Spatio-temporal Objects Research Articles

Multi-granularity spatiotemporal object modelling of waterborne traffic elements

The electronic navigational charts are crucial carriers for representing the multi-source heterogeneous data of Waterborne Traffic Elements (WTEs). However, their layer-based modelling method has some shortcomings in expressing the multi-granularity features, complex relationships, and dynamic evolution of elements. This paper proposes an objectification modelling method for WTEs based on the concept of multi-granularity spatiotemporal object modelling. A classification system for waterborne traffic objects is developed based on the relevance of behavior to elements; combining characteristics of waterborne traffic, a data model for waterborne traffic objects is constructed from eight aspects: spatiotemporal reference, spatiotemporal position, spatial form, basic information, attributes, behavioral ability, structure, and associative relationships. An object extraction function is also established, extracting object attributes and relationships between objects according to different element classes. Taking the Jiashan section of the Hangzhou-Shanghai Line in Zhejiang Province as the experimental subject, the multi-granularity spatiotemporal characteristics, dynamic evolution, and relationship expression of channel class objects are tested. The experimental results show that the proposed method provides the theoretical basis and data organization mode for the multi-granularity expression of WTEs.

K-dStHash tree for indexing big spatio-temporal datasets

Today’s era is witness of tremendous ever growing spatial, temporal and spatiotemporal data. The huge spatio-temporal data immensely pushes the need for design and development of novel methods tailored for indexing spatio-temporal data. In this research paper, we propose the design of a novel spatio-temporal data indexing method, named as k-dStHash. We have proposed the algorithm k-dStHashInsertion for inserting spatio-temporal objects and an algorithm k-dStHashSrchPlaceTime has been used to search for the objects at given location and time. It is able to handle datasets with duplicate keys which has been ignored in many research works. Though the algorithm k-dStHashInsertion takes 1.3-1.5 times longer time to insert data in k-dStHash data structure as it needs to find a specific location to organize data efficiently, but when it comes to search for required records it is even more than 90 times faster when analyzed in comparison to brute force method. It is generalized enough to organize any kind of k-dimensional data and time-based data also including object finding, fleet management, clustering, leader identification, nearest neighbor, human/animal tracking, path finding and many more.

Stereoscopic artificial compound eyes for spatiotemporal perception in three-dimensional space.

Arthropods' eyes are effective biological vision systems for object tracking and wide field of view because of their structural uniqueness; however, unlike mammalian eyes, they can hardly acquire the depth information of a static object because of their monocular cues. Therefore, most arthropods rely on motion parallax to track the object in three-dimensional (3D) space. Uniquely, the praying mantis (Mantodea) uses both compound structured eyes and a form of stereopsis and is capable of achieving object recognition in 3D space. Here, by mimicking the vision system of the praying mantis using stereoscopically coupled artificial compound eyes, we demonstrated spatiotemporal object sensing and tracking in 3D space with a wide field of view. Furthermore, to achieve a fast response with minimal latency, data storage/transportation, and power consumption, we processed the visual information at the edge of the system using a synaptic device and a federated split learning algorithm. The designed and fabricated stereoscopic artificial compound eye provides energy-efficient and accurate spatiotemporal object sensing and optical flow tracking. It exhibits a root mean square error of 0.3 centimeter, consuming only approximately 4 millijoules for sensing and tracking. These results are more than 400 times lower than conventional complementary metal-oxide semiconductor-based imaging systems. Our biomimetic imager shows the potential of integrating nature's unique design using hardware and software codesigned technology toward capabilities of edge computing and sensing.

