Scene Changes Research Articles

Thermal Infrared Image Georeferencing using an Ensemble of Land Cover Predictions

Abstract. Precise georeferencing of remote sensing data is usually implemented in a post-processing fashion and is a crucial step for Earth observation applications such as change detection, natural hazard management, and ground target tracking. It is particularly important for small satellites intending to perform temperature monitoring and wildfire detection on a global scale wherein the precise location of fire is to be communicated. The cost-efficient navigating systems on board such satellites are often not capable of providing accurate geolocation information directly due to space and power limitations. Therefore, it is very important to have a globally applicable georeferencing refinement framework that is robust against illuminational and time-relevant scene changes. In this paper, we propose a georeferencing framework for thermal infrared images that consists of ensemble matching of deep learning-based land cover predictions to archival, well-georeferenced land cover maps. We verify the proposed framework on the georeferencing of single-band Landsat thermal imagery. Experimental results show the efficiency and practicality of the method with 72% of the test images geolocated within 1-pixel accuracy with no trajectory information available.

Bistatic multi‐polarimetric synthetic aperture radar coherence investigation using spatially variant incoherence trimming

AbstractSynthetic Aperture Radar (SAR) Coherent Change Detection allows for the detection of very small scene changes. This is particularly useful for Intelligence, Surveillance and Reconnaissance as small changes such as vehicle tracks can be identified. Rapidly collecting repeat pass SAR imagery is important in these applications. For space‐borne platforms, such repeat passes may however have significant differences, or baselines. Coherent Change Detection products are reliant on high coherence for good interpretability. This work investigates the sources and levels of incoherence associated with bistatic SAR imagery for a variety of baselines using simulations and measured laboratory data for two ground types. Additionally, spatially variant incoherence trimming is implemented. The paper shows the importance of angle‐dependant backscatter on the coherence of sub‐resolution cell scatterers.

Dual Stream Encoder–Decoder Architecture with Feature Fusion Model for Underwater Object Detection

Underwater surveillance is an imminent and fascinating exploratory domain, particularly in monitoring aquatic ecosystems. This field offers valuable insights into underwater behavior and activities, which have broad applications across various domains. Specifically, underwater surveillance involves detecting and tracking moving objects within aquatic environments. However, the complex properties of water make object detection a challenging task. Background subtraction is a commonly employed technique for detecting local changes in video scenes by segmenting images into the background and foreground to isolate the object of interest. Within this context, we propose an innovative dual-stream encoder–decoder framework based on the VGG-16 and ResNet-50 models for detecting moving objects in underwater frames. The network includes a feature fusion module that effectively extracts multiple-level features. Using a limited set of images and performing training in an end-to-end manner, the proposed framework yields accurate results without post-processing. The efficacy of the proposed technique is confirmed through visual and quantitative comparisons with eight cutting-edge methods using two standard databases. The first one employed in our experiments is the Underwater Change Detection Dataset, which includes five challenges, each challenge comprising approximately 1000 frames. The categories in this dataset were recorded under various underwater conditions. The second dataset used for practical analysis is the Fish4Knowledge dataset, where we considered five challenges. Each category, recorded in different aquatic settings, contains a varying number of frames, typically exceeding 1000 per category. Our proposed method surpasses all methods used for comparison by attaining an average F-measure of 0.98 on the Underwater Change Detection Dataset and 0.89 on the Fish4Knowledge dataset.

Enhanced Abandoned Object Detection through Adaptive Dual-Background Modeling and SAO-YOLO Integration

