Yanran Dai

Object detection, as a fundamental task, forms the cornerstone of intelligent applications in both UAV surveillance and satellite remote sensing. While most prior works concentrate on solving object scale and rotation angle variance caused by altitude changes, the spatial misalignment stemming from the differing demands of classification subtask and regression subtask also plays a critical role. To tackle these problems, a novel deep-guided dual-task collaborative learning framework is proposed. This framework integrates two key modules: deep-guided collaborative feature fusion (DGC-FF) and dual-task collaborative feature alignment (DTC-FA). DGC-FF effectively integrates fine-grained spatial and semantic information to enhance the network’s multi-scale perception capability. DTC-FA alleviates spatial misalignment between classification and regression branches through collaborative feature alignment and incorporates a rotation-aware detection branch to adapt to varying object orientations. Experimental results show that the proposed method achieves mAP@0.5 of 79.3% on the DroneVehicle dataset and mAP@0.5 of 81.6% on the DIOR-R dataset. The proposed method not only outperforms all compared methods in accuracy but also strikes a favorable efficiency–accuracy balance with an inference rate of 55–58 FPS.

Achieving precise synchronization is critical for multi-camera systems in various applications. Traditional methods rely on hardware-triggered synchronization, necessitating significant manual effort to connect and adjust synchronization cables, especially with multiple cameras involved. This not only increases labor costs but also restricts scene layout and incurs high setup expenses. To address these challenges, we propose a novel subframe synchronization technique for multi-camera systems that operates without the need for additional hardware triggers. Our approach leverages a time-calibrated video featuring specific markers and a uniformly moving ball to accurately extract the temporal relationship between local and global time systems across cameras. This allows for the calculation of new timestamps and precise frame-level alignment. By employing interpolation algorithms, we further refine synchronization to the subframe level. Experimental results validate the robustness and high temporal precision of our method, demonstrating its adaptability and potential for use in demanding multi-camera setups.

Free-viewpoint video allows the user to view objects from any virtual perspective, creating an immersive visual experience. This technology enhances the interactivity and freedom of multimedia performances. However, many free-viewpoint video synthesis methods hardly satisfy the requirement to work in real time with high precision, particularly for sports fields having large areas and numerous moving objects. To address these issues, we propose a free-viewpoint video synthesis method based on distance field acceleration. The central idea is to fuse multi-view distance field information and use it to adjust the search step size adaptively. Adaptive step size search is used in two ways: for fast estimation of multi-object three-dimensional surfaces, and synthetic view rendering based on global occlusion judgement. We have implemented our ideas using parallel computing for interactive display, using CUDA and OpenGL frameworks, and have used real-world and simulated experimental datasets for evaluation. The results show that the proposed method can render free-viewpoint videos with multiple objects on large sports fields at 25 fps. Furthermore, the visual quality of our synthetic novel viewpoint images exceeds that of state-of-the-art neural-rendering-based methods.

Bullet-time videos have been widely used in movies, TV advertisements, and computer games, and can produce an immersive and smooth orbital free-viewpoint of frozen action. However, existing bullet-time video synthesis methods remain challenging in practical applications, especially in complex situations with poor camera calibration and a variety of camera array structures. This paper proposes a novel bullet-time video synthesis method based on a virtual dynamic target axis. We adopt an image similarity transformation strategy to eliminate image distortion in the bullet-time video. We use a high-order polynomial curve fitting strategy to reserve more bullet-time video frame content. The proposed dynamic target axis strategy can support various camera array structures, including camera arrays with and without a common field of view. In addition, this strategy can also tolerate poor camera calibration situations with unevenly distributed reprojection errors to some extent and synthesize smooth bullet-time videos without high-precision camera calibration. Qualitative and quantitative experiments in real environments and on simulation platforms demonstrate the high performance of our bullet-time video synthesis method. Compared with the state-of-the-art methods, the proposed method shows superiority.

In this paper, we investigate the problem of aligning multiple deployed camera into one united coordinate system for cross-camera information sharing and intercommunication. However, the difficulty is greatly increased when faced with large-scale scene under chaotic camera deployment. To address this problem, we propose a UAV-assisted wide area multi-camera space alignment approach based on spatiotemporal feature map. It employs the great global perception of Unmanned Aerial Vehicles (UAVs) to meet the challenge from wide-range environment. Concretely, we first present a novel spatiotemporal feature map construction approach to represent the input aerial and ground monitoring data. In this way, the motion consistency across view is well mined to overcome the great perspective gap between the UAV and ground cameras. To obtain the corresponding relationship between their pixels, we propose a cross-view spatiotemporal matching strategy. Through solving relative relationship with the above air-to-ground point correspondences, all ground cameras can be aligned into one surveillance space. The proposed approach was evaluated in both simulation and real environments qualitatively and quantitatively. Extensive experimental results demonstrate that our system can successfully align all ground cameras with very small pixel error. Additionally, the comparisons with other works on different test situations also verify its superior performance.

Moving target detection plays a primary and pivotal role in avionics visual analysis, which aims to completely and accurately detect moving objects from complex backgrounds. However, due to the relatively small sizes of targets in aerial video, many deep networks that achieve success in normal size object detection are usually accompanied by a high rate of false alarms and missed detections. To address this problem, we propose a novel visual detail augmented mapping approach for small aerial target detection. Concretely, we first present a multi-cue foreground segmentation algorithm including motion and grayscale information to extract potential regions. Then, based on the visual detail augmented mapping approach, the regions that might contain moving targets are magnified to multi-resolution to obtain detailed target information and rearranged into new foreground space for visual enhancement. Thus, original small targets are mapped to a more efficient foreground augmented map which is favorable for accurate detection. Finally, driven by the success of deep detection network, small moving targets can be well detected from aerial video. Experiments extensively demonstrate that the proposed method achieves success in small aerial target detection without changing the structure of the deep network. In addition, compared with the-state-of-art object detection algorithms, it performs favorably with high efficiency and robustness.