Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, 110016, China.
Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, 110169, China.
Sensors (Basel). 2019 Oct 28;19(21):4691. doi: 10.3390/s19214691.
In the field of aerial image object detection based on deep learning, it's difficult to extract features because the images are obtained from a top-down perspective. Therefore, there are numerous false detection boxes. The existing post-processing methods mainly remove overlapped detection boxes, but it's hard to eliminate false detection boxes. The proposed dual non-maximum suppression (dual-NMS) combines the density of detection boxes that are generated for each detected object with the corresponding classification confidence to autonomously remove the false detection boxes. With the dual-NMS as a post-processing method, the precision is greatly improved under the premise of keeping recall unchanged. In vehicle detection in aerial imagery (VEDAI) and dataset for object detection in aerial images (DOTA) datasets, the removal rate of false detection boxes is over 50%. Additionally, according to the characteristics of aerial images, the correlation calculation layer for feature channel separation and the dilated convolution guidance structure are proposed to enhance the feature extraction ability of the network, and these structures constitute the correlation network (CorrNet). Compared with you only look once (YOLOv3), the mean average precision (mAP) of the CorrNet for DOTA increased by 9.78%. Commingled with dual-NMS, the detection effect in aerial images is significantly improved.
在基于深度学习的航空图像目标检测领域，由于图像是从上向下获取的，因此很难提取特征，导致存在大量的误检框。现有的后处理方法主要是去除重叠的检测框，但很难消除误检框。所提出的双非极大值抑制（dual-NMS）方法结合了为每个检测对象生成的检测框的密度和相应的分类置信度，以自主去除误检框。在航空图像中的车辆检测（VEDAI）和航空图像目标检测数据集（DOTA）中，误检框的去除率超过 50%。此外，根据航空图像的特点，提出了特征通道分离的相关计算层和扩张卷积引导结构，增强了网络的特征提取能力，这些结构构成了相关网络（CorrNet）。与你只看一次（YOLOv3）相比，CorrNet 在 DOTA 上的平均精度（mAP）提高了 9.78%。与 dual-NMS 结合后，显著提高了航空图像的检测效果。