Abandoned object detection is a critical task in the field of public safety. However, existing methods perform poorly when detecting small and occluded objects, leading to high false detection and missed detection rates. To address this issue, this paper proposes an abandoned object detection method that integrates an adaptive dual-background model with SAO-YOLO (Small Abandoned Object YOLO). The goal is to reduce false and missed detection rates for small and occluded objects, thereby improving overall detection accuracy. First, the paper introduces an adaptive dual-background model that adjusts according to scene changes, reducing noise interference in the background model. When combined with an improved PFSM (Pixel-based Finite State Machine) model, this enhances detection accuracy and robustness. Next, a network model called SAO-YOLO is designed. Key improvements within this model include the SAO-FPN (Small Abandoned Object FPN) feature extraction network, which fully extracts features of small objects, and a lightweight decoupled head, SODHead (Small Object Detection Head), which precisely extracts local features and enhances detection accuracy through multi-scale feature fusion. Finally, experimental results show that SAO-YOLO increases mAP@0.5 and mAP@0.5:0.95 by 9.0% and 5.1%, respectively, over the baseline model. It outperforms other advanced detection models. Ultimately, after a series of experiments on the ABODA, PETS2006, and AVSS2007 datasets, the proposed method achieved an average detection precious of 91.1%, surpassing other advanced methods. It significantly outperforms other advanced detection methods. This approach notably reduces false and missed detections, especially for small and occluded objects.

OVERLOOKING THE TRANSFORMATION OF VALUES THROUGH THE TRANSNATIONAL AMERICAN REMAKES MOVIES

This study explores the transformation of values in transnational remake movies, focusing on their popularity and the incorporation of new elements to suit target audience preferences. An analysis of The Lake House, a remake of the Korean film Il Mare, reveals shifts in values and the integration of American cultural aspects. These changes stem from audience demands, business considerations, and Hollywood's global influence. Remakes require more than simply reproducing original content; they involve capturing cultural nuances from both versions. Utilizing Hall's representation approach and qualitative methods, the study assesses transnational remakes and their conveyed values. The research identifies shifts from South Korean values to those of the American target market, such as the transition from interdependence to self-reliance and a preference for directness, assertion, and rationality. The American film industry should carefully evaluate the suitability of movies for its audiences, recognizing changes in scenes and messages. The establishment of American values in remakes is influenced by the success of original films and their formulas. As transnational products, movies must be repackaged for target audiences. The industry faces complex processes to align the values of popular films with audience tastes while maintaining the essence of original works.

Quick action required: revealing pheochromocytoma as the hidden trigger behind postoperative hypertensive crisis.

Managing patients who present with elevated blood pressure (BP) requires careful but expeditious assessment and triage to differentiate between those at immediate risk of complications and those for whom BP elevation does not pose an immediate threat to health. We present a case of a 54-year-old healthy male patient who experienced refractory hypertension during the immediate postoperative period following nasal surgery. Additional gastrointestinal symptoms and imaging findings made it possible to consider a catecholamine-producing tumour as the primary cause. Despite efforts, managing hypertension continued to be a challenge, and major neurologic complications arose within the following hours. This case illustrates the potential for rapid changes in the clinical scene during hypertensive emergency management. If not addressed promptly, a routine postoperative complication (at first glance) can turn into serious complications, particularly when there are uncommon underlying causes involved.

Blog Serials: Digital Literature, Seriality, Readerly Performativity

Abstract The 1990s and the first decade of the 2000s were a period that witnessed dramatic changes in the literary scene in South Korea. Literary production’s engagement with digital media was one of the major changes in this period, when the divide, collision, and merge between pre-digital and digital came to affect almost every aspect of the society. This article explores the divergent strands in the development of digital literature, the new affordances of the digital environment that affected the literary serial vis-à-vis the print serial, and a virtual and actual community that readers and writers created through their engagement with literary texts and beyond. Through close analysis of a blog serial of Hwang Sŏgyŏng’s Evening Star (February 27–July 21, 2008; 102 episodes in all), which represents one of the significant moments in the early digital serialization of South Korean literature, this article discusses various types of performativity and participatory culture generated by and connected to the blog serial and participants.

