KCNN: Extremely-Efficient Hardware Keypoint Detection with a Compact Convolutional Neural Network

Febbo, Paolo Di; Mutto, Carlo Dal; Tieu, Kinh; Mattoccia, Stefano

doi:10.1109/cvprw.2018.00111

Cited by 18 publications

(12 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first approach for keypoint detection to rely on machine learning was FAST [41]. Later, Di et al [10] learn to mimic the output of handcrafted detectors with a compact neural network. In [22], handcrafted and learned filters are combined to detect repeatable keypoints.…”

Section: Related Workmentioning

confidence: 99%

R2D2: Repeatable and Reliable Detector and Descriptor

Revaud,

Weinzaepfel,

De Souza

et al. 2019

Preprint

107

View full text Add to dashboard Cite

Interest point detection and local feature description are fundamental steps in many computer vision applications. Classical methods for these tasks are based on a detect-thendescribe paradigm where separate handcrafted methods are used to first identify repeatable keypoints and then represent them with a local descriptor. Neural networks trained with metric learning losses have recently caught up with these techniques, focusing on learning repeatable saliency maps for keypoint detection and learning descriptors at the detected keypoint locations. In this work, we argue that salient regions are not necessarily discriminative, and therefore can harm the performance of the description. Furthermore, we claim that descriptors should be learned only in regions for which matching can be performed with high confidence. We thus propose to jointly learn keypoint detection and description together with a predictor of the local descriptor discriminativeness. This allows us to avoid ambiguous areas and leads to reliable keypoint detections and descriptions. Our detection-and-description approach, trained with selfsupervision, can simultaneously output sparse, repeatable and reliable keypoints that outperforms state-of-the-art detectors and descriptors on the HPatches dataset. It also establishes a record on the recently released Aachen Day-Night localization benchmark.

show abstract

Section: Related Workmentioning

confidence: 99%

R2D2: Repeatable and Reliable Detector and Descriptor

Revaud,

Weinzaepfel,

De Souza

et al. 2019

Preprint

107

View full text Add to dashboard Cite

show abstract

“…The motivation for using learning in FAST was to speed up the detection by early rejection of non-corner points. Other authors [57,19] also showed how to learn a fast approximation of existing detectors. But other authors follow this direction by training efficient ensembles of decision trees.…”

Section: Event-based Features Detectionmentioning

confidence: 99%

Speed Invariant Time Surface for Learning to Detect Corner Points With Event-Based Cameras

Manderscheid

Sironi

Bourdis

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

We propose a learning approach to corner detection for event-based cameras that is stable even under fast and abrupt motions. Event-based cameras offer high temporal resolution, power efficiency, and high dynamic range. However, the properties of event-based data are very different compared to standard intensity images, and simple extensions of corner detection methods designed for these images do not perform well on event-based data. We first introduce an efficient way to compute a time surface that is invariant to the speed of the objects. We then show that we can train a Random Forest to recognize events generated by a moving corner from our time surface. Random Forests are also extremely efficient, and therefore a good choice to deal with the high capture frequency of event-based cameras-our implementation processes up to 1.6Mev/s on a single CPU. Thanks to our time surface formulation and this learning approach, our method is significantly more robust to abrupt changes of direction of the corners compared to previous ones. Our method also naturally assigns a confidence score for the corners, which can be useful for postprocessing. Moreover, we introduce a highresolution dataset suitable for quantitative evaluation and comparison of corner detection methods for event-based cameras. We call our approach SILC, for Speed Invariant Learned Corners, and compare it to the state-of-the-art with extensive experiments, showing better performance.

show abstract

“…DNN-based individual detector/descriptor methods. There are also a number of methods that only focus on DNN-based detector or descriptor, e.g., [36,30,8,13] proposed DNN-based keypoints detectors, and [31,22,34,21,20,33] worked on descriptor computation. However, we usually employ one local feature algorithm as a whole since either detector or descriptor would influence the performance of each other.…”

Section: Related Workmentioning

confidence: 99%

SEKD: Self-Evolving Keypoint Detection and Description

Song,

Cai,

et al. 2020

Preprint

View full text Add to dashboard Cite

Researchers have attempted utilizing deep neural network (DNN) to learn novel local features from images inspired by its recent successes on a variety of vision tasks. However, existing DNN-based algorithms have not achieved such remarkable progress that could be partly attributed to insufficient utilization of the interactive characters between local feature detector and descriptor. To alleviate these difficulties, we emphasize two desired properties, i.e., repeatability and reliability, to simultaneously summarize the inherent and interactive characters of local feature detector and descriptor. Guided by these properties, a self-supervised framework, namely self-evolving keypoint detection and description (SEKD), is proposed to learn an advanced local feature model from unlabeled natural images. Additionally, to have performance guarantees, novel training strategies have also been dedicatedly designed to minimize the gap between the learned feature and its properties. We benchmark the proposed method on homography estimation, relative pose estimation, and structurefrom-motion tasks. Extensive experimental results demonstrate that the proposed method outperforms popular handcrafted and DNN-based methods by remarkable margins. Ablation studies also verify the effectiveness of each critical training strategy. We will release our code along with the trained model publicly.

show abstract

KCNN: Extremely-Efficient Hardware Keypoint Detection with a Compact Convolutional Neural Network

Cited by 18 publications

References 25 publications

R2D2: Repeatable and Reliable Detector and Descriptor

R2D2: Repeatable and Reliable Detector and Descriptor

Speed Invariant Time Surface for Learning to Detect Corner Points With Event-Based Cameras

SEKD: Self-Evolving Keypoint Detection and Description

Contact Info

Product

Resources

About