Towards Real-Time Edge Detection for Event Cameras Based on Lifetime and Dynamic Slicing

Mohamed, Sherif Abdelmonem Sayed; Haghbayan, Mohammad-Hashem; Heikkonen, Jukka; Tenhunen, Hannu; Plosila, Juha

doi:10.1007/978-3-030-44289-7_55

Cited by 9 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Frequency [10] 81.48 47.58 SAE [14,15] 82.81 LIF [18] 78.92 NSTS (proposed) 84.08 NSTS-SAE (proposed) 86.37…”

Section: Encoding Methods Ap (%) Detect Time (Ms)mentioning

confidence: 99%

“…Therefore, the results from NSTS-SAE were superior to others. [10]; (c) SAE (surface of active events) [15]; (d) LIF (leaky integrate-and-fire) [18]; (e) NSTS (neighborhood suppression time surface); (f) NSTS-SAE.…”

Section: Encoding Methods Ap (%) Detect Time (Ms)mentioning

confidence: 99%

“…Another common form of representation for event data is to create a structure named surface of active events (SAE) [14,15]. SAE was proposed to combine spatial and temporal information of events.…”

Section: Event-stream Encoding Based On Surface Of Active Eventsmentioning

confidence: 99%

See 2 more Smart Citations

Event-Based Pedestrian Detection Using Dynamic Vision Sensors

et al. 2021

View full text Add to dashboard Cite

Pedestrian detection has attracted great research attention in video surveillance, traffic statistics, and especially in autonomous driving. To date, almost all pedestrian detection solutions are derived from conventional framed-based image sensors with limited reaction speed and high data redundancy. Dynamic vision sensor (DVS), which is inspired by biological retinas, efficiently captures the visual information with sparse, asynchronous events rather than dense, synchronous frames. It can eliminate redundant data transmission and avoid motion blur or data leakage in high-speed imaging applications. However, it is usually impractical to directly apply the event streams to conventional object detection algorithms. For this issue, we first propose a novel event-to-frame conversion method by integrating the inherent characteristics of events more efficiently. Moreover, we design an improved feature extraction network that can reuse intermediate features to further reduce the computational effort. We evaluate the performance of our proposed method on a custom dataset containing multiple real-world pedestrian scenes. The results indicate that our proposed method raised its pedestrian detection accuracy by about 5.6–10.8%, and its detection speed is nearly 20% faster than previously reported methods. Furthermore, it can achieve a processing speed of about 26 FPS and an AP of 87.43% when implanted on a single CPU so that it fully meets the requirement of real-time detection.

show abstract

“…Frequency [10] 81.48 47.58 SAE [14,15] 82.81 LIF [18] 78.92 NSTS (proposed) 84.08 NSTS-SAE (proposed) 86.37…”

Section: Encoding Methods Ap (%) Detect Time (Ms)mentioning

confidence: 99%

Section: Encoding Methods Ap (%) Detect Time (Ms)mentioning

confidence: 99%

See 1 more Smart Citation

Event-Based Pedestrian Detection Using Dynamic Vision Sensors

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Visual sensors or cameras rely on capturing the images of the environment and objects to give useful information to be extracted. Visual cameras are typically monocular, stereo, and event-based cameras [49]- [51]. The benefits of using cameras are their small size, lesser weight, lower power consumption, flexibility, and they can be easily mounted.…”

Section: ) Cameramentioning

confidence: 99%

Unmanned Aerial Vehicles (UAVs): Collision Avoidance Systems and Approaches

et al. 2020

Self Cite

View full text Add to dashboard Cite

Moving towards autonomy, unmanned vehicles rely heavily on state-of-the-art collision avoidance systems (CAS). A lot of work is being done to make the CAS as safe and reliable as possible, necessitating a comparative study of the recent work in this important area. The paper provides a comprehensive review of collision avoidance strategies used for unmanned vehicles, with the main emphasis on unmanned aerial vehicles (UAV). It is an in-depth survey of different collision avoidance techniques that are categorically explained along with a comparative analysis of the considered approaches w.r.t. different scenarios and technical aspects. This also includes a discussion on the use of different types of sensors for collision avoidance in the context of UAVs. INDEX TERMS autonomous aerial vehicles, autonomous vehicles, collision avoidance, active and passive sensors, optimisation-based, force-field based, sense and avoid, geometry based

show abstract

“…In principle, a dynamic batching strategy [25] can alleviate the issues above. However, accurately estimating batching parameters is difficult; perhaps as difficult as performing VO itself since the optimal batching parameters depend on knowledge of the instantaneous camera motion.…”

Section: A Frame-based Optimisation With Batchingmentioning

confidence: 99%

Spatiotemporal Registration for Event-based Visual Odometry

Liu

Parra

Chin

2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Event cameras open up new possibilities for robotic perception due to their low latency and high dynamic range. On the other hand, developing effective event-based vision algorithms that fully exploit the beneficial properties of event cameras remains work in progress. In this paper, we focus on event-based visual odometry (VO). While existing event-driven VO pipelines have adopted continuous-time representations to asynchronously process event data, they either assume a known map, restrict the camera to planar trajectories, or integrate other sensors into the system. Towards map-free event-only monocular VO in SE(3), we propose an asynchronous structure-from-motion optimisation back-end. Our formulation is underpinned by a principled joint optimisation problem involving non-parametric Gaussian Process motion modelling and incremental maximum a posteriori inference. A high-performance incremental computation engine is employed to reason about the camera trajectory with every incoming event. We demonstrate the robustness of our asynchronous back-end in comparison to frame-based methods which depend on accurate temporal accumulation of measurements.

show abstract

Towards Real-Time Edge Detection for Event Cameras Based on Lifetime and Dynamic Slicing

Cited by 9 publications

References 18 publications

Event-Based Pedestrian Detection Using Dynamic Vision Sensors

Event-Based Pedestrian Detection Using Dynamic Vision Sensors

Unmanned Aerial Vehicles (UAVs): Collision Avoidance Systems and Approaches

Spatiotemporal Registration for Event-based Visual Odometry

Contact Info

Product

Resources

About