Elliptic Fourier transformation-based histograms of oriented gradients for rotationally invariant object detection in remote-sensing images

High-resolution remote-sensing images are widely used for object detection but are affected by various factors. During the detection process, the orientation sensitivity of the image features is crucial to the detection performance. This study presents a novel rotationally invariant object detection descriptor that can address the difficulties with object detection that are caused by different object orientations. We use orientation normalization, feature space mapping, and an elliptic Fourier transform to achieve rotational invariance of the histogram of oriented gradients. Validation experiments indicate that the proposed descriptor is robust to rotation, noise, and compression. We use this novel image descriptor to detect aircraft and cars in remote-sensing images. The results show that the proposed method offers robust rotational invariance in object detection.