Spatial-temporal Regularization Research Articles

Spatial-Temporal Regularities of Hydrooptical Characteristics of the Ob River

Field studies conducted in spring (March 26 — April 9, 2022) and summer (June 5-16, 2022) in the Ob River mouth region at the three hydromorphological stations „Kazym-Mys“, „Azovy“, and „Salemal“ (YaNAO) to obtain new data on the hydrooptical characteristics of water in the Lower Ob river. Also, the trophic status and ecological state of the Lower Ob river region were assessed. The greatly varying light attenuation coefficient ε(λ) was calculated at the four characteristic wavelengths of 430, 450, 550, and 670 nm, respectively. It ranges from 9.3 m-1 to 22.1 m-1 during the winter low water (freeze-up) period and from 7.3 m-1 to 33.0 m-1 during the open water (high water) period. The calculated relative spectral contributions of major optically active components of water (pure water, suspension, yellow substance, chlorophyll) to ε(λ) suggest that suspension and yellow substance make up the maximal contribution at different horizons. Additionally, the calculated coefficient of light absorption by yellow substance кys(λ) varies within the ranges from 5.5 m-1 to 9.9 m-1 (spring) and from 3.1 m-1 to 17.0 m-1 (summer), respectively. The relative transparency was measured using the Secchi disc. The concentrations of yellow substance and major photosynthetic pigments — chlorophylls a, b, c, and carotenoids — were estimated alongside. The obtained results could be useful for environmental monitoring and predicting the dynamics of aquatic ecosystems in the region under climate change and increased anthropogenic pressure caused by the use of natural resources.

Learning dynamic spatial-temporal regularized correlation filter tracking with response deviation suppression via multi-feature fusion

Visual object tracking (VOT) for intelligent video surveillance has attracted great attention in the current research community, thanks to advances in computer vision and camera technology. Meanwhile, discriminative correlation filter (DCF) trackers garnered significant interest owing to their high accuracy and low computing cost. Many researchers have introduced spatial and temporal regularization into the DCF framework to achieve a more robust appearance model and further improve tracking performance. However, these algorithms typically set fixed spatial and temporal regularization parameters, which limit flexibility and adaptability under cluttered and challenging scenarios. To overcome these problems, in this work, we propose a new dynamic spatial–temporal regularization for the DCF tracking model that emphasizes the filter to concentrate on more reliable regions during the training stage. Furthermore, we present a response deviation-suppressed regularization term for responses to encourage temporal consistency and avoid model degradation by suppressing relative response changes between two consecutive frames. Moreover, we introduce a multi-memory tracking framework to exploit various features and each memory contributes to tracking the target across all frames. Significant experiments on the OTB-2013, OTB-2015, TC-128, UAV-123, UAVDT, and DTB-70 datasets have revealed that the performance thereof outperformed many state-of-the-art trackers based on DCF and deep-based frameworks in terms of tracking accuracy and tracking success rate.

Spatial-temporal regularized UAV correlation filter based on adaptive filter template

Due to its quick computation, the correlation filter (CF) is frequently employed in object-tracking activities. The occlusion and deformation of the tracking object during the CF tracking process will pollute the filter, which will cause the filter’s performance to degrade. This is especially obvious in unmanned aerial vehicle (UAV) tracking and increased interfered sequences will further aggravate the problem. In response to this problem, we use ARCF as the baseline and add a spatial-temporal regularization term based on the adaptive template. We also introduce a historical filter template to generate a more global adaptive template. The experimental results illustrate that our tracker has the most sophisticated capabilities compared to the other 8 SOTA trackers on the DTB70 benchmark.

Rethinking causality-driven robot tool segmentation with temporal constraints.

Vision-based robot tool segmentation plays a fundamental role in surgical robots perception and downstream tasks. CaRTS, based on a complementary causal model, has shown promising performance in unseen counterfactual surgical environments in the presence of smoke, blood, etc. However, CaRTS requires over 30 iterations of optimization to converge for a single image due to limited observability. To address the above limitations, we take temporal relation into consideration and propose a temporal causal model for robot tool segmentation on video sequences. We design an architecture named Temporally Constrained CaRTS (TC-CaRTS). TC-CaRTS has three novel modules to complement CaRTS-temporal optimization pipeline, kinematics correction network, and spatial-temporal regularization. Experiment results show that TC-CaRTS requires fewer iterations to achieve the same or better performance as CaRTS on different domains. All three modules are proven to be effective. We propose TC-CaRTS, which takes advantage of temporal constraints as additional observability. We show that TC-CaRTS outperforms prior work in the robot tool segmentation task with improved convergence speed on test datasets from different domains.

