Elongated Small Object Detection from Remote Sensing Images Using Hierarchical Scale-Sensitive Networks

Abstract

The detection of elongated objects, such as ships, from satellite images has very important application prospects in marine transportation, shipping management, and many other scenarios. At present, the research of general object detection using neural networks has made significant progress. However, in the context of ship detection from remote sensing images, due to the elongated shape of ship structure and the wide variety of ship size, the detection accuracy is often unsatisfactory. In particular, the detection accuracy of small-scale ships is much lower than that of the large-scale ones. To this end, in this paper, we propose a hierarchical scale sensitive CenterNet (HSSCenterNet) for ship detection from remote sensing images. HSSCenterNet adopts a multi-task learning strategy. First, it presents a dual-direction vector to represent the posture or direction of the tilted bounding box, and employs a two-layer network to predict the dual direction vector, which improves the detection block of CenterNet, and cultivates the ability of detecting targets with tilted posture. Second, it divides the full-scale detection task into three parallel sub-tasks for large-scale, medium-scale, and small-scale ship detection, respectively, and obtains the final results with non-maximum suppression. Experimental results show that, HSSCenterNet achieves a significant improved performance in detecting small-scale ship targets while maintaining a high performance at medium and large scales.

Selecting Post-Processing Schemes for Accurate Detection of Small Objects in Low-Resolution Wide-Area Aerial Imagery

“…In addition, we need to improve the spatio-temporal processing scheme [14,20,81] by considering other hybrid approaches in the computer vision field, i.e., multi-scale structure information [6], multiple instance learning [100], and sparse representations [71,[101][102][103]. While employing any subset of methods from unsupervised, semi-supervised, and multi-task feature learning strategies [64,69,75,96,[104][105][106][107][108] on object detection, classification, and recognition, broader practical applications in the remote sensing domain may benefit from our research study.…”

Slender object detection algorithm based on improved YOLOv8 for intelligent driving scenarios

“…In recent years, there have been a few solutions that leverage the power of deep learning detection networks to tackle the challenge of detecting slender objects. HSSCenterNet [16] employs a dual-layer network to enhance vector detection efficiency, while DCNN [15] incorporates deep convolutional networks to preprocess target objects by performing tasks such as direction classification. However, these approaches still struggle to achieve the level of accuracy required for autonomous driving algorithms.…”

“…In practice, detection algorithms designed for small objects are often adapted for elongated objects, employing techniques like multiscale feature fusion, context information utilization [13], and data augmentation strategies [14]. Certainly, there are algorithms dedicated to the detection of slender objects that aim to improve upon R-CNN [15], CenterNet [16], and DETR [17]. However, the baselines of these algorithms often prioritize increasing network depth or blindly incorporating large-scale deformable convolution modules, leading to slow detection speeds and an inability to accurately distinguish between backgrounds and occlusions, which fails to meet the safety requirements of intelligent driving systems.…”

Absorption Pruning of Deep Neural Network for Object Detection in Remote Sensing Imagery

“…The papers [30][31][32] have further explored the application of YOLO series networks for object detection in remote sensing maps. In [33], the authors improved CenterNet to obtain a better small object detection capability in remote sensing imagery.…”