Analysis of Lake Shoreline Evolution Characteristics Based on Object Increments

Evolutionary changes in shallow lake shorelines can significantly impact wetland biodiversity transformation. This paper aims to further elucidate the wetland evolution process by investigating the temporal and spatial characteristics and rules governing lake shoreline evolution. Departing from traditional analyses of wetland area and shoreline length changes, this paper presents a comprehensive approach to quantifying typical lake shoreline evolution patterns using the concept of object increments. These evolutionary patterns are classified into four types: “expansion”, “shrinkage”, “appearance”, and “disappearance”. Using Shengjin Lake as a case study, Landsat images from 2001 to 2020 were used to extract the lake shoreline. The temporal series characteristics of different evolution patterns, the laws at the patch scale, and the characteristics of evolution direction were analyzed. The key findings are as follows. (1) The evolution of Shengjin Lake’s shoreline from 2001 to 2020 was primarily characterized by “expansion” or “shrinkage” patterns with a clear negative correlation between them. The “appearance” and “disappearance” of lake shorelines were rare. (2) The evolutionary patterns of “expansion” or “shrinkage” mainly occurred in smaller patches with a large number, while the “appearance” and “disappearance” of lake shorelines occurred mostly in larger patches with a small number, and there were no occurrences in certain years. (3) The “expansion” evolutionary pattern was more dominant in the northeast and east-by-northeast regions, while the “shrinkage” evolutionary pattern varied across the southwest and west-by-southwest regions. In conclusion, the analysis of shoreline evolution’s temporal and spatial characteristics, based on spatiotemporal object increments, can quantitatively elucidate the lake wetland evolution process and offers a novel perspective for future research on lake wetlands.

STO2Vec: A Multiscale Spatio-Temporal Object Representation Method for Association Analysis

Spatio-temporal association analysis has attracted attention in various fields, such as urban computing and crime analysis. The proliferation of positioning technology and location-based services has facilitated the expansion of association analysis across spatio-temporal scales. However, existing methods inadequately consider the scale differences among spatio-temporal objects during analysis, leading to suboptimal precision in association analysis results. To remedy this issue, we propose a multiscale spatio-temporal object representation method, STO2Vec, for association analysis. This method comprises of two parts: graph construction and embedding. For graph construction, we introduce an adaptive hierarchical discretization method to distinguish the varying scales of local features. Then, we merge the embedding method for spatio-temporal objects with that for discrete units, establishing a heterogeneous graph. For embedding, to enhance embedding quality for homogeneous and heterogeneous data, we use biased sampling and unsupervised models to capture the association strengths between spatio-temporal objects. Empirical results using real-world open-source datasets show that STO2Vec outperforms other models, improving accuracy by 16.25% on average across diverse applications. Further case studies indicate STO2Vec effectively detects association relationships between spatio-temporal objects in a range of scenarios and is applicable to tasks such as moving object behavior pattern mining and trajectory semantic annotation.

Kant on Mind-Dependence: Possible or Actual Experience?

AbstractIn Kant’s idealism, all spatiotemporal objects depend on the human mind in a certain way. A central issue here is whether the existence of spatiotemporal things requires that these things are, at least at some point, objects of some actual experience or of a merely possible experience. In this essay, I argue (on textual and philosophical grounds) for the latter view: spatiotemporal things exist (or spatiotemporal events occur) if they are objects of a (suitably qualified) possible experience.

Voxel modeling and association of ubiquitous spatiotemporal information in natural language texts

ABSTRACT The ubiquitous spatiotemporal information extracted from Internet texts limits its application in spatiotemporal association and analysis due to its unstructured nature and uncertainty. This study uses ST-Voxel modeling to solve the problem of structured modeling and the association of ubiquitous spatiotemporal information in natural language texts. It provides a new solution for associating ubiquitous spatiotemporal information on the Internet and discovering public opinion. The main contributions of this paper include: (1) It proposes a convolved method for ST-Voxel, which solves the voxel modeling problem of unstructured and uncertain spatiotemporal objects and spatiotemporal relation in natural language texts. Experiments show that this method can effectively model 5 types of spatiotemporal objects and 16 types of uncertain spatiotemporal relation founded in texts; (2) It realizes the unknown event discovery based on voxelized spatiotemporal information association. Experiments show that this method can effectively solve the aggregation of ubiquitous spatiotemporal information in multi-natural language texts, which is conducive to discovering spatiotemporal events. The selection of convolution parameters in voxel modeling is also discussed. A parameter selection method for balancing the discovery capability and discovery accuracy of spatiotemporal events is given.

