Shi Yanli, Jia Yi, Zhang Xianhe
College of Information and Control Engineering, Jilin Institute of Chemical Technology, Jilin, 132000, China.
Sci Rep. 2024 May 10;14(1):10697. doi: 10.1038/s41598-024-61136-w.
The object scale of a small object scene changes greatly, and the object is easily disturbed by a complex background. Generic object detectors do not perform well on small object detection tasks. In this paper, we focus on small object detection based on FocusDet. FocusDet refers to the small object detector proposed in this paper. It consists of three parts: backbone, feature fusion structure, and detection head. STCF-EANet was used as the backbone for feature extraction, the Bottom Focus-PAN for feature fusion, and the detection head for object localization and recognition.To maintain sufficient global context information and extract multi-scale features, the STCF-EANet network backbone is used as the feature extraction network.PAN is a feature fusion module used in general object detectors. It is used to perform feature fusion on the extracted feature maps to supplement feature information.In the feature fusion network, FocusDet uses Bottom Focus-PAN to capture a wider range of locations and lower-level feature information of small objects.SIOU-SoftNMS is the proposed algorithm for removing redundant prediction boxes in the post-processing stage. SIOU multi-dimension accurately locates the prediction box, and SoftNMS uses the Gaussian algorithm to remove redundant prediction boxes. FocusDet uses SIOU-SoftNMS to address the missed detection problem common in dense tiny objects.The VisDrone2021-DET and CCTSDB2021 object detection datasets are used as benchmarks, and tests are carried out on VisDrone2021-det-test-dev and CCTSDB-val datasets. Experimental results show that FocusDet improves mAP@.5% from 33.6% to 46.7% on the VisDrone dataset. mAP@.5% on the CCTSDB2021 dataset is improved from 81.6% to 87.8%. It is shown that the model has good performance for small object detection, and the research is innovative.
小目标场景的目标尺度变化很大，且目标容易受到复杂背景的干扰。通用目标检测器在小目标检测任务上表现不佳。在本文中，我们专注于基于FocusDet的小目标检测。FocusDet指的是本文提出的小目标检测器。它由三部分组成：主干网络、特征融合结构和检测头。使用STCF-EANet作为特征提取的主干网络，使用Bottom Focus-PAN进行特征融合，使用检测头进行目标定位和识别。为了保持足够的全局上下文信息并提取多尺度特征，将STCF-EANet网络主干用作特征提取网络。PAN是通用目标检测器中使用的特征融合模块。它用于对提取的特征图进行特征融合，以补充特征信息。在特征融合网络中，FocusDet使用Bottom Focus-PAN来捕获小目标更广泛的位置和更低层次的特征信息。SIOU-SoftNMS是在后处理阶段用于去除冗余预测框的算法。SIOU多维精确地定位预测框，SoftNMS使用高斯算法去除冗余预测框。FocusDet使用SIOU-SoftNMS来解决密集微小目标中常见的漏检问题。将VisDrone2021-DET和CCTSDB2021目标检测数据集用作基准，并在VisDrone2021-det-test-dev和CCTSDB-val数据集上进行测试。实验结果表明，在VisDrone数据集上，FocusDet将mAP@.5%从33.6%提高到了46.7%。在CCTSDB2021数据集上，mAP@.5%从81.6%提高到了87.8%。结果表明该模型在小目标检测方面具有良好的性能，且该研究具有创新性。