Investigation of gait and balance function in cervical spondylotic myelopathy patients using wearable sensors

Background ContextCervical spondylotic myelopathy (CSM) is a degenerative disease caused by cervical cord compression and can lead to the significant impairment of motor function including gait and balance disturbances and changes in lower extremity muscle activity. PurposeThis study aimed to characterize gait, balance and lower extremity muscle activity in patients with CSM compared to age-matched healthy controls (HCs) using wearable sensors in the clinical setting. Study DesignNonrandomized, prospective cohort study. Patient SampleTen CSM patients and 10 age-matched HCs were recruited for this study. Outcome MeasuresGait and balance function parameters contained spatial temporal parameters, step regularity (SR1), stride regularity (SR2) and harmonic ratio (HR). EMG muscle activity parameters included time to peak and peak value during loading, stance, and swing phase. MethodsIn this study, parameters of gait and balance function were extracted using triaxial accelerometer attached to the spinous processes of Lumbar 5 while participants performed an overground walking at a self-preferred speed. Moreover, muscular activity was simultaneously recorded via sEMG sensors attached to tibialis anterior (TA), rectus femoris (RF), bicep femoris (BF), and gastrocnemius lateral (GL). Independent sample t test was used to find the differences between CSM patients and HCs. ResultsGait analysis showed cadence, step length and walking speed were statistically significantly lower in CSM patients than HCs. Stride time was significantly higher for CSM patients in comparison to HCs. Lower root mean square ratio (RMSR) of acceleration in the mediolateral (ML) direction, HR in the anteroposterior (AP) direction, SR1 in the AP direction and SR2 in all three directions were observed in CSM patients. For muscle activity analysis, EMG RMS for TA and RF during loading phase and RMS for GL during midstance phase was significantly lower for CSM patients, while significantly higher value was observed for RF RMS during midstance phase and GL RMS during swing phase in CSM patients. ConclusionOur pilot study shows that wearable sensors are able to detect the changes of gait, balance and lower extremity muscle activities of CSM patients in the clinical setting. This pilot study sets the stage for future researches on the diagnosis and monitor progression of CSM disease using wearable technology.

A Context- and Trajectory-Based Destination Prediction of Public Transportation Users

Location prediction based on contextual information is the core of a plethora of personalized location-based services (LBSs). Several applications require the use of techniques for predicting travel destinations based on human movement. Network analyses of human behavioral data show how the spatial-temporal regularity of human movement can be harnessed for inferring human mobility patterns. However, techniques are often based on a limited number of contextual features, which may limit prediction accuracy, especially if only historical location data are used. Using movement data obtained from public transportation users, we investigate the utility of contextual features derived via the installation of Bluetooth beacons in transportation vehicles and software tools in end-users’ travel applications. Using a multiclass random forest classifier, we show that contextual information of a user’s past travel history and at journey onset goes beyond spatial information and boosts destination prediction accuracy. The likely destination and travel-path length obtained at journey onset can then serve as the input for a stochastic-based model to predict a destination based on acquired trajectory information. Here we show that previously predicted destinations boost the performance of a Markov chain network. Thus, various contextual information at the start of a journey provides information beyond the location information acquired during a journey’s progression that can be employed for destination prediction. These findings have strong implications for LBSs as they require accurate destination prediction at early stages of a journey while at the same time mitigating the privacy concerns associated with collection of location data.

Electrocortical activity prior to predictable and unpredictable stimuli requiring a motor response

BACKGROUND: The fronto-central slow-wave known as the contingent negative variation (CNV) is an electroencephalographic measure related to the ability of the motor system to extract spatial-temporal regularities to produce a motor response. AIM: This study aimed to investigate the levels of electrocortical activity prior to predictable and unpredictable stimuli in a motor control task, and the association between CNV and reaction time (RT). METHOD: Seventeen participants performed a task that consisted of removing the right index finger from the space bar as fast as possible after stimulus onset. All participants practiced under both a predictable (PC) and an unpredictable (UC) context. RESULTS: Results indicated that RT under the unpredictable context was slower than under the predictable context. However, CNV levels under predictable and unpredictable contexts did not differ. CONCLUSION: The certainty of stimulus appearance in the UC may have produced effects similar to those under the PC, resulting in similar CNV levels. However, the use of this mechanism under the UC was suboptimal to motor performance.