The Senses of Apeiron in Philebus 16b–27c

Abstract Scholars debate whether ‘apeiron’ (unlimited) is univocal or multivocal in Plato’s Philebus. Offering a ‘middle path,’ I argue that the term is univocal, but used with respect to two senses of unlimited continua. The term appears early in two dense passages on ontological structure: the descriptions of the ‘god-given method’ (16b–18d) and ‘the fourfold division of beings’ (23c–27c). I consider each passage and argue that they respectively concern the eidetic continua of being that the knower comes to understand and the fluxing continua of opposed and co-constitutive bodily elements from which spatiotemporal objects derive their natures. They also indicate two major influences on Plato, respectively the Pythagorean and Heraclitean as recorded in Aristotle’s Metaphysics, and I draw on these resources to develop my account. I conclude by considering some important Platonic lessons that we learn from thinking through this distinction between the related senses of the unlimited.

Why I am not an Anti-Haecceitist

In this paper I argue that if the Identity of Indiscernibles is not necessarily true, then Haecceitism ensues—where Haecceitism is the view that there are maximal possibilities that include all the same qualitative possibilities, and yet differ with respect to the non-qualitative possibilities they include. This goes against the common intuition that Anti-Haecceitism is compatible with the Identity of Indiscernibles being only contingently true. My argument is interesting in many respects. First, it shows that in any modal framework there is a connection between the number of worldbound ordinary spatio-temporal objects, and the number of overall possibilities. Second, it has repercussions for the tenability of some philosophical positions, like Generalism, which is usually interpreted as entailing Anti-Haecceitism while at the same time being compatible with the claim that the Identity of Indiscernibles is not necessarily true. If I am correct, Generalism and similar philosophical accounts turn out to be inconsistent. Finally, it provides a strong argument for Haecceitism, given that the majority of authors today find counterexamples to the Identity of Indiscernibles extremely convincing, and many philosophical positions have been and continue being criticised on the basis of their commitment to the Identity of Indiscernibles. The paper is structured as follows: I introduce Haecceitism and the Identity of Indiscernibles in Sects. 1 and 2 respectively. Drawing on a result from the Philosophy of Quantum Mechanics, which I survey in Sect. 3, I give my main argument in Sect. 4. Finally, I discuss some implications in Sect. 5.

Spatiotemporal Database Schema for Data Driven Applications in Smart Agriculture

Background: Data driven sustainable agriculture involves the collection, storage, processing, and analysis of enormous spatiotemporal data related to crop production processes, systems, infrastructure, and environment. Literature survey on smart agriculture research projects indicates that there is a need for improving handling of spatiotemporal data. There are gaps in handling spatial and temporal variability of parameters, division of crop field into management zones to reduce the variability for optimizing application of inputs such as fertilizers, water or pesticides. These gaps are to be addressed at design level of spatiotemporal database for smart agriculture. Objective: To engineer a spatiotemporal database schema that can be used for data driven sustainable agriculture. Methods: The methodology involves spatiotemporal data representation and modeling, Object oriented analysis and design of the database and Verification of the database using life cycle model and algorithmic steps. Findings: The resulting database is capable to store spatial and temporal variability of soil, plant and water parameters as well as handle spatial split, spatial merge, geometry and location changes of spatiotemporal objects. Novelty: Novel Use cases in smart agriculture along with spatiotemporal attributes are identified so that efficient applications can be realized. Adaption of the spatiotemporal database schema for Smart Irrigation System and its implementation methodology are presented. Keywords: Spatiotemporal Database Design; Data-Driven Agriculture; Agriculture Informatics; Database Verification; Spatiotemporal Data Analysis

