4.7 Article

Spike-Based Motion Estimation for Object Tracking Through Bio-Inspired Unsupervised Learning

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Computer Science, Artificial Intelligence

Event-Based Motion Segmentation With Spatio-Temporal Graph Cuts

Yi Zhou et al.

Summary: Identifying independently moving objects in dynamic scenes is a crucial task for scene understanding. Traditional cameras may face limitations such as motion blur or exposure artifacts, while event-based cameras offer advantages to overcome these limitations by reporting pixel-wise intensity changes asynchronously. This research develops a method to solve the event-based motion segmentation problem by casting it as an energy minimization problem involving fitting multiple motion models. The experiments demonstrate the versatility of the method in scenes with different motion patterns and number of moving objects, achieving state-of-the-art results without the need to determine the expected number of moving objects beforehand. The software and dataset are released under an open source license to encourage research in event-based motion segmentation.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2023)

Article Computer Science, Artificial Intelligence

Temporal Encoding and Multispike Learning Framework for Efficient Recognition of Visual Patterns

Qiang Yu et al.

Summary: This article focuses on developing temporal-based SNN methods to enhance the accuracy of image recognition while maintaining efficiency. The research shows that under various conditions, these methods exhibit efficient and effective performance, even comparable to rate-based ones, but with a lighter network structure and fewer spikes.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2022)

Proceedings Paper Automation & Control Systems

SpikeMS: Deep Spiking Neural Network for Motion Segmentation

Chethan M. Parameshwara et al.

Summary: Spiking Neural Networks (SNN) are a promising approach that closely mimics the biological brain's functioning, encoding temporal data efficiently and being well-suited for event-based sensors. However, the complexity of algorithms and training has hindered their widespread application in real-world large-scale tasks compared to standard Artificial Neural Networks (ANNs).

2021 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) (2021)

Proceedings Paper Computer Science, Artificial Intelligence

High-speed Image Reconstruction through Short-term Plasticity for Spiking Cameras

Yajing Zheng et al.

Summary: This paper presents a novel method for high-speed image reconstruction using the short-term plasticity mechanism of the brain, which establishes an STP model at each pixel of the spiking camera to infer scene radiance with temporal regularity of the spike stream. STP can be utilized to distinguish static and motion areas and enhance the quality of the reconstruction results. The experimental results demonstrate state-of-the-art performance in both image quality and computing time.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Proceedings Paper Computer Science, Artificial Intelligence

v2e: From Video Frames to Realistic DVS Events

Yuhuang Hu et al.

Summary: This paper introduces a toolbox that generates realistic synthetic DVS events and corrects incorrect claims about DVS characteristics. Using these synthetic events can improve network training in uncontrolled lighting conditions.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021 (2021)

Article Computer Science, Artificial Intelligence

Unsupervised Learning of a Hierarchical Spiking Neural Network for Optical Flow Estimation: From Events to Global Motion Perception

Federico Paredes-Valles et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2020)

Article Computer Science, Artificial Intelligence

An Event-Driven Categorization Model for AER Image Sensors Using Multispike Encoding and Learning

Rong Xiao et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2020)

Proceedings Paper Computer Science, Artificial Intelligence

Joint Filtering of Intensity Images and Neuromorphic Events for High-Resolution Noise-Robust Imaging

Zihao W. Wang et al.

2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2020)

Proceedings Paper Computer Science, Theory & Methods

An Efficient Coding Method for Spike Camera using Inter-Spike Intervals

Siwei Dong et al.

2019 DATA COMPRESSION CONFERENCE (DCC) (2019)

Proceedings Paper Computer Science, Artificial Intelligence

EV-IMO: Motion Segmentation Dataset and Learning Pipeline for Event Cameras

Anton Mitrokhin et al.

2019 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Event-Based Motion Segmentation by Motion Compensation

Timo Stoffregen et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

Proceedings Paper Computer Science, Software Engineering

A RETINA-INSPIRED SAMPLING METHOD FOR VISUAL TEXTURE RECONSTRUCTION

Lin Zhu et al.

2019 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME) (2019)

Article Computer Science, Hardware & Architecture

Loihi: A Neuromorphic Manycore Processor with On-Chip Learning

Mike Davies et al.

IEEE MICRO (2018)

Article Computer Science, Artificial Intelligence

SuperSpike: Supervised Learning in Multilayer Spiking Neural Networks

Friedemann Zenke et al.

NEURAL COMPUTATION (2018)

Proceedings Paper Computer Science, Artificial Intelligence

A Unifying Contrast Maximization Framework for Event Cameras, with Applications to Motion, Depth, and Optical Flow Estimation

Guillermo Gallego et al.

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2018)

Proceedings Paper Computer Science, Artificial Intelligence

ECO: Efficient Convolution Operators for Tracking

Martin Danelljan et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

Article Computer Science, Artificial Intelligence

A Spiking Neural Network System for Robust Sequence Recognition

Qiang Yu et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2016)

Article Neurosciences

Training Deep Spiking Neural Networks Using Backpropagation

Jun Haeng Lee et al.

FRONTIERS IN NEUROSCIENCE (2016)

Article Computer Science, Hardware & Architecture

True North: Design and Tool Flow of a 65 mW 1 Million Neuron Programmable Neurosynaptic Chip

Filipp Akopyan et al.

IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS (2015)

Review Multidisciplinary Sciences

Deep learning

Yann LeCun et al.

NATURE (2015)

Article Computer Science, Artificial Intelligence

Visual Tracking Using Neuromorphic Asynchronous Event-Based Cameras

Zhenjiang Ni et al.

NEURAL COMPUTATION (2015)

Article Computer Science, Artificial Intelligence

Asynchronous Event-Based Multikernel Algorithm for High-Speed Visual Features Tracking

Xavier Lagorce et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2015)

Article Computer Science, Artificial Intelligence

An Asynchronous Neuromorphic Event-Driven Visual Part-Based Shape Tracking

David Reverter Valeiras et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2015)

Article Engineering, Electrical & Electronic

A 240 x 180 130 dB 3 μs Latency Global Shutter Spatiotemporal Vision Sensor

Christian Brandli et al.

IEEE JOURNAL OF SOLID-STATE CIRCUITS (2014)

Article Mathematical & Computational Biology

Probabilistic inference of short-term synaptic plasticity in neocortical microcircuits

Rui P. Costa et al.

FRONTIERS IN COMPUTATIONAL NEUROSCIENCE (2013)

Article Neurosciences

Robotic goalie with 3 ms reaction time at 4% CPU load using event-based dynamic vision sensor

Tobi Delbruck et al.

FRONTIERS IN NEUROSCIENCE (2013)

Article Microscopy

Asynchronous event-based high speed vision for microparticle tracking

Z. Ni et al.

JOURNAL OF MICROSCOPY (2012)

Article Engineering, Mechanical

Toward real-time particle tracking using an event-based dynamic vision sensor

David Drazen et al.

EXPERIMENTS IN FLUIDS (2011)

Article Engineering, Electrical & Electronic

A 128x128 120 dB 15 μs latency asynchronous temporal contrast vision sensor

Patrick Lichtsteiner et al.

IEEE JOURNAL OF SOLID-STATE CIRCUITS (2008)

Article Engineering, Electrical & Electronic

Evaluating Multiple Object Tracking Performance: The CLEAR MOT Metrics

Keni Bernardin et al.

EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING (2008)