Detecting Stable Keypoints from Events through Image Gradient Prediction

Chiberre, Philippe; Pérot, Etienne; Sironi, Amos; Lepetit, Vincent

doi:10.1109/cvprw53098.2021.00153

Cited by 10 publications

(4 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In image processing, image gradient is one of the most widely used features [ 77 , 78 , 79 , 80 ] and a strong predictive factor for image quality [ 61 , 81 ]. To characterize gradient degradation in the presence of image noise, the idea of gradient magnitude (GM), relative gradient orientation (RO), and relative gradient magnitude (RM) maps were applied from [ 61 ], on the one hand.…”

Section: Materials and Methodsmentioning

confidence: 99%

No-Reference Quality Assessment of Authentically Distorted Images Based on Local and Global Features

Varga

2022

J. Imaging

View full text Add to dashboard Cite

With the development of digital imaging techniques, image quality assessment methods are receiving more attention in the literature. Since distortion-free versions of camera images in many practical, everyday applications are not available, the need for effective no-reference image quality assessment algorithms is growing. Therefore, this paper introduces a novel no-reference image quality assessment algorithm for the objective evaluation of authentically distorted images. Specifically, we apply a broad spectrum of local and global feature vectors to characterize the variety of authentic distortions. Among the employed local features, the statistics of popular local feature descriptors, such as SURF, FAST, BRISK, or KAZE, are proposed for NR-IQA; other features are also introduced to boost the performances of local features. The proposed method was compared to 12 other state-of-the-art algorithms on popular and accepted benchmark datasets containing RGB images with authentic distortions (CLIVE, KonIQ-10k, and SPAQ). The introduced algorithm significantly outperforms the state-of-the-art in terms of correlation with human perceptual quality ratings.

show abstract

Section: Materials and Methodsmentioning

confidence: 99%

No-Reference Quality Assessment of Authentically Distorted Images Based on Local and Global Features

Varga

2022

J. Imaging

View full text Add to dashboard Cite

show abstract

“…Several works have devised the use of image-like eventframes or other time-invariant representations [13] on which traditional frame-based techniques to feature detection and tracking can be easily adapted. For instance, the method from [14] infers intensity gradient images from batches of events whereas the algorithm in [15] generates imagelike edge-maps that are updated at each new event and on which traditional Harris corners [16] are detected. Similarly, the event-based VO systems described in [17,18] use an Inertial Measurement Unit (IMU)-aided motioncompensation scheme to also generate event-frames where traditional frame-based FAST corners [19] are detected and tracked using KLT [20].…”

Section: Related Workmentioning

confidence: 99%

Continuous-Time Gaussian Process Motion-Compensation for Event-vision Pattern Tracking with Distance Fields

Gentil¹,

Alzugaray²,

Vidal-Calleja³

2023

Preprint

View full text Add to dashboard Cite

This work addresses the issue of motion compensation and pattern tracking in event camera data. An event camera generates asynchronous streams of events triggered independently by each of the pixels upon changes in the observed intensity. Providing great advantages in low-light and rapid-motion scenarios, such unconventional data present significant research challenges as traditional vision algorithms are not directly applicable to this sensing modality. The proposed method decomposes the tracking problem into a local SE(2) motion-compensation step followed by a homography registration of small motion-compensated event batches. The first component relies on Gaussian Process (GP) theory to model the continuous occupancy field of the events in the image plane and embed the camera trajectory in the covariance kernel function. In doing so, estimating the trajectory is done similarly to GP hyperparameter learning by maximising the log marginal likelihood of the data. The continuous occupancy fields are turned into distance fields and used as templates for homography-based registration. By benchmarking the proposed method against other state-of-the-art techniques, we show that our open-source implementation performs high-accuracy motion compensation and produces high-quality tracks in realworld scenarios.

show abstract

“…Since in event cameras pixels are operating independent from each other, in this research average gradient magnitude becomes of great importance compared to the gradient direction which requires a separate study for event output. We must first determine the gradient in the x and y axes [13] then calculate the magnitude based on them and the end find the average amount of this gradient for all the pixels. Formula 1 is used to find the average amount of the image gradient magnitude or shortly the average gradient (AG):…”

Section: Image Gradientmentioning

confidence: 99%

Control and evaluation of event cameras output sharpness via bias

Dilmaghani

Shariff

Ryan

et al. 2023

Fifteenth International Conference on Machine Vision (ICMV 2022)

View full text Add to dashboard Cite

Event cameras also known as neuromorphic sensors are relatively a new technology with some privilege over the RGB cameras. The most important one is their difference in capturing the light changes in the environment, each pixel changes independently from the others when it captures a change in the environment light. To increase the user's degree of freedom in controlling the output of these cameras, such as changing the sensitivity of the sensor to light changes, controlling the number of generated events and other similar operations, the camera manufacturers usually introduce some tools to make sensor level changes in camera settings. The contribution of this research is to examine and document the effects of changing the sensor settings on the sharpness as an indicator of quality of the generated stream of event data. To have a qualitative understanding this stream of event is converted to frames, then the average image gradient magnitude as an index of the number of edges and accordingly sharpness is calculated for these frames. Five different bias settings are explained and the effect of their change in the event output is surveyed and analyzed. In addition, the operation of the event camera sensing array is explained with an analogue circuit model and the functions of the bias foundations are linked with this model.

show abstract

Detecting Stable Keypoints from Events through Image Gradient Prediction

Cited by 10 publications

References 37 publications

No-Reference Quality Assessment of Authentically Distorted Images Based on Local and Global Features

No-Reference Quality Assessment of Authentically Distorted Images Based on Local and Global Features

Continuous-Time Gaussian Process Motion-Compensation for Event-vision Pattern Tracking with Distance Fields

Control and evaluation of event cameras output sharpness via bias

Contact Info

Product

Resources

About