EFFICIENT SPATIO-TEMPORAL MODELLING TO ENABLE TOPOLOGICAL ANALYSIS

Abstract. Time-dependent analysis scenarios such as heat, wind or flood analysis in cities and in landscapes need a correct and consistent modelling of geometry and topology over time. However, hitherto efficient time-dependent geometry models and topological analysis based on a mathematically sound theory were neglected when modelling objects in the built and natural environment. This is surprising as incorrect topological relationships over time such as not fitting neighbourhoods of surfaces or solids inevitably lead to wrong analysis results. In this paper we propose the combination of a spatio-temporal geometry model together with a topological schema to provide accessible and consistent objects over time. Where an efficient spatio-temporal geometry model reduces redundant geometric data and enables spatio-temporal queries, an efficient topological model minimizes the number of relations as far as possible and enables robust topological queries. The geometry model uses the concepts of point tubes, delta storage as well as net components and pre- and post-objects to enable the change of geometry and topology over time for natural structures, e.g., digital terrain models (DTM). Geometry here are the boundary and interior coordinates of the objects whereas topology here is interpreted in a wider sense than only focusing on geometrically induced topology to maintain topological consistency by the management of incidence relations. In addition, the topological schema introduces three basic bidirectional relation types to manage aggregations, abstractions and incidences in order to provide a general abstract topological schema for the management of complex intra- and inter-related spatio-temporal objects to enable the modelling of consistent complex topology over time. Finally, a conclusion is given highlighting the applicability of the approach and future research.

Challenges of intracellular visualization using virtual and augmented reality.

Microscopy image observation is commonly performed on 2D screens, which limits human capacities to grasp volumetric, complex, and discrete biological dynamics. With the massive production of multidimensional images (3D + time, multi-channels) and derived images (e.g., restored images, segmentation maps, and object tracks), scientists need appropriate visualization and navigation methods to better apprehend the amount of information in their content. New modes of visualization have emerged, including virtual reality (VR)/augmented reality (AR) approaches which should allow more accurate analysis and exploration of large time series of volumetric images, such as those produced by the latest 3D + time fluorescence microscopy. They include integrated algorithms that allow researchers to interactively explore complex spatiotemporal objects at the scale of single cells or multicellular systems, almost in a real time manner. In practice, however, immersion of the user within 3D + time microscopy data represents both a paradigm shift in human-image interaction and an acculturation challenge, for the concerned community. To promote a broader adoption of these approaches by biologists, further dialogue is needed between the bioimaging community and the VR&AR developers.

Sortals, bodies, and variables. A critique of Quine’s theory of reference

Among the philosophical accounts of reference, Quine’s (1974) The Roots of Reference stands out in offering an integrated account of the acquisition of linguistic reference and object individuation. Based on a non-referential ability to distinguish bodies, the acquisition of sortals and quantification are crucial steps in learning to refer to objects. In this article, we critically re-assess Quine’s account of reference. Our critique will proceed in three steps with the aim of showing that Quine effectively presupposes what he sets out to explain, namely, reference to objects. We are going to argue (i) that sortals do not individuate, (ii) that bodies are already objects, and (iii) that the acquisition of variables presupposes a notion of identity. The result is diagnostic of a central desideratum for any theory of reference: an explanation of spatiotemporal object individuation.

Multimodal image translation via deep learning inference model trained in video domain

BackgroundCurrent medical image translation is implemented in the image domain. Considering the medical image acquisition is essentially a temporally continuous process, we attempt to develop a novel image translation framework via deep learning trained in video domain for generating synthesized computed tomography (CT) images from cone-beam computed tomography (CBCT) images.MethodsFor a proof-of-concept demonstration, CBCT and CT images from 100 patients were collected to demonstrate the feasibility and reliability of the proposed framework. The CBCT and CT images were further registered as paired samples and used as the input data for the supervised model training. A vid2vid framework based on the conditional GAN network, with carefully-designed generators, discriminators and a new spatio-temporal learning objective, was applied to realize the CBCT–CT image translation in the video domain. Four evaluation metrics, including mean absolute error (MAE), peak signal-to-noise ratio (PSNR), normalized cross-correlation (NCC), and structural similarity (SSIM), were calculated on all the real and synthetic CT images from 10 new testing patients to illustrate the model performance.ResultsThe average values for four evaluation metrics, including MAE, PSNR, NCC, and SSIM, are 23.27 ± 5.53, 32.67 ± 1.98, 0.99 ± 0.0059, and 0.97 ± 0.028, respectively. Most of the pixel-wise hounsfield units value differences between real and synthetic CT images are within 50. The synthetic CT images have great agreement with the real CT images and the image quality is improved with lower noise and artifacts compared with CBCT images.ConclusionsWe developed a deep-learning-based approach to perform the medical image translation problem in the video domain. Although the feasibility and reliability of the proposed framework were demonstrated by CBCT–CT image translation, it can be easily extended to other types of medical images. The current results illustrate that it is a very promising method that may pave a new path for medical image translation research.

