Multi-Sector Oriented Object Detector for Accurate Localization in Optical Remote Sensing Images

Abstract

Oriented object detection in optical remote sensing images (ORSIs) is a challenging task since the targets in ORSIs are displayed in an arbitrarily oriented manner and on small scales, and are densely packed. Current state-of-the-art oriented object detection models used in ORSIs primarily evolved from anchor-based and direct regression-based detection paradigms. Nevertheless, they still encounter a design difficulty from handcrafted anchor definitions and learning complexities in direct localization regression. To tackle these issues, in this paper, we proposed a novel multi-sector oriented object detection framework called MSO2-Det, which quantizes the scales and orientation prediction of targets in ORSIs via an anchor-free classification-to-regression approach. Specifically, we first represented the arbitrarily oriented bounding box as four scale offsets and angles in four quadrant sectors of the corresponding Cartesian coordinate system. Then, we divided the scales and angle space into multiple discrete sectors and obtained more accurate localization information by a coarse-granularity classification to fine-grained regression strategy. In addition, to decrease the angular-sector classification loss and accelerate the network’s convergence, we designed a smooth angular-sector label (SASL) that smoothly distributes label values with a definite tolerance radius. Finally, we proposed a localization-aided detection score (LADS) to better represent the confidence of a detected box by combining the category-classification score and the sector-selection score. The proposed MSO2-Det achieves state-of-the-art results on three widely used benchmarks, including the DOTA, HRSC2016, and UCAS-AOD data sets.

OrientedDiffDet: Diffusion Model for Oriented Object Detection in Aerial Images

“…Remote-sensing image object detection often relies on prior anchors to represent oriented boxes [13][14][15]. Azimi et al (2018) [16] proposed the unconstrained detection algorithm ICN (Image Cascade Network), which utilizes adaptive weight sharing to combine the image pyramid with the feature pyramid, thereby enriching the semantic information.…”

Video Analysis in Sports by Lightweight Object Detection Network under the Background of Sports Industry Development

“…In fact, this is like semantic segmentation, except that there is four more bounding box offset information [ 16 ]. When FCOS is lightweight, the model effect is not as good as expected because the centerness branch of FCOS is difficult to converge on lightweight models [ 17 ]. Chen and Qin proposed the generalized focal loss function.…”