Damage Scene Change Detection Based on Infrared Polarization Imaging and Fast-PCANet

Change detection based on optical image processing plays a crucial role in the field of damage assessment. Although existing damage scene change detection methods have achieved some good results, they are faced with challenges, such as low accuracy and slow speed in optical image change detection. To solve these problems, an image change detection approach that combines infrared polarization imaging with a fast principal component analysis network (Fast-PCANet) is proposed. Firstly, the acquired infrared polarization images are analyzed, and pixel image blocks are extracted and filtered to obtain the candidate change points. Then, the Fast-PCANet network framework is established, and the candidate pixel image blocks are sent to the network to detect the change pixel points. Finally, the false-detection points predicted by the Fast-PCANet are further corrected by region filling and filtering to obtain the final binary change map of the damage scene. Comparisons with typical PCANet-based change detection algorithms are made on a dataset of infrared-polarized images. The experimental results show that the proposed Fast-PCANet method improves the PCC and the Kappa coefficient of infrared polarization images over infrared intensity images by 6.77% and 13.67%, respectively. Meanwhile, the inference speed can be more than seven times faster. The results verify that the proposed approach is effective and efficient for the change detection task with infrared polarization imaging. The study can be applied to the damage assessment field and has great potential for object recognition, material classification, and polarization remote sensing.

The Blanking Effect on Detecting Changes in Natural Scenes across Saccades

The Blanking Effect on Detecting Changes in Natural Scenes across Saccades

Development of a new indicator for identifying vegetation destruction events using remote sensing data

Frequent climate change and intense anthropogenic activity increase the risk of vegetation destruction. Remote sensing technology, known for its timely observations and wide coverage, is a crucial tool for monitoring vegetation growth. However, accurately detecting vegetation destruction events remains challenging due to their spectral diversity, particularly in complex environments. Existing spectral indices (VIs) have limitations in effectively capturing vegetation dynamics as they are only sensitive to specific physiological parameters of vegetation, such as foliage, canopy, or water content, and are prone to background interference. To address this issue, we proposed the Slope Vegetation Index (SVI) based on Sentinel-2 imagery and PROSAIL model simulation data. Five representative VIs were selected for comprehensive comparison. The results showed that, compared with other VIs, SVI had the highest sensitivity to vegetation physiological parameters, with a correlation coefficient (R2) greater than 0.98. SVI performed best across all vegetation change scenes, with producer accuracy (PA), user accuracy (UA), and F1 score all exceeding 0.90. SVI proved effective in detecting various vegetation destruction events, including logging, insect infestation, landslides, and wildfires. Moreover, SVI was suitable for Landsat-8/9 imagery, achieving an F1 score of over 0.89. Overall, SVI is an effective and robust vegetation monitoring index, offering valuable insights for vegetation resource management and post-disaster ecological restoration.

Our Princes are in Borrowed Robes: Significance of Expressed Costume Choices by Selected Ghanaian Playwrights

The playwright’s work remains the blueprint upon which all other theatre artists build their craft. This positions playwrights as indispensable artists in theatrical discourse. While some playwrights express specific costume demands in their texts, others leave it to theatre directors and designers to decipher the appropriate costume choices for the plays. The former suggests a stylistic feature by some playwrights; however, less visibility appears to be given to this phenomenon in Ghanaian theatre scholarship. What the significance and implications are for both the costume designer and playwrights is the subject of this exploration. Employing a qualitative approach, this paper samples three Ghanaian playwright educators and their costume choices and examines the dramatic significance of their choices. The findings of the study revealed that the rationale for expressing costume choices was to project major characters, and that the necessity to create special characters, create impression, as well as scene changes and time, all influenced character costume choices. The significance of costume choices was to project a rich tapestry of cultural identity and characters and enforce themes, while the implications of such costume choices were to support costumiers, make issues easier for them and the playwright, and encourage them to be more creative. Ultimately, this study contributes to scholarship on costume usage in theatrical discourse.

SpectralGPT: Spectral Remote Sensing Foundation Model.