Spatial-Temporal Data Integration Modeling and Dynamic Simulation of Coal-Rock Dynamic Disasters

To solve the problem of accurate identification of coal-rock dynamic disaster precursors, a spatiotemporal data integrated monitoring, and early warning system was proposed. The system consists of a spatiotemporal data integration model, a time series and visual monitoring, and an early warning platform. It takes the comprehensive mining face of a deep coal mine as the monitoring object. It uses structured light 3D scanning and Brillouin optical time domain reflectometry to collect physical entity data in the monitoring area, reconstructs data and processes data redundancy through edge microprocessors, and decomposes spatiotemporal objects into elements to construct a data integration model for data integration. Inner relationship and space-time unity. Using the time series database as the data integration model carrier, the processed physical entity data is mapped to the visual monitoring and early warning platform for dynamic simulation display, which provides data support for accurate early warning of coal-rock dynamic disasters. Finally, a prototype system is developed to verify the generality and feasibility of the system.

Spatiotemporal tubelet feature aggregation and object linking for small object detection in videos

This paper addresses the problem of exploiting spatiotemporal information to improve small object detection precision in video. We propose a two-stage object detector called FANet based on short-term spatiotemporal feature aggregation and long-term object linking to refine object detections. First, we generate a set of short tubelet proposals. Then, we aggregate RoI pooled deep features throughout the tubelet using a new temporal pooling operator that summarizes the information with a fixed output size independent of the tubelet length. In addition, we define a double head implementation that we feed with spatiotemporal information for spatiotemporal classification and with spatial information for object localization and spatial classification. Finally, a long-term linking method builds long tubes with the previously calculated short tubelets to overcome detection errors. The association strategy addresses the generally low overlap between instances of small objects in consecutive frames by reducing the influence of the overlap in the final linking score. We evaluated our model in three different datasets with small objects, outperforming previous state-of-the-art spatiotemporal object detectors and our spatial baseline.

Visualizing and quantifying the spatiotemporal expansion of the Blue Lentic Belt in Alabama and Mississippi

The Blue Lentic Belt is a spatial belt of dense lentic habitats formed in the Mobile River Basin since the 1990s, and it is imposing considerable environmental stress on local and downstream aquatic habitats. Depicting the spatiotemporal evolution of the Blue Lentic Belt is essential to understanding its formation and consequential impacts on local environments. However, relevant discussion on it is absent since the Blue Lentic Belt is a new discovery. In this study, we developed a retrospective delineation method to visualize the spatiotemporal evolution of the lentic habitats in the Mobile River Basin and a tesseral model to numerically analyze the spatiotemporal expansion of the Blue Lentic Belt. In the developed method, the baseline inventory of lentic habitats is first delineated from 2019 Sentinel-2 satellite imagery at a spatial resolution of 10 m. The baseline inventory is then used to retrospectively delineate the past lentic habitats in the Mobile River Basin using the National Land Cover Database (NLCD). Kernel density surfaces of lentic habitat image objects are estimated to detect the regions of dense lentic habitats, which sequentially form spatiotemporal objects of dense lentic habitats. The spatiotemporal objects of dense lentic habitats are projected onto planar space and are then structuralized as groups of spatial tesserae, namely α-peaks, β-slopes, and γ-edges. Attributes of these tesserae are numerically derived to quantify the spatiotemporal expansion of the Blue Lentic Belt. The results indicate that the Blue Lentic Belt has 4 α-peaks, 3 β-slopes, and a single γ-edge. It is formed from 4 stable hotspots (α-peaks) of the densest lentic habitats. The expansion of the Blue Lentic Belt ranges about 15.42 km. The expansion distance is about 0.57 of the average range of the β-slopes in the Blue Lentic Belt, indicating a significant change of landscape in the Mobile River Basin. The development of the farm-raised catfish industry is considered the main driving force in the formation of the Blue Lentic Belt. The outcomes of this study have emphasized the rapid expansion of the Blue Lentic Belt and its negative impacts on local and downstream aquatic habitats, which calls for attention to systemic investigations by multiple disciplines.

