Skip to main content

Research Repository

Advanced Search

Local keypoint-based Faster R-CNN

Ding, Xintao; Li, Qingde; Cheng, Yongqiang; Wang, Jinbao; Bian, Weixin; Jie, Biao


Xintao Ding

Yongqiang Cheng

Jinbao Wang

Weixin Bian

Biao Jie


Region-based Convolutional Neural Network (R-CNN) detectors have achieved state-of-the-art results on various challenging benchmarks. Although R-CNN has achieved high detection performance, the research of local information in producing candidates is insufficient. In this paper, we design a Keypoint-based Faster R-CNN (K-Faster) method for object detection. K-Faster incorporates local keypoints in Faster R-CNN to improve the detection performance. In detail, a sparse descriptor, which first detects the points of interest in a given image and then samples a local patch and describes its invariant features, is first employed to produce keypoints. All 2-combinations of the produced keypoints are second selected to generate keypoint anchors, which are helpful for object detection. The heterogeneously distributed anchors are then encoded in feature maps based on their areas and center coordinates. Finally, the keypoint anchors are coupled with the anchors produced by Faster R-CNN, and the coupled anchors are used for Region Proposal Network (RPN) training. Comparison experiments are implemented on PASCAL VOC 07/12 and MS COCO. The experimental results show that our K-Faster approach not only increases the mean Average Precision (mAP) performance but also improves the positioning precision of the detected boxes.


Ding, X., Li, Q., Cheng, Y., Wang, J., Bian, W., & Jie, B. (in press). Local keypoint-based Faster R-CNN. Applied Intelligence,

Journal Article Type Article
Acceptance Date Feb 6, 2020
Online Publication Date Apr 28, 2020
Deposit Date Jul 20, 2020
Publicly Available Date Apr 29, 2021
Journal Applied Intelligence
Print ISSN 0924-669X
Electronic ISSN 1573-7497
Publisher Springer (part of Springer Nature)
Peer Reviewed Peer Reviewed
Keywords Keypoint; SIFT; Convolutional neural network; Faster R-CNN
Public URL
Publisher URL
Additional Information First Online: 28 April 2020


You might also like

Downloadable Citations