PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments

By Zhiming Chen, Kean Chen, Weiyao Lin, John See, Hui Yu, Yan Ke, Cong Yang. European Conference on Computer Vision, 2020

299 citations recorded by the source corpus.

Object detection using an oriented bounding box (OBB) can better target rotated objects by reducing the overlap with background areas. Existing OBB approaches are mostly built on horizontal bounding box detectors by introducing an additional angle dimension optimized by a distance loss. However, as the distance loss only minimizes the angle error of the OBB and that it loosely correlates to the IoU, it is insensitive to objects with high aspect ratios. Therefore, a novel loss, Pixels-IoU (PIoU) Loss, is formulated to exploit both the angle and IoU for accurate OBB regression. The PIoU loss is derived from IoU metric with a pixel-wise form, which is simple and suitable for both horizontal and oriented bounding box. To demonstrate its effectiveness, we evaluate the PIoU loss on both anchor-based and anchor-free frameworks. The experimental results show that PIoU loss can dramatically improve the performance of OBB detectors, particularly on objects with high aspect ratios and complex backgrounds. Besides, previous evaluation datasets did not include scenarios where the objects have high aspect ratios, hence a new dataset, Retail50K, is introduced to encourage the community to adapt OBB detectors for more complex environments.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/c32adbd5522696f87ce9fff113d7f56a5090a8c4

How researchers see this paper

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

In Aerospace Engineering

1. Junchi Yan
2. Wentao Wang
3. Xue Yang
4. Qi Ming
5. Qi Tian
6. Yue Zhou
7. Liping Hou
8. Xiaopeng Zhang

In Computer Vision and Pattern Recognition

1. Junchi Yan
2. Xue Yang
3. Wentao Wang
4. Qi Tian
5. Qi Ming
6. Xiaopeng Zhang
7. Wenwei Zhang
8. Yue Zhou

Citations in the corpus

• R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object (2019, methodology): “2020) and PIoU (Chen et al. 2020) Loss are the latest two rotation detectors used in retail scene detection, and two rotation retail datasets are proposed.”
• Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss (2021, background): “PIoU [5] is realized by simply counting the number of pixels.”
• Focal and Efficient IOU Loss for Accurate Bounding Box Regression (2021, unknown): “Pixels IOU [4] increases both the angle and IOU accuracy for oriented bounding boxes regression.”
• Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence (2021, methodology): “Si ng le -s ta ge PIoU [31] DLA-34 [55] 80.”
• MMRotate: A Rotated Object Detection Benchmark using PyTorch (2022, methodology): “In addition to the three applications mentioned above, rotated object detection is also widely used in 3D objects detection [44] and retail scenes detection [2, 23].”
• Dense Label Encoding for Boundary Discontinuity Free Rotation Detection (2020, background): “S in g le -s ta g e m et h o d s PIoU [4] DLA-34 [53] 80.”