Adrish Kar

Megan Birch, James Rick, Adrish Kar et al.

Event-based cameras (EBCs) are an attractive sensing modality for surveillance due to their reporting of pixel-level radiance changes with microsecond resolution and high dynamic range, enabling motion extraction while suppressing background. Their asynchronous, sparse output, however, necessitate algorithms that identify targets in event-space without processing full frames. We introduce Frequency Rate Information for Event Space (FRIES), a neuromorphic processing framework that detects periodicity in events, such as rotor rotation and mechanical vibrations, to discriminate and monitor man-made objects. FRIES first applies a time gate to suppress background and noise, then aggregates events into a pixel-wise activity (e.g., density) map and clusters pixels into regions-of-interest (ROIs). A localized spectral analysis is applied to each ROI to extract dominant frequencies used to distinguish structured object signatures from unstructured background and noise. Discriminated targets are visualized using a Resonant Time Surface (RTS), a frequency-selective method that weights events by their phase coherence with the extracted frequencies, rewarding in-sync content and suppressing out-of-sync clutter. We demonstrate FRIES and RTS in a controlled indoor experiment to recover the rotational frequency of a mechanical chopper and drone rotors against a moving background. We further test these methods on an outdoor data to detect a hovering drone against a realistic treeline. These preliminary results establish frequency-domain event processing as a promising front-end for selective surveillance in neuromorphic pipelines and a complementary surveillance modality, leveraging the high temporal resolution to enable spectral discrimination.

Joseph L. Greene, Adrish Kar, Ignacio Galindo et al.

Event, or neuromorphic cameras, offer a novel encoding of natural scenes by asynchronously reporting significant changes in brightness, known as events, with improved dynamic range, temporal resolution and lower data bandwidth when compared to conventional cameras. However, their adoption in domain-specific research tasks is hindered in part by limited commercial availability, lack of existing datasets, and challenges related to predicting the impact of their nonlinear optical encoding, unique noise model and tensor-based data processing requirements. To address these challenges, we introduce Synthetic Events for Neural Processing and Integration (SENPI) in Python, a PyTorch-based library for simulating and processing event camera data. SENPI includes a differentiable digital twin that converts intensity-based data into event representations, allowing for evaluation of event camera performance while handling the non-smooth and nonlinear nature of the forward model The library also supports modules for event-based I/O, manipulation, filtering and visualization, creating efficient and scalable workflows for both synthetic and real event-based data. We demonstrate SENPI's ability to produce realistic event-based data by comparing synthetic outputs to real event camera data and use these results to draw conclusions on the properties and utility of event-based perception. Additionally, we showcase SENPI's use in exploring event camera behavior under varying noise conditions and optimizing event contrast threshold for improved encoding under target conditions. Ultimately, SENPI aims to lower the barrier to entry for researchers by providing an accessible tool for event data generation and algorithmic developmnent, making it a valuable resource for advancing research in neuromorphic vision systems.