Gliding vertex on the horizontal bounding box for multi-oriented object detection

TL;DR

This paper introduces a novel method for multi-oriented object detection that glides vertices on horizontal bounding boxes to better capture object orientation, improving accuracy in aerial images and scene texts.

Contribution

It proposes a vertex gliding approach with an obliquity factor for more accurate multi-oriented object detection, integrated into Faster R-CNN with minimal additional computation.

Findings

Achieves superior performance on multiple benchmarks.

Effectively handles nearly horizontal objects.

Requires minimal extra computation.

Abstract

Object detection has recently experienced substantial progress. Yet, the widely adopted horizontal bounding box representation is not appropriate for ubiquitous oriented objects such as objects in aerial images and scene texts. In this paper, we propose a simple yet effective framework to detect multi-oriented objects. Instead of directly regressing the four vertices, we glide the vertex of the horizontal bounding box on each corresponding side to accurately describe a multi-oriented object. Specifically, We regress four length ratios characterizing the relative gliding offset on each corresponding side. This may facilitate the offset learning and avoid the confusion issue of sequential label points for oriented objects. To further remedy the confusion issue for nearly horizontal objects, we also introduce an obliquity factor based on area ratio between the object and its horizontal bounding box, guiding the selection of horizontal or oriented detection for each object. We add these five extra target variables to the regression head of faster R-CNN, which requires ignorable extra computation time. Extensive experimental results demonstrate that without bells and whistles, the proposed method achieves superior performances on multiple multi-oriented object detection benchmarks including object detection in aerial images, scene text detection, pedestrian detection in fisheye images.