Dual-NMS: A Method for Autonomously Removing False Detection Boxes from Aerial Image Object Detection Results

Abstract

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.

Introspective False Negative Prediction for Black-Box Object Detectors in Autonomous Driving

“…According to Equation (11), the direct reason is FP predictions for FNs are added to the object detection results. This can be the result that, in the object-wise decoder, the filtering method of the center heatmap is not distinguishable enough, and the original NMS we use might impact the prediction precision [ 38 ], especially with dense targets [ 39 ]. Therefore, more effective post-processing methods should be considered in future work.…”

SuperDet: An Efficient Single-Shot Network for Vehicle Detection in Remote Sensing Images

“…In [31], a detection framework that appropriately handles the rotation equivariance inherent to any aerial image task is developed using the Faster R-CNN approach. In [32], the authors improved the non-maximum suppression (NMS) method and introduced the dual-NMS by combining the density of the generated bounding boxes, which can reduce the false detection rate effectively. In addition, a correlation network (CorrNet) was designed by the proposed correlation calculation layer and the dilated convolution guidance structure, which is helpful to improve the network's feature extraction capability.…”