1
|
Wan Z, Dai Y, Mao Y. Learning Dense and Continuous Optical Flow From an Event Camera. IEEE TRANSACTIONS ON IMAGE PROCESSING : A PUBLICATION OF THE IEEE SIGNAL PROCESSING SOCIETY 2022; 31:7237-7251. [PMID: 36374880 DOI: 10.1109/tip.2022.3220938] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/16/2023]
Abstract
Event cameras such as DAVIS can simultaneously output high temporal resolution events and low frame-rate intensity images, which own great potential in capturing scene motion, such as optical flow estimation. Most of the existing optical flow estimation methods are based on two consecutive image frames and can only estimate discrete flow at a fixed time interval. Previous work has shown that continuous flow estimation can be achieved by changing the quantities or time intervals of events. However, they are difficult to estimate reliable dense flow, especially in the regions without any triggered events. In this paper, we propose a novel deep learning-based dense and continuous optical flow estimation framework from a single image with event streams, which facilitates the accurate perception of high-speed motion. Specifically, we first propose an event-image fusion and correlation module to effectively exploit the internal motion from two different modalities of data. Then we propose an iterative update network structure with bidirectional training for optical flow prediction. Therefore, our model can estimate reliable dense flow as two-frame-based methods, as well as estimate temporal continuous flow as event-based methods. Extensive experimental results on both synthetic and real captured datasets demonstrate that our model outperforms existing event-based state-of-the-art methods and our designed baselines for accurate dense and continuous optical flow estimation.
Collapse
|
2
|
Vogginger B, Kreutz F, López-Randulfe J, Liu C, Dietrich R, Gonzalez HA, Scholz D, Reeb N, Auge D, Hille J, Arsalan M, Mirus F, Grassmann C, Knoll A, Mayr C. Automotive Radar Processing With Spiking Neural Networks: Concepts and Challenges. Front Neurosci 2022; 16:851774. [PMID: 35431782 PMCID: PMC9012531 DOI: 10.3389/fnins.2022.851774] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/10/2022] [Accepted: 03/07/2022] [Indexed: 11/13/2022] Open
Abstract
Frequency-modulated continuous wave radar sensors play an essential role for assisted and autonomous driving as they are robust under all weather and light conditions. However, the rising number of transmitters and receivers for obtaining a higher angular resolution increases the cost for digital signal processing. One promising approach for energy-efficient signal processing is the usage of brain-inspired spiking neural networks (SNNs) implemented on neuromorphic hardware. In this article we perform a step-by-step analysis of automotive radar processing and argue how spiking neural networks could replace or complement the conventional processing. We provide SNN examples for two processing steps and evaluate their accuracy and computational efficiency. For radar target detection, an SNN with temporal coding is competitive to the conventional approach at a low compute overhead. Instead, our SNN for target classification achieves an accuracy close to a reference artificial neural network while requiring 200 times less operations. Finally, we discuss the specific requirements and challenges for SNN-based radar processing on neuromorphic hardware. This study proves the general applicability of SNNs for automotive radar processing and sustains the prospect of energy-efficient realizations in automated vehicles.
