Realtime CNN-based Keypoint Detector with Sobel Filter and CNN-based Descriptor Trained with Keypoint Candidates

by   Xun Yuan, et al.

The local feature detector and descriptor are essential in many computer vision tasks, such as SLAM and 3D reconstruction. In this paper, we introduce two separate CNNs, lightweight SobelNet and DesNet, to detect key points and to compute dense local descriptors. The detector and the descriptor work in parallel. Sobel filter provides the edge structure of the input images as the input of CNN. The locations of key points will be obtained after exerting the non-maximum suppression (NMS) process on the output map of the CNN. We design Gaussian loss for the training process of SobelNet to detect corner points as keypoints. At the same time, the input of DesNet is the original grayscale image, and circle loss is used to train DesNet. Besides, output maps of SobelNet are needed while training DesNet. We have evaluated our method on several benchmarks including HPatches benchmark, ETH benchmark, and FM-Bench. SobelNet achieves better or comparable performance with less computation compared with SOTA methods in recent years. The inference time of an image of 640x480 is 7.59ms and 1.09ms for SobelNet and DesNet respectively on RTX 2070 SUPER.


page 1

page 6


ELF: Embedded Localisation of Features in pre-trained CNN

This paper introduces a novel feature detector based only on information...

S-TREK: Sequential Translation and Rotation Equivariant Keypoints for local feature extraction

In this work we introduce S-TREK, a novel local feature extractor that c...

D2D: Keypoint Extraction with Describe to Detect Approach

In this paper, we present a novel approach that exploits the information...

On the Comparison of Classic and Deep Keypoint Detector and Descriptor Methods

The purpose of this study is to give a performance comparison between se...

DeDoDe: Detect, Don't Describe – Describe, Don't Detect for Local Feature Matching

Keypoint detection is a pivotal step in 3D reconstruction, whereby sets ...

FisheyeSuperPoint: Keypoint Detection and Description Network for Fisheye Images

Keypoint detection and description is a commonly used building block in ...

A Comparison of CNN and Classic Features for Image Retrieval

Feature detectors and descriptors have been successfully used for variou...

Please sign up or login with your details

Forgot password? Click here to reset