FA-Harris: A Fast and Asynchronous Corner Detector for Event Cameras

Li, Ruoxiang; Shi, Dianxi; Zhang, Yongjun; Li, Kaiyue; Li, Ruihao

doi:10.1109/iros40897.2019.8968491

Cited by 45 publications

(76 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Conversely, eFAST [ 24 ] has high computational efficiency, but the performance is not as effective as eHarris. FA-Harris [ 28 ] adopts a coarse-to-fine extraction strategy; in this algorithm, corner candidates are first selected by an improved eFAST detector and then refined by an improved eHarris detector. Although the accuracy has been effectively improved, this algorithm consumes a large amount of computation time and hardly runs in real-time due to the tedious eHarris-based method.…”

Section: Methodsmentioning

confidence: 99%

“…In order to improve the tracking accuracy, Alzugaray and Chli processed events individually as they generated and proposed an asynchronous patch-feature tracker [ 27 ], but because of the huge computing burden, this method runs about 30× slower than the tracker in [ 26 ], and it has poor real-time computing capability. Li et al proposed an event-based corner detection algorithm called FA-Harris [ 28 ]; in this algorithm, corner candidates are first selected by an improved eFAST and then refined by an improved eHarris detector. Although the accuracy has been effectively improved, this algorithm consumes a large amount of computation time and hardly runs in real-time due to the tedious eHarris-based method.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Asynchronous Real-Time Corner Extraction and Tracking Algorithm for Event Camera

Duo

Zhao

2021

Sensors

View full text Add to dashboard Cite

Event cameras have many advantages over conventional frame-based cameras, such as high temporal resolution, low latency and high dynamic range. However, state-of-the-art event- based algorithms either require too much computation time or have poor accuracy performance. In this paper, we propose an asynchronous real-time corner extraction and tracking algorithm for an event camera. Our primary motivation focuses on enhancing the accuracy of corner detection and tracking while ensuring computational efficiency. Firstly, according to the polarities of the events, a simple yet effective filter is applied to construct two restrictive Surface of Active Events (SAEs), named as RSAE+ and RSAE−, which can accurately represent high contrast patterns; meanwhile it filters noises and redundant events. Afterwards, a new coarse-to-fine corner extractor is proposed to extract corner events efficiently and accurately. Finally, a space, time and velocity direction constrained data association method is presented to realize corner event tracking, and we associate a new arriving corner event with the latest active corner that satisfies the velocity direction constraint in its neighborhood. The experiments are run on a standard event camera dataset, and the experimental results indicate that our method achieves excellent corner detection and tracking performance. Moreover, the proposed method can process more than 4.5 million events per second, showing promising potential in real-time computer vision applications.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

An Asynchronous Real-Time Corner Extraction and Tracking Algorithm for Event Camera

Duo

Zhao

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Asynchronous event-based clustering and tracking for intrusion monitoring in UAS. In IEEE International Conference on Robotics and Automation (ICRA 2020) false positive rate, and computational efficiency [9]. Then, the corners detected are separated by polarity and tracked to remove inconsistent and noisy corners.…”

Section: The Proposed Methodsmentioning

confidence: 99%

“…Asynchronous event-by-event processing usually has higher computational needs and is mainly adopted for low-level processing techniques, e.g. feature detection [9] or tracking [10]. Some schemes combine asynchronous methods for lowlevel processing with others based on event images for highlevel processing [11], but they do not always fully exploit either the advantages of event cameras.…”

Section: Introductionmentioning

confidence: 99%

Asynchronous event-based clustering and tracking for intrusion monitoring in UAS

Eguíluz

Dios

Ollero

2020

2020 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

Automatic surveillance and monitoring using Unmanned Aerial Systems (UAS) require the development of perception systems that robustly work under different illumination conditions. Event cameras are neuromorphic sensors that capture the illumination changes in the scene with very low latency and high dynamic range. Although recent advances in eventbased vision have explored the use of event cameras onboard UAS, most techniques group events in frames and, therefore, do not fully exploit the sequential and asynchronous nature of the event stream. This paper proposes a fully asynchronous scheme for intruder monitoring using UAS. It employs efficient event clustering and feature tracking modules and includes a sampling mechanism to cope with the computational cost of event-by-event processing adapting to on-board hardware computational constraints. The proposed scheme was tested on a real multirotor in challenging scenarios showing significant accuracy and robustness to lighting conditions.

show abstract

“…Mueggler et al [17] presented an event-based FAST corner detector for event streams and improved the event-based Harris corner detector [18]. Later, [19] presented an speed-up version of [18]. Alzugaray and Chli [20] introduced a filter for event streams to remove redundant events before detecting, and the filter can enhance both accuracy and real-time performance.…”

Section: A Event-based Feature Detectionmentioning

confidence: 99%

Feature Tracking Based on Line Segments With the Dynamic and Active-Pixel Vision Sensor (DAVIS)

Shi²,

Zhang³

et al. 2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

As a novel vision sensor, the dynamic and active-pixel vision sensor (DAVIS) combines a standard camera and an asynchronous event-based sensor in the same pixel array. In this paper, we propose a novel asynchronous feature tracking method based on line segments with the DAVIS. The proposed method takes asynchronous events, synchronous image frames, and IMU data as the input. We first use the Harris detector to extract feature points and the Canny detector to extract line segment templates from image frames. Then we select spatio-temporal windows from asynchronous events and perform registration to estimate the optical flow. The registration is achieved by associating the extracted line segments with the events inside the window. Expectation maximization-iterative closest point (EM-ICP) is adopted for the registration. Afterward, we use the estimated optical flow and the IMU data to update the position of line segments, and take them as the new templates. We evaluate our method on the public event camera datasets. The results show that our method can achieve comparable performance to other methods in terms of accuracy and tracking time. INDEX TERMS Feature tracking, event camera, EM-ICP, line segments, DAVIS.

show abstract

FA-Harris: A Fast and Asynchronous Corner Detector for Event Cameras

Cited by 45 publications

References 27 publications

An Asynchronous Real-Time Corner Extraction and Tracking Algorithm for Event Camera

An Asynchronous Real-Time Corner Extraction and Tracking Algorithm for Event Camera

Asynchronous event-based clustering and tracking for intrusion monitoring in UAS

Feature Tracking Based on Line Segments With the Dynamic and Active-Pixel Vision Sensor (DAVIS)

Contact Info

Product

Resources

About