The foundation model has recently garnered significant attention due to its potential to revolutionize the field of visual representation learning in a self-supervised manner. While most foundation models are tailored to effectively process RGB images for various visual tasks, there is a noticeable gap in research focused on spectral data, which offers valuable information for scene understanding, especially in remote sensing (RS) applications. To fill this gap, we created for the first time a universal RS foundation model, named SpectralGPT, which is purpose-built to handle spectral RS images using a novel 3D generative pretrained transformer (GPT). Compared to existing foundation models, SpectralGPT 1) accommodates input images with varying sizes, resolutions, time series, and regions in a progressive training fashion, enabling full utilization of extensive RS Big Data; 2) leverages 3D token generation for spatial-spectral coupling; 3) captures spectrally sequential patterns via multi-target reconstruction; and 4) trains on one million spectral RS images, yielding models with over 600 million parameters. Our evaluation highlights significant performance improvements with pretrained SpectralGPT models, signifying substantial potential in advancing spectral RS Big Data applications within the field of geoscience across four downstream tasks: single/multi-label scene classification, semantic segmentation, and change detection.

A fast adaptive spatio-temporal fusion method to enhanced Fit-FC.

Space-time fusion is an economical and efficient way to solve "space-time contradiction". Among all kinds of space-time fusion methods, Fit-FC space-time fusion method based on weight Function is widely used. However, this method is based on the linear model to depict the phase change, but the phase change in the real scene is complicated, and the linear model is difficult to accurately capture the phase change, resulting in the spectral distortion of the fusion image. In addition, pixel-by-pixel scanning with moving Windows leads to inefficiency issues, limiting its use in large-scale and long-term tasks. To overcome these limitations, this paper developed a simple and fast adaptive remote sensing image Spatio-Temporal fusion method based on Fit-FC, called Adapt Lasso-Fit-FC (AL-FF). Firstly, the sparse characteristics of time phase change between images are explored, and a time phase change estimation model based on sparse regression is constructed, which overcomes the fuzzy problem of fusion image caused by the failure of linear regression to capture complex nonlinear time phase transition in the weighted Function method, making the algorithm better at capturing details. Secondly, an adaptive window selection Function is established to overcome the problem of manually setting parameters on different data sets, improve the convenience of the algorithm and robustness of the application on different data sets, and make the algorithm simpler and more efficient. Finally, the improved AL-FF algorithm is compared with other algorithms to verify the performance improvement. Compared with the current advanced Spatio-Temporal fusion methods, AL-FF algorithm has stronger detail capture ability and can generate more accurate fusion results. In addition, the computational efficiency is significantly improved, and the efficiency is increased by more than 20 times compared with the current mainstream method.

Co-scale cross-attentional transformer for rearrangement target detection

Rearranging objects (e.g. vase, door) back in their original positions is one of the most fundamental skills for domestic service robots (DSRs). In rearrangement tasks, it is crucial to detect the objects that need to be rearranged according to the goal and current states. In this study, we focus on Rearrangement Target Detection (RTD), where the model generates a change mask for objects that should be rearranged. Although many studies have been conducted in the field of Scene Change Detection (SCD), most SCD methods often fail to segment objects with complex shapes and fail to detect the change in the angle of objects that can be opened or closed. In this study, we propose a Co-Scale Cross-Attentional Transformer for RTD. We introduce the Serial Encoder which consists of a sequence of serial blocks and the Cross-Attentional Encoder which models the relationship between the goal and current states. We built a new dataset consisting of RGB images and change masks regarding the goal and current states. We validated our method on the dataset and the results demonstrated that our method outperformed baseline methods on F 1 -score and mean IoU.

The metacontrol of event segmentation-A neurophysiological and behavioral perspective.

