Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 28 for “"Event-based vision"”.
-
PATTERN RECOGNITION APPROACHES FOR EVENT-BASED VISION
… thesis is a compilation of approaches aimed at event-based pattern recognition applications,such as object recognition, feature tracking and gesture recognition. For object recognition, I document two different ways of realizing a classifier (CNN and slow-ELM) for event-based data streams. Focus …
-
Event-based Vision for High-Speed Robotics
… heavy, and require additional power, which prevents their use in agile mobile robots. In this thesis, we investigate event cameras as a biologically-inspired alternative to overcome the limitations of standard cameras. These neuromorphic vision sensors work in a completely different way: …
-
Event-Based Vision Processing in Deep Neural Networks
… supplied highly accurate algorithms for computer vision. Unfortunately, these algorithms are not directly compatible with neuromorphic hardware. The present work bridges this gap by developing algorithms that leverage the power of Deep Learning while being suited for operation on neuro-inspired …
-
BEYOND FRAMES: LEARNING TO PERCEIVE WITH EVENT-BASED VISION
Conventional frame-based vision systems face inherent limitations in high-speed, high-dynamic-range settings, where motion blur, latency, and temporal aliasing degrade performance. Event cameras—neuromorphic sensors that asynchronously report per-pixel brightness changes—offer a fundamentally …
-
Behavioral measurement of zebrafish larvae using event-based vision
… central nervous system and often relies on frame-based cameras and large populations of subjects. These methods compress the subjects' behavior into frames, massively reducing granularity. In contrast, in the current work, event-based vision is used to record behavior of two genotypes of zebrafish …
-
EVENT-BASED VISION SYSTEMS: BRIDGING BIOLOGICAL INSPIRATION AND ROBOTIC PERCEPTION
… exploring the relationship between biological vision systems and artificial event-based cameras, this research delves into fundamental aspects of motion perception and structural understanding within dynamic environments. The study draws inspiration from the diverse and highly parallel visual …
-
ENABLING TIGHT PERCEPTION-ACTION LOOPS FOR AUTONOMOUS ROBOTS WITH EVENT-BASED VISION
… in simulation. We first examine the use of a vision transformer in an end-to-end method for perception-to-control of a quadrotor obstacle avoidance task. Trained only in simulation, this model generalizes zero-shot to real-world flight, where we see improved generalization and context-aware …
-
An Event-Based Vision Sensor Simulation Framework for Space Domain Awareness Applications
Event-based vision sensors (EVS) provide a unique opportunity for Space Domain Awareness (SDA) applications. Inspired by the human eye, these sensors operate on the principle of change detection and each pixel functions independently and asynchronously from the other pixels. Pixels trigger events …
-
Event-based vision for human-robot handover: Deep learning on tensor representations for robotic control
… close range environments. Traditional frame based vision systems are often limited by latency, motion blur, and redundant data particularly during high speed interactions. To address these limitations, this thesis investigates the use of event based cameras, which asynchronously capture pixel …
-
Event-based Perception for Aerial Robots: From Multirotors to Ornithopters
… community by exploring the advantages of event cameras for aerial robotics, in particular on flapping-wing robots in which event-based vision is almost unexplored. It proposes a set of tools and perception algorithms to leverage the advantages of event-based vision in aerial robot …
-
Neuromorphic Computing and Vision for Interactive Robotics
Neuromorphic computing and event-based vision seek to replicate the brain’s sparse, spike-driven information flow, offering a route to robots that see and react with the speed and parsimony of their biological counterparts. This thesis pursues that goal through a single narrative arc that begins …
-
Event-Based Perception for Flapping-Wing Robots
… by investigating the advantages of integrating event-based vision into flapping-wing aerial robots, two emerging bioinspired technologies with the potential to transform the future of autonomous aerial systems. Event cameras offer relevant advantages (e.g., microsecond temporal resolution, low …
-
Neuromorphic vision Sensors with Foveation for efficient Processing
… efficiency and adaptability of high-resolution event-based vision sensors for real-time applications. While dynamic vision sensors (DVS) offer significant advantages over frame-based vision sensors, increasing spatial resolution leads to a substantial rise in event throughput, resulting in …
-
Computing with Spikes: Legendre-based SNNs and Deep Local Learning toward Neuromorphic Intelligence
… directions: the algorithmic design of reservoir-based SNNs, their deployment on Intel's Loihi-2 neuromorphic chip, a biologically-inspired local-learning method to train deep SNNs, and real-world neuromorphic applications spanning wireless domain and event-based vision. We begin by proposing a …
-
Vision and Control for Insect-scale Robots
This dissertation focuses on advancing vision and control for insect-scale robots, tackling two critical challenges: hovering and navigation. For hovering, the first study, presented in the TinySense paper (Best Student Paper Award at ICRA 2025), develops a lightweight, energy-efficient avionics …
-
A Scalable Hardware-Efficient CSNN Accelerator with Binarized STDP and STDG-based Hybrid Learning
… that processes information through sparse, event-driven spike signals. In this work, we present Binarized spike-timing dependent plasticity-gradient (BSTDPG), a novel SNN framework that combines Time-to-first-spike (TTFS) latency encoding with simple integrate-and-fire (IF) neuron model, …
-
Event-based Star Tracking
… This thesis investigates the application of event-based vision sensors that asynchronously detect per-pixel brightness changes with microsecond temporal resolution to address these challenges in star tracking. A comprehensive review of historical developments in star tracking technologies …
-
Vector Kernel Representation Theory, Applications in Point Clouds and Events Cameras
… in fields such as point cloud processing and event-based vision. A point set is an unordered collection of points in Euclidean space, typically generated by sensing technologies like 3D scanners or event cameras. The goal of point set representation is to transform these unordered points into …
Page 1 of 2