ST-CRMF: Compensated Residual Matrix Factorization with Spatial-Temporal Regularization for Graph-Based Time Series Forecasting.

Despite the extensive efforts, accurate traffic time series forecasting remains challenging. By taking into account the non-linear nature of traffic in-depth, we propose a novel ST-CRMF model consisting of the Compensated Residual Matrix Factorization with Spatial-Temporal regularization for graph-based traffic time series forecasting. Our model inherits the benefits of MF and regularizer optimization and further carries out the compensatory modeling of the spatial-temporal correlations through a well-designed bi-directional residual structure. Of particular concern is that MF modeling and later residual learning share and synchronize iterative updates as equal training parameters, which considerably alleviates the error propagation problem that associates with rolling forecasting. Besides, most of the existing prediction models have neglected the difficult-to-avoid issue of missing traffic data; the ST-CRMF model can repair the possible missing value while fulfilling the forecasting tasks. After testing the effects of key parameters on model performance, the numerous experimental results confirm that our ST-CRMF model can efficiently capture the comprehensive spatial-temporal dependencies and significantly outperform those state-of-the-art models in the short-to-long terms (5-/15-/30-/60-min) traffic forecasting tasks on the open Seattle-Loop and METR-LA traffic datasets.

Correlation filter tracking algorithm based on spatial-temporal regularization and context awareness

Correlation filter tracking algorithm based on spatial-temporal regularization and context awareness

Second-Order Spatial-Temporal Correlation Filters for Visual Tracking

Discriminative correlation filters (DCFs) have been widely used in visual object tracking, but often suffer from two problems: the boundary effect and temporal filtering degradation. To deal with these issues, many DCF-based variants have been proposed and have improved the accuracy of visual object tracking. However, these trackers only adopt first-order data-fitting information and have difficulty maintaining robust tracking in unconstrained scenarios, especially in the case of complex appearance variations. In this paper, by introducing a second-order data-fitting term to the DCF, we propose a second-order spatial–temporal correlation filter (SSCF) learning model. To be specific, the SSCF tracker both incorporates the first-order and second-order data-fitting terms into the DCF framework and makes the learned correlation filter more discriminative. Meanwhile, the spatial–temporal regularization was integrated to develop a robust model in tracking with complex appearance variations. Extensive experiments were conducted on the benchmarking databases CVPR2013, OTB100, DTB70, UAV123, and UAVDT-M. The results demonstrated that our SSCF can achieve competitive performance compared to the state-of-the-art trackers. When penalty parameter λ was set to 10−5, our SSCF gained DP scores of 0.882, 0.868, 0.706, 0.676, and 0.928 on the CVPR2013, OTB100, DTB70, UAV123, and UAVDT-M databases, respectively.

Stochastic fractional heat equation perturbed by general Gaussian and non-Gaussian noise

In this work, we study the stochastic heat equation with Caputo derivative perturbed by a class of noises that include Gaussian noises and non-Gaussian noises. We have deduced the existence, uniqueness and pathwise spatial–temporal regularity properties of mild solutions to the corresponding non-linear time-fractional stochastic heat type equation.

Robust DCF object tracking with adaptive spatial and temporal regularization based on target appearance variation

To alleviate the boundary effect and constrain the update of the tracking model, current object tracking methods based on Discriminative Correlation Filter (DCF) usually introduce spatial and temporal regularization constraints in the filter training objective function. However, these regularization constraints with fixed coefficients greatly limit the adaptability of the tracker with respect to target appearance variation. This paper proposes a spatial-temporal regularization model based on the real-time target appearance variation for the filter training, improving the adaptability of the filter related to target appearance variation. Moreover, the filter training objective function with the adaptive spatial-temporal regularization is proposed to enhance the robustness of the filter. Finally, an iterative optimization method based on the alternating direction method of multipliers (ADMM) is proposed to update the filter, and the convergence proof of the optimization method is also presented. Comparison experiments with some representative trackers including ASRCF,ARCF, CSR_CF, DSAR_CF and SSR_CF etc. on OTB2015, UAV123 and LaSOT databases show that the proposed algorithm effectively improves the tracking accuracy.