During our everyday life, the constant flow of information is divided into discrete events, a process conceptualized in Event Segmentation Theory (EST). How people perform event segmentation and the resulting granularity of encapsulated segments likely depends on their metacontrol style. Yet, the underlying neural mechanisms remain undetermined. The current study examines how the metacontrol style affects event segmentation through the analysis of EEG data using multivariate pattern analysis (MVPA) and source localization analysis. We instructed two groups of healthy participants to either segment a movie as fine-grained as possible (fine-grain group) or provided no such instruction (free-segmentation group). The fine-grain group showed more segments and a higher likelihood to set event boundaries upon scene changes, which supports the notion that cognitive control influences segmentation granularity. On a neural level, representational dynamics were decodable 400 ms prior to the decision to close a segment and open a new one, and especially fronto-polar regions (BA10) were associated with this representational dynamic. Groups differed in their use of this representational dynamics to guide behavior and there was a higher sensitivity to incoming information in the Fine-grain group. Moreover, a higher likelihood to set event boundaries was reflected by activity increases in the insular cortex suggesting an increased monitoring of potentially relevant upcoming events. The study connects the EST with the metacontrol framework and relates these to overarching neural concepts of prefrontal cortex function.

Prenatal Exposure of PFAS in Cohorts of Pregnant Women: Identifying the Critical Windows of Vulnerability and Health Implications.

Cohorts of pregnant women in 2018 and 2020 were selected to explore prenatal exposure to perfluoroalkyl and polyfluoroalkyl substances (PFAS). Maternal serum during the whole pregnancy (first to third trimesters) and matched cord serum were collected for the analysis of 50 PFAS. Perfluorooctanoic acid (PFOA), perfluorooctanesulfonic acid (PFOS), and 6:2 fluorotelomer sulfonic acid (6:2 FTS) were the dominant PFAS in both the maternal and cord serum. The median ∑PFAS concentration was 14.18 ng/mL, and the ∑PFAS concentration was observed to decline from the first trimester to the third trimester. The transplacental transfer efficiencies (TTE) of 29 PFAS were comprehensively assessed, and a "U"-shaped trend in TTE values with increasing molecular chain length of perfluoroalkyl carboxylic acid (PFCA) was observed in this study. Moreover, the maternal concentrations of 9-chlorohexadecafluoro-3-oxanonane-1-sulfonic acid (6:2 Cl-PFESA), perfluorononanoic acid (PFNA), perfluorodecanoic acid (PFDA), perfluoroundecanoic acid (PFUdA), perfluorododecanoic acid (PFDoA), PFOS, and hexafluoropropylene oxide dimer acid (HFPO-DA) in the 2020 cohort were significantly lower than those in the 2018 cohort, declining by about 23.85-43.2% from 2018 to 2020 (p < 0.05). Higher proportions of emerging PFAS were observed in fetuses born in 2020. This birth cohort was collected during the COVID-19 epidemic period. The change in the PFAS exposure scene might be in response to the different exposure profiles of the 2018 and 2020 cohorts, which are attributed to the impact of COVID-19 on the social activities and environment of pregnant women. Finally, by application of a multiple informant model, the third trimester was identified as the critical window of vulnerability to PFAS exposure that affects birth weight and birth length.

Research on escape route planning analysis in forest fire scenes based on the improved A* algorithm

The forest fire environment is complex and volatile, posing a serious threat to the lives of firefighters at any time. Aiming at how people choose escape routes when facing these dangers, this paper proposed an escape route planning method based on the improved A* algorithm. Taking the forest fire that occurred in Xintian County, Yongzhou City, Hunan Province on October 17, 2022, as the research object, this study collected data from multi-temporal remote sensing imagery including GF-4, and Sentinel-2 to obtain 11 factors affecting the escape route planning. We used the FAHP-CRITIC combination weighting method to analyze the weights of the escape impact factors. Forest fire scenes were categorized into five classes based on escape risk coefficient from high to low. The heuristic function and weight coefficients of the traditional A* algorithm were reconstructed to obtain the improved A* algorithm. The computing time of both A* algorithm is similar in the same fire scene. But the percentage of the escape route length, located inside the high-risk zones, in the total escape route planned by the improved algorithm decreased by 53.63% than that planned by the traditional A* algorithm. The escape risk coefficient was reduced by 24.22%, and the escape safety was significantly improved. On this basis, the study combined the improved A* algorithm with the dynamic escape window method to search for the nearest safe area to the escapees and compute the corresponding escape routes. The real-time safety of the algorithm was verified using GF-1 remote sensing images obtained 7 and 35 min after the previous fire burning moment. Results revealed that the escape paths planned by the improved A* algorithm remained in a safe state and were able to be updated in real time according to the trend of the fire. This demonstrates the ability of the improved A* algorithm to adapt to real-time changes in forest fire scenes. It can provide multiple reliable escape options for escapees, thus scientifically and effectively reducing human casualties.