Modeling vague spatiotemporal objects based on interval type-2 fuzzy sets

Fuzziness is an inherent property of geographical phenomena and the processes of data acquisition, processing, and analysis often introduce uncertainty. Existing methods predominantly use fuzzy set (FS) theory to capture the fuzziness of geographical phenomena as fuzzy spatial objects. However, this approach has a conceptual confusion regarding fuzziness, uncertainty, and vagueness, and the membership degree is expressed using accurate values that ignore uncertainty. Furthermore, FS-based methods lack a vague temporal descriptor. Herein, a vague-spatiotemporal-object model based on the interval type-2 FS theory is proposed to express the vagueness of spatiotemporal objects. To verify the feasibility and superiority of the proposed method, the fuzzy and vague clustering algorithm was used to classify the vegetation cover types on Poyang Lake Plain, China. Furthermore, the classification accuracy was validated via field investigations, and its ability to identify the wet season of the area was verified via the annual vague water area changes of Poyang Lake. The results indicate that, compared with the spatial object model based on FSs, the proposed method increases the ability to measure membership error and express spatiotemporal vagueness.

Long-Range Multi-Object Tracking at Traffic Intersections on Low-Power Devices

The next generation of intelligent traffic signal control systems needs multi-object tracking (MOT) algorithms that can track vehicles hundreds of meters away from traffic intersections. To facilitate the integration of long-range MOT into existing traffic infrastructure, the tracker must achieve a good balance of cost-effectiveness, accuracy, and efficiency. Although much progress has been made on deep-learning-based MOT for video, these approaches have limited applicability for edge deployment since deep neural networks typically require power-hungry hardware accelerators to achieve real-time performance. Furthermore, traffic cameras have a field of view limited to near the intersection. To address these shortcomings, we introduce a practical MOT framework that fuses tracks from a novel video MOT neural architecture designed for low-power edge devices with tracks from a commercially available traffic radar. The proposed neural architecture achieves high efficiency by using depthwise separable convolutions to jointly predict object detections alongside a dense grid of features at a single scale for spatiotemporal object re-identification. A simple and effective late fusion strategy is also presented where tracks of distant vehicles from a traffic radar are handed over to the video tracker within a region where the sensor fields of view overlap. Our video tracker is empirically validated on the UA-DETRAC video MOT benchmark for traffic intersections and the multi-sensor tracker is evaluated on video and radar data collected and labeled by the authors at an instrumented traffic intersection.

Wet Tropospheric Correction Methods for Wide-Swath Altimeters

Wet troposphere path delay (WPD) is a crucial error source for wide-swath altimeters with high-resolution observations. This study generated a simulated wide-swath through the nadir microwave radiometer (MWR) track and evaluated four wide-swath wet tropospheric correction (WTC) methods based on multisource data from 2017 with strict spacetime windows. The Numerical Weather Model (NWM) method can provide a basic correction for the wide-swath altimeter. The MWR method, based on the extension of nadir 1-beam MWR, could not provide a reliable correction. The residual error increased rapidly after deviating from the nadir profile. The overall root-mean-square error (RMSE) of the combination method was approximately 0.58 cm and had high uniformity within the swath. Even at the far end of the swath, the correction was better than that on the NWM and MWR methods. The objective analysis (OA) method using linear spatiotemporal objective analysis had the best result among the four correction methods. The overall RMSE was only 0.49 cm, which was 34% lower than the NWM method. High consistency was maintained at each cross-track position of the swath. The last two wide-swath WTC methods provided in this study had high performance. For the wide-swath altimeter, the combination method is a scheme worthy of consideration, as it can provide WTC results conveniently, quickly, and accurately. Although the operation of the OA method is complex and depends on multisource observation data, it promises to be a high-quality scheme for the wide-swath altimeter WTC when a more accurate WTC value is required.