Deep learning methods have achieved the state-of-the-art performance of object detection and tracking in natural images, such as keypoint-based detectors and appearance/motion-based trackers. However, for small and bl...
详细信息
Deep learning methods have achieved the state-of-the-art performance of object detection and tracking in natural images, such as keypoint-based detectors and appearance/motion-based trackers. However, for small and blurry moving vehicles in satellite videos, keypoint-based detectors cause the missed detection of keypoints and incorrect keypoint matching. In terms of multi-object tracking, it is difficult to track the crowded similar vehicles stably only by using the appearance or motion information. To address these problems, a novel deep learning framework is proposed for moving vehicle detection and tracking in the satellite videos. It is comprised of the cross-frame keypoint-based detection network (CKDNet) and spatial motion information-guided tracking network (SMTNet). In CKDNet, a customized cross-frame module is designed to assist the detection of keypoints by exploiting complementary information between frames. Furthermore, CKDNet improves keypoint matching by incorporating size prediction around the keypoints and defining the soft mismatch suppression for out-of-size keypoint pairs. based on high-quality detection, SMTNet can track the densely-packed vehicles effectively by constructing two-branch long short-term memories. It extracts not only spatial information of the same frame by considering the relative spatial relationship of neighboring vehicles, but also motion information among consecutive frames by calculating the movement velocity. Especially, it regresses virtual positions for missed or occluded vehicles and keeps on tracking these vehicles while they reappear. Experimental results on Jilin-1 and SkySat satellite videos demonstrate the effectiveness of the proposed detection and tracking methods.
Traditional object detection methods, such as anchor-based YOLO variants, face challenges due to the irregular shapes and small sizes of these contaminants. This paper introduces a novel approach that leverages swarm ...
详细信息
Traditional object detection methods, such as anchor-based YOLO variants, face challenges due to the irregular shapes and small sizes of these contaminants. This paper introduces a novel approach that leverages swarm Intelligence to enhance the performance of a keypoint-driven YOLO framework. By integrating keypointdetection with Boundary-Aware Vectors (BBAVectors) and utilizing swarm intelligence algorithms for model optimization, our approach improves the localization and identification of small, irregularly shaped non-metallic objects. By optimizing the feature extraction process through swarm-based techniques and incorporating keypoint-driven object detection, our model significantly boosts precision and recall compared to traditional methods. Evaluated on a custom dataset of fiber like materials, our approach achieves a mean Average Precision (mAP) of 92.9% at IoU 0.5, demonstrating strong performance in real-world applications.
The detection of image forgeries is a crucial area of study within the discipline of digital image analysis, with the objective of identifying and accurately determining the location of modified regions inside images....
详细信息
Oriented object detection in remote sensing images (RSIs) is a significant yet challenging Earth Vision task, as the objects in RSIs usually emerge with complicated backgrounds, arbitrary orientations, multi-scale dis...
详细信息
Oriented object detection in remote sensing images (RSIs) is a significant yet challenging Earth Vision task, as the objects in RSIs usually emerge with complicated backgrounds, arbitrary orientations, multi-scale distributions, and dramatic aspect ratio variations. Existing oriented object detectors are mostly inherited from the anchor-based paradigm. However, the prominent performance of high-precision and real-time detection with anchor-based detectors is overshadowed by the design limitations of tediously rotated anchors. By using the simplicity and efficiency of keypoint-based detection, in this work, we extend a keypoint-based detector to the task of oriented object detection in RSIs. Specifically, we first simplify the oriented bounding box (OBB) as a center-based rotated inscribed ellipse (RIE), and then employ six parameters to represent the RIE inside each OBB: the center point position of the RIE, the offsets of the long half axis, the length of the short half axis, and an orientation label. In addition, to resolve the influence of complex backgrounds and large-scale variations, a high-resolution gated aggregation network (HRGANet) is designed to identify the targets of interest from complex backgrounds and fuse multi-scale features by using a gated aggregation model (GAM). Furthermore, by analyzing the influence of eccentricity on orientation error, eccentricity-wise orientation loss (ewoLoss) is proposed to assign the penalties on the orientation loss based on the eccentricity of the RIE, which effectively improves the accuracy of the detection of oriented objects with a large aspect ratio. Extensive experimental results on the DOTA and HRSC2016 datasets demonstrate the effectiveness of the proposed method.
暂无评论