JOINT MULTISCALE SPATIAL-FREQUENCY DOMAIN NETWORK FOR ORIENTED OBJECT DETECTION IN REMOTE SENSING IMAGES

The detection of oriented object detection in remote sensing images remains a daunting challenge due to their complex backgrounds, various sizes, and especially arbitrary orientations. However, most existing methods only model the structural features of images in the spatial domain, while the horizontal convolution kernels limit the model's ability to perceive object direction information. Furthermore, frequency features contain rich information about scale, texture and angle, which can be a good complement to the spatial features. Inspired by this, we propose a multiscale spatial-frequency domain network (MSFN) to utilize spatial-frequency information for oriented object detection, which can be integrated into any CNN architectures seamlessly and perform end-toend training easily. Besides, we design a channel alignment feature fusion module (CA-FFM) to address the problem of fusing low-level texture and high-level semantic features with a significant difference in channel dimension. Experimental results on HRSC2016 and SSDD dataset demonstrate the effectiveness of the proposed method.