Aug 2026· IEEE Robotics and Automation Letters· Vol 11, pp. 9883-9890· 0 citations· 43 references
Computer Science
Abstract
Event-based cameras offer promising potential for object tracking due to their high temporal resolution and low latency. However, the sparse and asynchronous nature of event streams makes it nontrivial to construct effective representations for event-only tracking. Existing methods predominantly rely on handcrafted event encodings, which are agnostic to downstream tracking objectives and often fail to fully exploit the temporal structure of events. In this work, we show that variations in tracking objectives fundamentally affect how event information should be represented, motivating the need for a task-adaptive event representation. We propose a novel Event Perturbation Field (EPF), a learnable and stackable event representation that enables end-to-end optimization of event features for object tracking. EPF models raw events as a learnable event vector field, capturing temporal perturbations in a flexible and objective-aware manner. To demonstrate the effectiveness of EPF for continuous event stream-based object tracking, we develop a transformer-based tracking framework that directly bridges raw event streams and target state prediction. Comprehensive experiments validate the advantages of EPF, and our tracker achieves state-of-the-art performance on multiple challenging event-based benchmarks.
This work investigates how temporal information can be encoded directly within the event representation, proposing a confidence-normalized continuous multi-timescale representation based on logarithmic B-spline temporal encoding together with a geometry-aware local confidence mechanism that exploits the spatial structu...
Fredrik Lundell, Per-Erik Forssén, Mårten Wadenbäck et al.· 1 citation
This work establishes a new performance benchmark for classical object discovery in event data, providing a highly scalable, training-free solution for resource-constrained visual perception.
P. G. Shenwai, H. Singh, Sridhar Ravi· 0 citations
This work proposes FLEET (Feature Learning from Events via Efficient Tokenization), a feature extractor that processes event sequences directly and decouples inference cost of the feature extractor's backbone from the sensor's resolution, enabling end-to-end learning without auxiliary losses.
T. Gottwald, Maximilian Schier, Melanie Schaller et al.· 0 citations
EventCV, an open-source and extensible Rust library with OpenCV-style Python bindings that lowers the entry barrier to working with event cameras, is presented and three robotics case studies spanning object detection, on-device model inference, and localization are presented.
Adam D. Hines, Michael Milford, Tobias Fischer· 0 citations
Experiments on three challenging benchmarks show that GTF improves identity association and overall tracking robustness, particularly under fast motion, appearance ambiguity, and frequent occlusions, and ablation studies further support the roles of encoder-level temporal fusion, adaptive gating, entropy regularization...
Event cameras are increasingly used for Multiple Object Tracking (MOT), but their asynchronous event output often requires specialized methods. Existing processing methods primarily follow two paradigms, pseudo-frames and event-by-event. The former is the prevailing approach since its data format aligns with images, ma...
Mu-Xi Zha, Bang-Lei Guan, Min-Zu Liang et al.· IEEE Transactions on Image P...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.