Recent Advances in Bio-Inspired Vision Sensor: A Review

Event-based cameras, also known as biologically inspired visual sensors, are capable of capturing real-time scene changes efficiently. Unlike traditional frame-based cameras, event cameras solely report triggered pixel-level brightness changes which are referred to as events. Event-based cameras show many advantages such as high temporal resolution, low latency, and high dynamic range, making them very attractive in robotics and computer vision, especially in challenging scenarios that are too demanding for traditional cameras. In this paper, we provide a comprehensive overview of the emerging field of event-based vision, focusing on the operation principle, sampling mechanisms, and algorithms that take advantage of their superior features. We also delve into the various tasks for which event cameras are utilized, such as object tracking, optical flow estimation, 3D reconstruction, SLAM, image reconstruction, and recognition. Additionally, we highlight the challenges and future opportunities for event cameras, seeking a more efficient way for machines to perceive and interact with the world.

Familiarity Alters the Bandwidth of Perceptual Awareness.

Results from paradigms like change blindness and inattentional blindness indicate that observers are unaware of numerous aspects of the visual world. However, intuition suggests that perceptual experience is richer than these results indicate. Why does it feel like we see so much when the data suggests we see so little? One possibility stems from the fact that experimental studies always present observers with stimuli that they have never seen before. Meanwhile, when forming intuitions about perceptual experience, observers reflect on their experiences with scenes with which they are highly familiar (e.g., their office). Does prior experience with a scene change the bandwidth of perceptual awareness? Here, we asked if observers were better at noticing alterations to the periphery in familiar scenes compared with unfamiliar scenes. Here, we found that observers noticed changes to the periphery more frequently with familiar stimuli. Signal detection theoretic analyses revealed that when observers are unfamiliar with a stimulus, they are less sensitive at noticing (d') and are more conservative in their response criterion (c). Taken together, these results suggest that prior knowledge expands the bandwidth of perceptual awareness. It should be stressed that these results challenge the widely held idea that prior knowledge fills in perception. Overall, these findings highlight how prior knowledge plays an important role in determining the limits of perceptual experience and is an important factor to consider when attempting to reconcile the tension between empirical observation and personal introspection.

RICE: A Dataset and Baseline for Cloud Removal in Remote Sensing Images

Removing clouds is an essential preprocessing step in analyzing remote sensing images, as cloud-based overlays commonly occur in optical remote sensing images and can significantly limit the usability of the acquired data. Deep learning has exhibited remarkable progress in remote sensing, encompassing scene classification and change detection tasks. Nevertheless, the appli-cation of deep learning techniques to cloud removal in remote sensing images is currently con-strained by the limited availability of training datasets explicitly tailored for neural networks. This paper presents the Remote sensing Image Cloud rEmoving dataset (RICE) to address this challenge and proposes baseline models incorporating a convolutional attention mechanism, which has demonstrated superior performance in identifying and restoring cloud-affected regions, with quantitative results indicating a 3.08% improvement in accuracy over traditional methods. This mechanism empowers the network to comprehend better the spatial structure, local details, and inter-channel correlations within remote sensing images, thus effectively addressing the diverse distributions of clouds. Moreover, by integrating this attention mechanism, our models achieve a crucial comparison advantage, outperforming existing state-of-the-art techniques in terms of both visual quality and quantitative metrics. We propose adopting the Learned Per-ceptual Image Patch Similarity metric, which emphasizes perceptual similarity, to evaluate the quality of cloud-free images generated by the models. Our work not only contributes to advancing cloud removal techniques in remote sensing but also provides a comprehensive evaluation framework for assessing the fidelity of the generated images.