Object detection in remote sensing plays a crucial role in various ground identification tasks. However, due to the limited feature information contained within small targets, which are more susceptible to being buried by complex backgrounds, especially in extreme environments (e.g., low-light, motion-blur scenes). Meanwhile, event cameras offer a unique paradigm with high temporal resolution and wide dynamic range for object detection. These advantages enable event cameras without being limited by the intensity of light, to perform better in challenging conditions compared to traditional cameras. In this work, we introduce the Multi-Vision Transformer (MVT), which comprises three efficiently designed components: the downsampling module, the Channel Spatial Attention (CSA) module, and the Global Spatial Attention (GSA) module. This architecture simultaneously considers short-term and long-term dependencies in semantic information, resulting in improved performance for small object detection. Additionally, we propose Cross Deformable Attention (CDA), which progressively fuses high-level and low-level features instead of considering all scales at each layer, thereby reducing the computational complexity of multi-scale features. Nevertheless, due to the scarcity of event camera remote sensing datasets, we provide the Event Object Detection (EOD) dataset, which is the first dataset that includes various extreme scenarios specifically introduced for remote sensing using event cameras. Moreover, we conducted experiments on the EOD dataset and two typical unmanned aerial vehicle remote sensing datasets (VisDrone2019 and UAVDT Dataset). The comprehensive results demonstrate that the proposed MVT-Net achieves a promising and competitive performance.

In the domain of visual perception tasks for Unmanned Aerial Vehicle (UAV) remote sensing, conventional object detection algorithms suffer severe challenges arise from drastic variations in perspective and complex backgrounds, proving particularly problematic for the identification of occluded and fast-motion targets. To address these issues, this paper proposes a novel dynamic streaming architecture that encompasses the following three solution approaches: 1) We have established a revolutionary Dual-Stage Streaming data pipeline (e.g., DSS Dataloader, DSS Sampler, and DSS Transform) to perceive target locations with more enriched spatiotemporal states, leveraging spatial pipeline to expedite rapid convergence on static representations, and applying temporal pipeline to facilitate fine-grained refinement by inject dynamic spatiotemporal details; 2) We have devised a novel selective memory module (SMM) that utilizes decoupled gating units to adaptively encode and store critical spatiotemporal features pertinent to the target from historical frame sequences, while furnishing abundant contextual priors and endows the model with the capacity to capture long-range temporal dependencies; 3) We have proposed a spatiotemporal loss function designed to constrain and guide the streaming model through state smoothing constraint, motion response constraint, and gating conflict penalty, thereby improving the localization performance of the model. Moreover, we introduce a comprehensively revised version of the VisDrone-VID dataset prompted by the identification of numerous instances of disorganized bounding box annotations and erroneous labels within the original compilation. Finally, extensive experiments demonstrate that the Dynamic Streaming Pipeline with Spatiotemporal Model (DSSM) outperforms all other state-of-the-art detection methods, achieving 14.4%, 77.6% and 58.4% mAP@0.5:0.95 on the VisDrone-VID, EMRS-Frame and EMRS-Event dataset. The updated VisDrone-VID dataset and our code are realeased at https://github.com/Jushl/DSSM.

With the rapid emergence of the low-altitude economy, the deployment scale of unmanned aerial vehicle (UAV) systems has also experienced substantial growth. This evolution toward airspace intelligence profoundly empowering traditional industrial paradigms, while introducing significant challenges to aerial security. Specifically, UAV object tracking still faces three major issues: 1) large variations in target scale, severe viewpoint changes, and background clutter hinder the clear capture of dynamic characteristics; 2) mainstream event representation methods lack spatiotemporal expressiveness, failing to reconstruct finer texture details; 3) prevailing object tracking frameworks suffer from redundant architectures and struggle to establish long-range dependencies between semantic information. In this paper, we construct the first event-based single object tracking dataset for UAVs (UAVEOT Dataset), providing a benchmark platform for tracking algorithms in challenging scenarios. Furthermore, we provide a novel event representation called Chaotic Sequence Encoder (CSE), which jointly employs temporal sequences, temporal entropy, and temporal weighting to convert asynchronous event streams into dense event tensors. Additionally, we propose a backbone named Hybrid State Space Attention (HSSA) network, incorporating three designed modules (e.g., Cross scale Fusion, Local Self Attention, and Global State Space), introducing state space duality into the tracking framework firstly, enabling efficient global spatiotemporal sequence modeling. Finally, extensive experiments demonstrate that the proposed tracker CSCMTrack achieves significant performance on the UAVEOT and VisEvent datasets, outperforming all other state-of-the-art tracking frameworks.