Multi-object tracking (MOT) aims to track multiple objects while maintaining consistent identities across frames of a given video. In unmanned aerial vehicle (UAV) recorded videos, frequent viewpoint changes and complex UAV-ground relative motion dynamics pose significant challenges, which often lead to unstable affinity measurement and ambiguous association. Existing methods typically model motion and appearance cues separately, overlooking their spatio-temporal interplay and resulting in suboptimal tracking performance. In this work, we propose AMOT, which jointly exploits appearance and motion cues through two key components: an Appearance-Motion Consistency (AMC) matrix and a Motion-aware Track Continuation (MTC) module. Specifically, the AMC matrix computes bi-directional spatial consistency under the guidance of appearance features, enabling more reliable and context-aware identity association. The MTC module complements AMC by reactivating unmatched tracks through appearance-guided predictions that align with Kalman-based predictions, thereby reducing broken trajectories caused by missed detections. Extensive experiments on three UAV benchmarks, including VisDrone2019, UAVDT, and VT-MOT-UAV, demonstrate that our AMOT outperforms current state-of-the-art methods and generalizes well in a plug-and-play and training-free manner.

Drive-by sensing, using vehicles as mobile sensors to collect environmental data, offers high spatiotemporal resolution monitoring. In drive-by sensing tasks, urban areas with intense human activity or pollution – termed high-priority hotspots – demand frequent sensing for adequate data collection. However, prior studies rarely address optimizing vehicle selection to enhance hotspot coverage frequency while maintaining non-hotspot coverage. This study formalized this problem as the Maximal Hotspot Regular Coverage Problem and proposed an Adaptive Level-Aware Vehicle Selection algorithm. Using air pollution hotspot sensing in Beijing as an empirical case, results show the advantage of the proposed algorithm over other baselines: Random selection (RS), Non-hotspot Greedy Adding and Multi-type hotspot Greedy MaxMin, covering 29.99% of hotspots and 77.08% non-hotspot zones with 1000 sensors on average. The spatial distribution of covered area and statistical distribution of average visits per hour reveals a large spatial range and high revisit times of the method, and its advantage over baselines in a hybrid sensing scenario is also proven (with 54.18% daily average coverage among all zones and 31.22% on hotspots). This study provides a method to advance the coverage of hotspots in single-type and hybrid sensing scenarios, inspiring a future extension of optimization based on the proposed algorithm.

Crop diseases present a critical threat to global food security, with traditional methods for disease detection often relying on manual diagnosis, which is labor-intensive and requires specialized expertise. While deep learning provides promising avenues for automated disease detection, many existing models are challenged by domain shift, performing poorly when applied to data from new environments with different distributions. To address this issue, we propose a novel cross-domain detection framework that integrates Multi-Domain Data Augmentation and Isolated Test-Time Adaptation Optimization (ITTA) to enhance model generalization and robustness in dynamic agricultural settings. Our approach begins with Multi-Domain Data Augmentation, which combines strong and weak augmenters to generate diverse cross-domain images. The strong augmenter, based on Generative Adversarial Networks (GANs), produces varied images that preserve class consistency, while the weak augmenter applies Gaussian noise and brightness adjustments to make the model more resilient to minor environmental changes. This dual augmentation strategy enables the model to learn domain-invariant features and improves its generalization capability across different domains. The second component ITTA, employs a teacher-student model structure that leverages the Fisher Information Matrix (FIM) to isolate domain-sensitive and domain-invariant parameters. During test-time adaptation, only the domain-sensitive parameters in the student model are updated, allowing the model to adapt to new domain-sensitive features while preserving essential knowledge from the source domain. This selective update process prevents catastrophic forgetting and maintains high detection accuracy under varying environmental conditions. Experimental results demonstrate that our framework significantly enhances model performance across diverse settings, offering a robust foundation for intelligent and precise crop disease detection, which is essential for improving agricultural productivity and food security. • A cross-domain framework for robust crop disease detection is proposed. • Dual augmentation using GANs and noise improves domain generalization. • FIM-guided teacher-student model avoids forgetting and adapts to new domains. • The method shows strong detection performance in diverse environments. • Selective updates ensure high accuracy in varied agricultural conditions.

Fixed-time tracking control is considered for a class of nonlinear systems in this article. Different from the conventional literature on fixed-time control studies, in this article, the nonlinearities of systems are all completely unknown. Fuzzy-logic systems are utilized to model these unknown nonlinearities. To deal with the fixed-time control under the approximation errors, three steps are taken. First, a new criterion of fixed-time stability is developed; second, a new fixed-time control scheme is proposed, which is different from the existing adaptive design method; and third, to analyze the fixed-time stability of the system, two novel inequalities are established. It shows that the proposed fuzzy control scheme can guarantee system performance in a fixed time, and the upper bound of the settling time only depends on the design parameters.

This paper studies the finite-time stabilization of a class of stochastic nonlinear systems. Different from functions which are necessarily known in the conventional finite-time control of nonlinear systems, the nonlinear functions can be completely unknown in this paper. By applying fuzzy-logic systems to approximate the unknown nonlinearities, a novel adaptive finite-time control strategy is proposed. However, due to the existence of approximation errors, the existing finite-time stability criterion cannot be used to analyze the stability of stochastic nonlinear systems. To deal with this difficulty, a finite-time stability criterion, by utilizing the mean value theorem of integrals, is first established in Lemma 5, which plays a significant role in the finite-time stability analysis of stochastic nonlinear systems. Then, the finite-time mean square stability of a stochastic nonlinear system is proved by combining Lemma 3 with Jensen's inequality.

This paper focuses on finite-time adaptive neural tracking control for nonlinear systems in nonstrict feedback form. A semiglobal finite-time practical stability criterion is first proposed. Correspondingly, the finite-time adaptive neural control strategy is given by using this criterion. Unlike the existing results on adaptive neural/fuzzy control, the proposed adaptive neural controller guarantees that the tracking error converges to a sufficiently small domain around the origin in finite time, and other closed-loop signals are bounded. At last, two examples are used to test the validity of our results.

The research on the sharing and interoperation of geospatial information is always a hotspot in GIS field. Many methods have been proposed such as data format transform, data direct access, Web GIS and data interoperation. These technologies have made great progresses in the sharing and interoperability of geospatial information. But there are many unconquerable problems such as the process of the distributed massive spatial data, providing integrated and transparent services, capability of geocomputing and migration of geospatial information services for users. In this paper, we combine grid and OGC web service to research how to realize the sharing and interoperation of geospatial information. We introduce the grid technology and OGC web service specifications. Then we design the architecture of integrated Grid and OGC. At last based on grid middleware Gloubs Toolkit 4 and Java technology, we develop and deploy Grid map services which encapsulate OGC Web Map Service.