Single-stage Rotate Object Detector via Two Points with Solar Corona Heatmap

Abstract

Oriented object detection is a crucial task in computer vision. Current top-down oriented detection methods usually directly detect entire objects, and not only neglecting the authentic direction of targets, but also do not fully utilise the key semantic information, which causes a decrease in detection accuracy. In this study, we developed a single-stage rotating object detector via two points with a solar corona heatmap (ROTP) to detect oriented objects. The ROTP predicts parts of the object and then aggregates them to form a whole image. Herein, we meticulously represent an object in a random direction using the vertex, centre point with width, and height. Specifically, we regress two heatmaps that characterise the relative location of each object, which enhances the accuracy of locating objects and avoids deviations caused by angle predictions. To rectify the central misjudgement of the Gaussian heatmap on high-aspect ratio targets, we designed a solar corona heatmap generation method to improve the perception difference between the central and non-central samples. Additionally, we predicted the vertex relative to the direction of the centre point to connect two key points that belong to the same goal. Experiments on the HRSC 2016, UCASAOD,

Knowledge Distillation for Oriented Object Detection on Aerial Images

“…1. In order to handle the object orientation on aerial images, a variety of angle-based and polygon boundary box encoding are developed [5], [6], [7], [8], [9], [10], [11], and strategy for extracting rotated region proposals are proposed for further boosting the detection precision [5]. However, these detectors are commonly overparameterized, and they can hardly be deployed on the devices with limited computation resources for onboard processing.…”