Learning Spatial–Temporal Background-Aware Based Tracking

Discriminative correlation filter (DCF) based tracking algorithms have obtained prominent speed and accuracy strengths, which have attracted extensive attention and research. However, some unavoidable deficiencies still exist. For example, the circulant shifted sampling process is likely to cause repeated periodic assumptions and cause boundary effects, which degrades the tracker’s discriminative performance, and the target is not easy to locate in complex appearance changes. In this paper, a spatial–temporal regularization module based on BACF (background-aware correlation filter) framework is proposed, which is performed by introducing a temporal regularization to deal effectively with the boundary effects issue. At the same time, the accuracy of target recognition is improved. This model can be effectively optimized by employing the alternating direction multiplier (ADMM) method, and each sub-problem has a corresponding closed solution. In addition, in terms of feature representation, we combine traditional hand-crafted features with deep convolution features linearly enhance the discriminative performance of the filter. Considerable experiments on multiple well-known benchmarks show the proposed algorithm is performs favorably against many state-of-the-art trackers and achieves an AUC score of 64.4% on OTB-100.

Adaptive Spatial-Temporal Regularization for Correlation Filters Based Visual Object Tracking

Recently, Discriminative Correlation Filters (DCF) have shown excellent performance in visual object tracking. The correlation for a computing response map can be conducted efficiently in Fourier domain by Discrete Fourier Transform (DFT) of inputs, where the DFT of an image has symmetry on the Fourier domain. To enhance the robustness and discriminative ability of the filters, many efforts have been devoted to optimizing the learning process. Regularization methods, such as spatial regularization or temporal regularization, used in existing DCF trackers aim to enhance the capacity of the filters. Most existing methods still fail to deal with severe appearance variations—in particular, the large scale and aspect ratio changes. In this paper, we propose a novel framework that employs adaptive spatial regularization and temporal regularization to learn reliable filters in both spatial and temporal domains for tracking. To alleviate the influence of the background and distractors to the non-rigid target objects, two sub-models are combined, and multiple features are utilized for learning of robust correlation filters. In addition, most DCF trackers that applied 1-dimensional scale space search method suffered from appearance changes, such as non-rigid deformation. We proposed a 2-dimensional scale space search method to find appropriate scales to adapt to large scale and aspect ratio changes. We perform comprehensive experiments on four benchmarks: OTB-100, VOT-2016, VOT-2018, and LaSOT. The experimental results illustrate the effectiveness of our tracker, which achieved a competitive tracking performance. On OTB-100, our tracker achieved a gain of 0.8% in success, compared to the best existing DCF trackers. On VOT2018, our tracker outperformed the top DCF trackers with a gain of 1.1% in Expected Average Overlap (EAO). On LaSOT, we obtained a gain of 5.2% in success, compared to the best DCF trackers.

Spatial-temporal Regularized Multi-modality Correlation Filters for Tracking with Re-detection

The development of multi-spectrum image sensing technology has brought great interest in exploiting the information of multiple modalities (e.g., RGB and infrared modalities) for solving computer vision problems. In this article, we investigate how to exploit information from RGB and infrared modalities to address two important issues in visual tracking: robustness and object re-detection. Although various algorithms that attempt to exploit multi-modality information in appearance modeling have been developed, they still face challenges that mainly come from the following aspects: (1) the lack of robustness to deal with large appearance changes and dynamic background, (2) failure in re-capturing the object when tracking loss happens, and (3) difficulty in determining the reliability of different modalities. To address these issues and perform effective integration of multiple modalities, we propose a new tracking-by-detection algorithm called Adaptive Spatial-temporal Regulated Multi-Modality Correlation Filter. Particularly, an adaptive spatial-temporal regularization is imposed into the correlation filter framework in which the spatial regularization can help to suppress effect from the cluttered background while the temporal regularization enables the adaptive incorporation of historical appearance cues to deal with appearance changes. In addition, a dynamic modality weight learning algorithm is integrated into the correlation filter training, which ensures that more reliable modalities gain more importance in target tracking. Experimental results demonstrate the effectiveness of the proposed method.

Multi-city traffic flow forecasting via multi-task learning

Traffic flow forecasting or prediction plays an important role in the traffic control and management of a city. Existing works mostly train a model using the traffic flow data of a city and then test the trained model using the data of the same city. It may not be truly intelligent as there are many cities around us and there should be some shared knowledge among different cities. The data of a city and its knowledge can be used to help improve the traffic flow forecasting of other cities. To address this motivation, we study building a universal deep learning model for multi-city traffic flow forecasting. In this paper, we exploit spatial-temporal correlations among different cities with multi-task learning to approach the traffic flow forecasting tasks of multiple cities. As a result, we propose a M ulti-city T raffic flow forecasting N etwork (MTN) via multi-task learning to extract the spatial dependency and temporal regularity among multiple cities later used to improve the performance of each individual city traffic flow forecasting collaboratively. In brief, the proposed model is a quartet of methods: (1) It integrates three temporal intervals and formulates a multi-interval component for each city to extract temporal features of each city; (2) A spatial-temporal attention layer with 3D Convolutional kernels is plugged into the neural networks to learn spatial-temporal relationship; (3) As traffic peak distributions of different cities are often similar, it proposes to use a peak zoom network to learn the peak effect of multiple cities and enhance the prediction performance on important time steps in different cities; (4) It uses a fusion layer to merge the outputs from distinct temporal intervals for the final forecasting results. Experimental results using real-world datasets from DIDI show the superior performance of the proposed model.

