School of Information Engineering, Jiangxi University of Science and Technology, Jiangxi, China.
Comput Intell Neurosci. 2022 Jun 1;2022:6394823. doi: 10.1155/2022/6394823. eCollection 2022.
Due to the small size and weak characteristics of small objects, the performance of existing object detection algorithms for small objects is not ideal. In this paper, we propose a small object detection network based on feature information enhancement to improve the detection effect of small objects. In our method, two key modules, information enhancement module and dense atrous convolution module, are proposed to enhance the expression and discrimination ability of feature information. The detection accuracy of this method on PASCAL VOC, MS COCO, and UCAS-AOD data sets is 81.3%, 34.8%, and 87.0%, respectively. In addition, the detection results of this paper in detecting small objects are slightly (0.2% and 0.1%) higher than the current advanced algorithms (YOLOv4 and DETR, respectively). Moreover, when these two modules are integrated into other algorithms, such as RFBNet, it can also bring considerable improvement.
由于小物体的体积小、特征弱，现有的小物体目标检测算法的性能并不理想。在本文中，我们提出了一种基于特征信息增强的小物体检测网络，以提高小物体的检测效果。在我们的方法中，提出了两个关键模块，信息增强模块和密集空洞卷积模块，以增强特征信息的表达和区分能力。该方法在 PASCAL VOC、MS COCO 和 UCAS-AOD 数据集上的检测精度分别为 81.3%、34.8%和 87.0%。此外，本文在检测小物体时的检测结果比当前先进算法（YOLOv4 和 DETR）分别高出（0.2%和 0.1%）。而且，当将这两个模块集成到其他算法中，如 RFBNet 时，也能带来相当大的改进。
