the pixel pairs of bi-temporal images are spatially registered. Detection accuracy is highly sensitive to the alignment accuracy of the image pairs. In practical applications, obtaining well-registered image pairs is often challenging. Currently, the approach of aligning first and then detecting is both inefficient and expensive. Explicitly integrating image alignment and change detection into a framework is an effective solution. However, offset information is difficult to be reflected in the high-level features of the image, it is hard to predict accurate image offsets, and it is also difficult to correct the spatial relationship of land covers in the image using the offset. To overcome the above problems, we propose a residual offset-driven feature alignment network (ROFANet). ROFANet combines two innovative methods: residual offset prediction (ROP) and dual-branch feature correction (DFC). ROP utilizes multi-level features to achieve offset prediction from coarse to fine granularity, effectively enhancing the model's predictive ability for image offsets. DFC has established two branches: image correction and feature correction, which respectively correct distorted images and distorted features. By optimizing the spatial relationship representation of land covers, the model's change detection ability under unaligned image conditions has been enhanced. Extensive experiments conducted on three publicly available change detection datasets demonstrate that the proposed ROFANet achieves outstanding detection performance in unaligned image scenarios. The source code will be available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/bitwgq/ROFANet</uri>.

Facing the challenge of small open labeled data sets in remote sensing change detection, this letter proposes a novel supervised change detection method by taking advantages of capsule network which can reach the same performance as traditional convolutional neural networks (CNNs) but with less training data. To achieve this aim, we propose a pseudo-Siamese capsule network which takes both rotational invariance and spatial hierarchies between features into account for aerial images change detection. First, the features of image pairs are extracted by two identical nonshared weights convolutional capsule networks. Second, the extracted features are directly concatenated and sent to another convolutional capsule layer. The change probability map is obtained by calculating the length of the capsule vectors in the final layer. Additionally, to reduce the influence of imbalance samples when we optimize our network, we design a margin-focal loss function to pay more attention to the misclassified samples. Finally, binary change map can be produced by a simple threshold. Experimental results carried out on the SZTAKI AirChange Benchmark Set show that the proposed method achieves comparable and even better results with existing state-of-the-art methods in terms of F-measure.

This work presents a study on the performance of printed low-cost moisture sensors fabricated using conductive ink on paper substrates. The sensors are intended to add value to the surveillance of packages. Two different kinds of sensors are evaluated and characterized. The two sensors have similar geometrical shapes, but different measuring principles are employed. The first sensor is measuring the moisture content in cellulose-based substrates, while the second is measuring high levels of relative humidity in the surroundings. The sensors have been developed so that they can be integrated into radio frequency identification (RFID) systems for surveillance in logistic chains. A laboratory setup of a RFID tag with sensor capability based on an ordinary passive RFID tag has been shown.

PurposeThe purpose of this paper is to present the research efforts of the Center of Aeronautical Studies of the Federal University of Minas Gerais – Brazil to develop a low‐cost flight test data acquisition system for light aircraft and unmanned aerial vehicles (UAEs).Design/methodology/approachThe development of this system was based on a microcontroller, chosen in accordance with main requirements of light aircrafts flight tests. The system uses the microcontroller in order to communicate with different kinds of sensors, including a GPS, and organize this information to be sent to a PDA device, which is used to control the acquisition process and storage the data acquired. Details about the development of this system, including firmware algorithm and sensors development, are presented and discussed in the paper.FindingsThe paper presents example results obtained with this system in applications such as performance evaluation and stability and control derivatives estimation problems. Take into account all the aspects of the system and the quality of the results, the main conclusion is that this system can efficiently support the demands of the aerospace industry for light aircraft and UAEs development programs as well as the necessities of the research centers and universities developing aeronautical research and didactic programs.Practical implicationsRecently, results confirm the applicability of this system in order to perform flight tests of aircrafts in accordance with FAR‐Part 23 or CS‐VLA or Light Sport Aircrafts as required by FAA Order 8130.2F and ASTM Designation F2245‐04.Originality/valueThis paper presents details about the construction of a low‐cost data acquisition system for flight tests of light aircrafts. The main advantage of this system is the use of a PDA device in order to control and storage the acquisition, which reduce costs, weight and size of the system and permits its installation in light aircrafts or UAVs.

Three different sensors (a near-infrared spectrophotometer 'NIR', a machine vision system 'MV' and an electronic nose system 'EN') are combined for nondestructive quality detection of Fuji apples. The intention is to take advantage of the three sensors, one performing a local measurement of one physical property of the fruit (sugar content), the others performing a global assessment of other physical properties of the fruit (color, size, shape and aroma), and to combine those types of measurement (local and global) to improve the accuracy of quality assessment. The EN is used to assess rotting stage of apple based on ANN (artificial neural network). A relationship is also found between sugar content and different NIR wavelengths by using MLR (multiple linear regression). The surface color, shape and size of apples were accessed by MV technique. The three sensors are working at the same time. 104 Fuji apples were detected by the three-sensor combination system, and were divided into two sets, with 84 in set A and 20 in set B. By combining the three different kinds of sensors, it is shown that the accuracy of quality assessment of apple can be improved with the high-level fusion technique. For sugar content assessment, the classification error rate drops from around 17%, using only NIR spectra, to around 6% when the three sensors are combined through ANN. Finally, the three sensors are combined to evaluate the quality of apples through a decision tree, and only 6 apples in set A, 1 apple in set B were misclassified

High resolution gas chromatography/selective odorant measurement by multisensor array (HRGC/SOMSA): a useful approach to standardise multisensor arrays for use in the detection of key food odorants

As the new era of the Internet of Things(IoT) is driving the evolution of conventional Vehicle Ad-hoc Networks into the Internet of Vehicles(IoV), vehicles are equipped with different kinds of sensor and become a sensing node themselves in IoV. Consequently, complexity of the automotive electronic system inside the vehicles are daily increasing. To guarantee the safe operation of vehicles, it is of great significance to acquire vehicle data in real-time to realize the on-line diagnosis, cybersecurity attacking detection and et al. In this paper, we propose to realize a STM32-based data acquisition system(DAS), where the vehicle data transferred on CAN networks are acquired through the OBD2(On-Broad Diagnosis) interface. And then, the acquired vehicle data are parsed and analyzed preliminarily according to the OBD2 protocol, and then shown on a LED displayer. Through the implementation of a prototype system, the feasibility and effectiveness of the proposed design of DAS is verified.