• 人工智能与模式识别 •

### 一种基于边界框关键点距离的框回归算法

1. 1. 国能网信科技（北京）有限公司 综合自动化部，北京 100011
2. 武汉大学 测绘遥感信息工程国家重点实验室，武汉 430079
• 收稿日期:2022-07-22 出版日期:2023-07-15 发布日期:2023-07-14
• 通讯作者: 阴宇薇
• 作者简介:

聂志勇（1982—），男，工程师，主研方向为自动化控制、电气设计、人工智能研发管理

汤佳欣，硕士

涂志刚，研究员、博士、博士生导师

• 基金资助:
国家自然科学基金(62106177)

### A Box Regression Algorithm Based on Key Point Distance of Bounding Box

Zhiyong NIE1, Yuwei YIN2,*, Jiaxin TANG2, Zhigang TU2

1. 1. General Automation Department, CHN Energy Network Information Technology(Beijing) Co., Ltd., Beijing 100011, China
2. State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China
• Received:2022-07-22 Online:2023-07-15 Published:2023-07-14
• Contact: Yuwei YIN

Abstract:

To address the challenges of low detection accuracy and slow convergence rate associated with the current box regression method utilizing Intersection-over-Union(IoU) in practical applications, a new box regression method based on Key point distance based Intersection-over-Union(KIoU) is proposed. The proposed method incorporates geometric knowledge by considering the three vertices and the center point of the rectangle as key points. These key points enable the determination of the position and morphological differences between the predicted box and the actual box by calculating the distance between corresponding points. A new loss function based on the IoU loss of key points is constructed to measure the difference between the IoU of the key points of the prediction box and the actual box in both real-world and ideal scenarios.The distance between the corresponding key points is used as the penalty term for IoU, thereby accelerating the convergence process of the model.The efficiency and accuracy of key point information in object positioning are leveraged to improve the target detection accuracy. Experimental comparisons were conducted on the PASCAL VOC and COCO datasets using the Single Shot multibox Detector(SSD), which is a single-stage object detection algorithm, and the Faster Region-Convolutional Neural Network(Faster R-CNN), which is a two-stage object detection algorithm, as benchmark algorithms. KIoU was compared against IoU, Generalized IoU(GIoU), Distance IoU (DIoU), and Complete IoU(CIoU).The results demonstrated notable improvements in detection accuracy.Specifically, compared to IoU, KIoU on Faster R-CNN exhibited a 2.91% increase, surpassing DIoU by 0.11% in current performance, and outperformed IoU and DIoU on SSD by 0.96% and 0.06%, respectively.Additionally, in terms of visual effects in object detection, the KIoU method exhibited more accurate target localization and demonstrated the ability to mitigate the occurrence of missed targets to some extent.