Natural Object Detection Research Articles

Алгоритм выделения точек земной поверхности из данных воздушного лазерного сканирования

The authors propose a new algorithm for classifying point clouds. It enables them to be separated according to the surface to which they belong. We present a brief analysis of existing methods for solving the problem considered, classifying them and indicating their advantages and disadvantages. The offered algorithm is based on iterative searching for points with a significant difference in height from the digital elevation model that approximates their cloud. In the course of processing, the formulated technique achieves a consistent adjustment of the approximating surface to the actual relief, which helps natural object detection on the ground. The results are demonstrated compared with the classification of point clouds by the CSF algorithm implemented in the widely used corresponding software. The juxtaposition of the obtained results shows that the proposed algorithm allows achieving a better classification quality in areas with irregular terrain, preserving also a greater number of points under the forested areas of the surface

Manhattan-distance IOU loss for fast and accurate bounding box regression and object detection

Bounding box regression is a crucial step in most object detection algorithms, and directly affects the positioning accuracy and regression speed of convolutional neural networks (CNN). The existing loss functions commonly used in bounding box regression suffer two main disadvantages: firstly, the ln-norm loss does not match the evaluation metric Intersection over Union (IOU), leading to poor regression performance. Second, some recently proposed IOU-based loss functions are beneficial to IOU metric, but the negative effects of some terms in these loss functions on bounding box regression lead to slow convergence and inaccurate regression results. To solve these shortcomings, we proposed a Manhattan-Distance IOU (MIOU) loss function here. It takes into account that the Euclidean distance term in the Complete IOU (CIOU) loss and the Efficient IOU (EIOU) loss is unstable in training due to the huge gradient in the early stage of regression, and the Manhattan distance is added to effectively alleviate this defect. In addition, the denominator of the Euclidean distance term in the two loss functions discussed above has an antagonistic effect on loss reduction, and setting it as a normalized coefficient without participating in backpropagation can effectively improve the convergence speed. The effectiveness of the proposed MIOU loss was verified with designed simulation experiments. Moreover, object detection is usually applied to natural scenes and remote sensing scenes, but the application of detection methods are often limited due to varied image characteristics in different scene settings. We incorporated the MIOU loss into YOLO v4 and other mainstream object detection networks to examine its effectiveness in remote sensing and natural object detection scenarios. The experimental results on real remote sensing datasets DOTA and natural datasets MS COCO demonstrate that the MIOU loss has strong robustness in both remote sensing object detection tasks and natural object detection tasks. In summary, as a general regression loss function, the MIOU loss shows excellent performance in the above two types of scenes.

A Low Coupling and Lightweight Algorithm for Ship Detection in Optical Remote Sensing Images

In recent years, many ship detection algorithms based on convolutional neural networks (CNNs) have been proposed to improve the performance of ship detection. However, with the increase in model complexity and size, it is challenging to deploy these models to resource-constrained edge platforms. In this letter, a low coupling algorithm that belongs to anchor-free methods is proposed for ship detection to reduce the model complexity and still obtain a competitive performance. The proposed low coupling network (LCNet) is easy to deploy and contributes to speeding up the inference and improving memory utilization. In addition, we propose a model compression process consisting of the quantization-aware training (QAT) method and a structural pruning method based on Taylor expansion, which can effectively reduce the model size according to hardware resource constraints. Comparative experimental results demonstrate that LCNet outperforms the state-of-the-art ship detection and natural object detection algorithms, with a 95.27% mAP and 88.91% F1 score on the HRSC2016 dataset. Our proposed model compression method also achieves a compression ratio of at least 80% with a negligible loss of performance.