MS-IAF: Multi-Scale Information Augmentation Framework for Aircraft Detection

Abstract

Aircrafts have been an important object of study in the field of multi-scale image object detection due to their important strategic role. However, the multi-scale detection of aircrafts and their key parts from remote sensing images can be a challenge, as images often present complex backgrounds and obscured conditions. Most of today’s multi-scale datasets consist of independent objects and lack mixed annotations of aircrafts and their key parts. In this paper, we contribute a multi-scale aircraft dataset (AP-DATA) consisting of 7000 aircraft images that were taken in complex environments and obscured conditions. Our dataset includes mixed annotations of aircrafts and their key parts. We also present a multi-scale information augmentation framework (MS-IAF) to recognize multi-scale aircrafts and their key parts accurately. First, we propose a new deep convolutional module ResNeSt-D as the backbone, which stacks scattered attention in a multi-path manner and makes the receptive field more suitable for the object. Then, based on the combination of Faster R-CNN with ResNeSt-D, we propose a multi-scale feature fusion module called BFPCAR. BFPCAR overcomes the attention imbalance problem of the non-adjacent layers of the FPN module by reducing the loss of information between different layers and including more semantic features during information fusion. Based on AP-DATA, a dataset with three types of features, the average precision (AP) of MS-IAF reached 0.884, i.e., 2.67% higher than that of the original Faster R-CNN. The APs of these two modules were improved by 2.32% and 1.39%, respectively. The robustness of our proposed model was validated using the open sourced RSOD remote sensing image dataset, and the best accuracy was achieved.

Multi-Branch Parallel Networks for Object Detection in High-Resolution UAV Remote Sensing Images

“…This approach employs 3-D convolution to establish a scale equilibrium pyramid convolution, enhancing the correlation between different feature levels and allowing flexible matching with objects exhibiting varying appearance changes. Additionally, Zhao et al [23] proposed a multi-scale feature fusion module, named BFPCAR, which mitigates the imbalance of attention in non-adjacent layers of the FPN network. Dong et al [24] innovatively replaced the lateral connection of the FPN with a deformable convolution lateral connection module to facilitate multi-scale object detection.…”

Aircraft-LBDet: Multi-Task Aircraft Detection with Landmark and Bounding Box Detection

“…It introduces SAMs (sword attenuation masks) to capture the geometric appearance of aircraft, which enriches local appearance features and improves the accuracy of the bounding boxes. Zhao et al [33] introduced a module for fusing multi-scale features called BFPCAR, which incorporates semantic features that are prioritized during the fusion of information to reduce information loss between different layers and overcome the issue of imbalanced attention between non-adjacent layers. Liu et al [50] proposed an aircraft detection CNN with a corner cluster algorithm.…”

“…Finally, the fine-grained classification of aircraft categories [28] relies heavily on the structural information of aircraft. The existing approaches [29][30][31][32][33] do not fully leverage these features, despite some improvements in aircraft detection methods. For example, bounding box regression-based methods suffer from irrelevant background interference within the rectangular anchor boxes, while implicit feature extraction fails to make full use of the strong structural information of aircraft targets.…”

LRF-SRNet: Large-Scale Super-Resolution Network for Estimating Aircraft Pose on the Airport Surface

“…Since images often present complex backgrounds and hazy situations, many studies have looked at how to obtain larger fields of perception at shallower network depths. Zhao et al [ 25 ] suggested a multiscale information augmentation framework (MS-IAF), which accurately identifies multiscale aircraft and their vital parts by stacking perceptual fields of various scale sizes in a multipath way. Li et al [ 26 ] developed a new core component CBL module to increase the receptive field range in the neural network in order to address the issue of aircraft detection in airport field video images that is caused by a long shooting distance, small aircraft targets, and mutual occlusion.…”