Закономірності формування та функціонування геосистем Стебницького хвостосховища

The specifics of the landscape structure within the first section of the Stebnyk tailings dam are considered. Two landscape terrains (of natural and anthropogenic genesis), 3 separate landscape belts, 8 types of landscape tracts, and 30 types of landscape sub-tracts have been identified. Geosystems are dominated by flat sloping surfaces of the tailings dam, the external embanked of which forms closed drainless areas requiring systematic regulation of the level of the final reservoir. Features of filling the tailings surfaces played an important relief-forming role. At the same time, there were raised areas (0.5‒2.5 m) confined to the southern and south-western parts of it. Actually, conditions for the formation of tree-bush and meadow-marsh vegetation of different stages of succession were created in these areas. Spatial-temporal regularities of the occurrence and development of plant communities within the first section of the Stebnyk tailings dam were determined based on the decryption of space images for 2006‒2018. Primary meadow-marsh, bush-meadow, and tree-bush communities on surfaces with different levels of salinization were distinguished. In fact, these communities form the primary succession series in the formation of vegetation cover of post-mining geosystems. To decipher the boundaries of plant communities, 16 space images were obtained from the publicly available Google Earth Pro program. The tendencies of changes in the number and area of the plots occupied by different plant groups have been determined. Currently, the area of tree-bush communities is 5.59 hectares (7.87 % of the total area). Bush-meadow and meadow-marsh communities recorded an intensive increase in areas by 2014, followed by a rapid decrease caused by salinization of areas due to significant elevations of the reservoir’s level. In 2014, maximum areas of plant communities (37.55 ha) were identified, covering more than half of the study area (52.84 %), and in 2018 they occupied 21.71 ha (30.55 %). The gradual differentiation of phytocoenoses by moisture gradients and soil salinization continues. To maintain the rate of overgrowth of the first section of the Stebnyk tailings dam, it is necessary to reduce the level of brines regularly.

WELL-POSEDNESS AND CONVERGENCE FOR TIME-SPACE FRACTIONAL STOCHASTIC SCHRÖGER-BBM EQUATION

<abstract> In this paper, the Banach fixed point theorem combined with Mittag-Leffler functions has been used to obtain the existence and uniqueness of global mild solution for a kind of time-space fractional stochastic Schr򤩮ger-BBM equation driven by Gaussian noise. The spatial-temporal regularity of the nonlocal stochastic convolution is established. Furthermore the convergence and simulation is provided by the Galerkin finite element method as well. </abstract>

Measuring spatial-temporal regularities of river flow based on IOT technology

Measuring spatial-temporal regularities of river flow based on IOT technology

Learning Dynamic Spatial-Temporal Regularization for UAV Object Tracking

With the wide vision and high flexibility, unmanned aerial vehicle (UAV) has been widely used into object tracking in recent years. However, its limited computing capability poses a great challenges to tracking algorithms. On the other hand, Discriminative Correlation Filter (DCF) based trackers have attracted great attention due to their computational efficiency and superior accuracy. Many studies introduce spatial and temporal regularization into the DCF framework to achieve a more robust appearance model and further enhance the tracking performance. However, such algorithms generally set fixed spatial or temporal regularization parameters, which lack flexibility and adaptability under cluttered and challenging scenarios. To tackle such issue, in this letter, we propose a novel DCF tracking model by introducing dynamic spatial regularization weight, which encourage the filter focuses on more reliable region during training stage. Furthermore, our method could optimize the spatial and temporal regularization weight simultaneously using Alternative Direction Method of Multiplies (ADMM) technique method, where each sub-problem has closed-form solution. Through the joint optimization, our tracker could not only suppress the potential distractors but also construct robust target appearance on the basis of reliable historical information. Experiments on two UAV benchmarks have demonstrated that our tracker performs favorably against other state-of-the-art algorithms.