Gliding Vertex on the Horizontal Bounding Box for Multi-Oriented Object Detection

By Yongchao Xu, Mingtao Fu, Qimeng Wang, Yukang Wang, Kai Chen, Guisong Xia, Xiang Bai. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019

916 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/335d0cd846e8c91c0802ddb5c5f1f484420f50e9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Junwei Han
2. Junchi Yan
3. Gong Cheng
4. Xue Yang
5. Luc Van Gool
6. Qi Tian
7. Guisong Xia
8. Dacheng Tao

Citations in the corpus

• An Empirical Study of Remote Sensing Pretraining (2022, neutral): “2 Gliding Vertex [119] IMP-ResNet-101-FPN 88.”
• ReDet: A Rotation-equivariant Detector for Aerial Object Detection (2021, background): “Gliding vertex [36] and CenterMap [30] use quadrilateral and mask to accurately describe oriented objects, respectively.”
• Learning Modulated Loss for Rotated Object Detection (2019, background): “2018) or eight parameters (Xu et al. 2020; Liao et al. 2018; Zhou et al. 2017; Zhang et al. 2019; He et al. 2017) to describe rotated bounding boxes and use `1-loss as loss functions.”
• Anchor-Free Oriented Proposal Generator for Object Detection (2021, background): “Instead of predicting the angle of oriented boxes, gliding vertex [2] predicts four-point”
• Oriented R-CNN for Object Detection (2021, methodology): “Most existing state-of-the-art oriented object detection methods [7, 37, 41] depend on proposal-driven frameworks, like Fast/Faster R-CNN [11, 10, 32].”
• Large Selective Kernel Network for Remote Sensing Object Detection (2023, methodology): “In contrast with Oriented RCNN and Gliding Vertex, RSDet [54] addresses the discontinuity of regression loss by introducing a modulated loss.”
• Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges (2021, background): “Work in [63] further uses the gliding offset and obliquity factor to eliminate the ambiguity.”
• MMRotate: A Rotated Object Detection Benchmark using PyTorch (2022, background): “…2 , 𝜋 / 2 ) ) [3, 6], and long edge 135° ) ) [5]. https://github.com/dingjiansw101/AerialDetection 4 https://github.com/jbwang1997/OBBDetection Recent works used two-dimensional Gaussian distribution [37, 39] and point sets [22–24, 31 ] to represent objects , which have achieved excellent results.”
• Dense Label Encoding for Boundary Discontinuity Free Rotation Detection (2020, methodology): “Gliding Vertex [44] and RSDet [30] achieve more accurate object detection through quadrilateral regression prediction.”
• SCRDet++: Detecting Small, Cluttered and Rotated Objects via Instance-Level Feature Denoising and Rotation Loss Smoothing (2020, methodology): “Gliding Vertex [48] and RSDet [47] achieve more accurate object detection via quadrilateral regression prediction.”
• Oriented RepPoints for Aerial Object Detection (2021, methodology): “Methods RetinaNet-O [19] Faster RCNN-O [28] Gliding Vertex [36] mAP 57.”
• Arbitrary-Oriented Object Detection with Circular Smooth Label (2020, methodology): “Glid-ing Vertex [40] and RSDet [30] achieve more accurate object detection through quadrilateral regression prediction.”
• Drone-Based RGB-Infrared Cross-Modality Vehicle Detection Via Uncertainty-Aware Learning (2020, methodology): “637 2) Baselines: For the DroneVehicle dataset, 638 we compared our method with nine competing methods: 639 RetinaNet(OBB) [42], Faster R-CNN(OBB) [8], Faster 640 R-CNN(Dpool) [53], Mask R-CNN [45], Cascade Mask 641 R-CNN [46], Hybrid Task Cascade [47], RoITransformer [9], 642 ReDet [54], and Glidin”
• R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object (2019, background): “Remote sensing and scene text are the main application scenarios of the rotation detector.”
• Dynamic Anchor Learning for Arbitrary-Oriented Object Detection (2020, neutral): “amp;RC2(LB et al. 2017) VGG16 - - 75.70 RRPN(Ma et al. 2018) ResNet101 800 800 54 79.08 R2PN(Zhang et al. 2018) VGG16 - 24 79.60 RoI Trans. (Ding et al. 2019) ResNet101 512 800 5 86.20 Gliding Vertex(Xu et al. 2020) ResNet101 512 800 5 88.20 Single-stage: RRD(Liao et al. 2018) VGG16 384 384 13 84.30”
• Poly Kernel Inception Network for Remote Sensing Detection (2024, background): “Consequently, numerous prior efforts have been dedicated to developing various oriented bounding box (OBB) detectors [10, 20, 31, 65, 67, 71] and improving the angle prediction accuracy for OBBs [68, 70, 72–74].”