[PDF] Low-latency event-based visual odometry | Semantic Scholar (2024)

This paper presents a low-latency visual odometry algorithm for the DAVIS sensor using event-based feature tracks that tightly interleaves robust pose optimization and probabilistic mapping and shows that the method successfully tracks the 6-DOF motion of the sensor in natural scenes.

The implementation of a CNN trained to detect and describe features within an image as well as the implementation of an event- based visual-inertial odometry (EVIO) pipeline, which estimates a vehicle’s 6-degrees-offreedom (DOF) pose using an affixed event-based camera with an integrated inertial measurement unit (IMU).

This paper is the first work on visual-inertial fusion with event cameras using a continuous-time framework and shows that the method provides improved accuracy over the result of a state-of-the-art visual odometry method for event cameras.

This document presents the research and implementation of an event-based visualinertial odometry (EVIO) pipeline, which estimates a vehicle’s 6-degrees-of-freedom (DOF) motion and pose utilizing an affixed event- based camera with an integrated Micro-Electro-Mechanical Systems (MEMS) inertial measurement unit (IMU).

The system successfully leverages the advantages of event-based cameras to perform visual odometry in challenging illumination conditions, such as low-light and high dynamic range, while running in real-time on a standard CPU.

This paper presents and releases a collection of datasets captured with a DAVIS in a variety of synthetic and real environments, which it hopes will motivate research on new algorithms for high-speed and high-dynamic-range robotics and computervision applications.

An algorithm is developed that augments each event with its lifetime, which is computed from the event's velocity on the image plane, which gives a continuous representation of events in time, hence enabling the design of new algorithms that outperform those based on the accumulation of events over fixed, artificially-chosen time intervals.

This paper addresses ego-motion estimation for an event-based vision sensor using a continuous-time framework to directly integrate the information conveyed by the sensor.

This paper presents the first onboard perception system for 6-DOF localization during high-speed maneuvers using a Dynamic Vision Sensor (DVS), and provides a versatile method to capture ground-truth data using a DVS.

This paper proposes a robust, high-accurate, and real-time optimization-based monocular event-based visual-inertial odometry (VIO) method with event-corner features, line-based event features, and point-based image features that can achieve superior performance compared with the state-of-the-art image-based or event- based VIO.

...

...

A method for low-latency pose tracking using a DVS and Active Led Markers, which are LEDs blinking at high frequency (>1 KHz), which is compared to traditional pose tracking based on a CMOS camera.

It is shown that matching on the timing of the visual events provides a new solution to the real-time computation of 3-D objects when combined with geometric constraints using the distance to the epipolar lines.

This work proposes a novel method for vision based simultaneous localization and mapping (vSLAM) using a biologically inspired vision sensor that mimics the human retina that operates on individual pixel events and generates high-quality 2D environmental maps with precise robot localizations.

This paper introduces a framework to estimate visual flow from the local properties of events' spatiotemporal space and shows that precise visual flow orientation and amplitude can be estimated using a local differential approach on the surface defined by coactive events.

A hybrid neuromorphic-procedural system consisting of an address-event silicon retina, a computer, and a servo motor can be used to implement a fast sensory-motor reactive controller to track and block balls shot at a goal.

This demonstration shows how a pair of spike-based silicon retina dynamic vision sensors (DVS) is used to provide fast visual feedback for controlling an actuated table to balance an ordinary pencil.

A novel algorithm for robot self-localization using an embedded event-based sensor which only represents pixel-level illumination changes in a scene, in contrast to classical image sensors, which wastefully transmit redundant information at a much lower frame rate.

This silicon retina provides an attractive combination of characteristics for low-latency dynamic vision under uncontrolled illumination with low post-processing requirements by providing high pixel bandwidth, wide dynamic range, and precisely timed sparse digital output.

A CMOS vision sensor that combines event-driven asychronous read out of temporal contrast with synchronous frams-based active pixel sensor (APS) readout of intensity that allows low latency at low data rate and low system-level power consumption is proposed.

...

...