Collapse
Affiliation(s)
- Bernhard Vogginger
- Chair of Highly-Parallel VLSI-Systems and Neuro-Microelectronics, Faculty of Electrical and Computer Engineering, Institute of Principles of Electrical and Electronic Engineering, Technische Universität Dresden, Dresden, Germany
- *Correspondence: Bernhard Vogginger
| | - Felix Kreutz
- Chair of Highly-Parallel VLSI-Systems and Neuro-Microelectronics, Faculty of Electrical and Computer Engineering, Institute of Principles of Electrical and Electronic Engineering, Technische Universität Dresden, Dresden, Germany
- Infineon Technologies Dresden GmbH & Co., KG, Dresden, Germany
| | | | - Chen Liu
- Chair of Highly-Parallel VLSI-Systems and Neuro-Microelectronics, Faculty of Electrical and Computer Engineering, Institute of Principles of Electrical and Electronic Engineering, Technische Universität Dresden, Dresden, Germany
| | - Robin Dietrich
- Department of Informatics, Technical University of Munich, Munich, Germany
| | - Hector A. Gonzalez
- Chair of Highly-Parallel VLSI-Systems and Neuro-Microelectronics, Faculty of Electrical and Computer Engineering, Institute of Principles of Electrical and Electronic Engineering, Technische Universität Dresden, Dresden, Germany
| | - Daniel Scholz
- Chair of Highly-Parallel VLSI-Systems and Neuro-Microelectronics, Faculty of Electrical and Computer Engineering, Institute of Principles of Electrical and Electronic Engineering, Technische Universität Dresden, Dresden, Germany
- Infineon Technologies Dresden GmbH & Co., KG, Dresden, Germany
| | - Nico Reeb
- Department of Informatics, Technical University of Munich, Munich, Germany
| | - Daniel Auge
- Department of Informatics, Technical University of Munich, Munich, Germany
- Infineon Technologies AG, Munich, Germany
| | - Julian Hille
- Department of Informatics, Technical University of Munich, Munich, Germany
- Infineon Technologies AG, Munich, Germany
| | | | - Florian Mirus
- BMW Group, Research, New Technologies, Garching, Germany
| | | | - Alois Knoll
- Department of Informatics, Technical University of Munich, Munich, Germany
| | - Christian Mayr
- Chair of Highly-Parallel VLSI-Systems and Neuro-Microelectronics, Faculty of Electrical and Computer Engineering, Institute of Principles of Electrical and Electronic Engineering, Technische Universität Dresden, Dresden, Germany
- Centre for Tactile Internet (CeTI) With Human-In-The-Loop, Cluster of Excellence, Technische Universität Dresden, Dresden, Germany
| |
Collapse
|
3
|
Deng Y, Chen H, Chen H, Li Y. Learning From Images: A Distillation Learning Framework for Event Cameras. IEEE TRANSACTIONS ON IMAGE PROCESSING : A PUBLICATION OF THE IEEE SIGNAL PROCESSING SOCIETY 2021; 30:4919-4931. [PMID: 33961557 DOI: 10.1109/tip.2021.3077136] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/12/2023]
Abstract
Event cameras have recently drawn massive attention in the computer vision community because of their low power consumption and high response speed. These cameras produce sparse and non-uniform spatiotemporal representations of a scene. These characteristics of representations make it difficult for event-based models to extract discriminative cues (such as textures and geometric relationships). Consequently, event-based methods usually perform poorly compared to their conventional image counterparts. Considering that traditional images and event signals share considerable visual information, this paper aims to improve the feature extraction ability of event-based models by using knowledge distilled from the image domain to additionally provide explicit feature-level supervision for the learning of event data. Specifically, we propose a simple yet effective distillation learning framework, including multi-level customized knowledge distillation constraints. Our framework can significantly boost the feature extraction process for event data and is applicable to various downstream tasks. We evaluate our framework on high-level and low-level tasks, i.e., object classification and optical flow prediction. Experimental results show that our framework can effectively improve the performance of event-based models on both tasks by a large margin. Furthermore, we present a 10K dataset (CEP-DVS) for event-based object classification. This dataset consists of samples recorded under random motion trajectories that can better evaluate the motion robustness of the event-based model and is compatible with multi-modality vision tasks.
Collapse
|
4
|
Li Y, Zhang L, Qian T. 2D Partial Unwinding-A Novel Non-Linear Phase Decomposition of Images. IEEE TRANSACTIONS ON IMAGE PROCESSING : A PUBLICATION OF THE IEEE SIGNAL PROCESSING SOCIETY 2019; 28:4762-4773. [PMID: 31071037 DOI: 10.1109/tip.2019.2914000] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/09/2023]
Abstract
This paper aims at proposing a novel 2D non-linear phase decomposition of images, which performs the image processing tasks better than the traditional Fourier transformation (linear phase decomposition), but further, it has additional mathematical properties allowing more effective image analysis, including adaptive decomposition components and positive instantaneous phase derivatives. 1D unwinding Blaschke decomposition has recently been proposed and studied. Through factorization it expresses arbitrary 1D signal into an infinite linear combination of Blaschke products. It offers fast converging positive frequency decomposition in the form of rational approximation. However, in the multi-dimensional cases, the usual factorization mechanism does not work. As a consequence, there is no genuine unwinding decomposition for multi-dimensions. In this paper, a 2D partial unwinding decomposition based on algebraic transforms reducing multi-dimensions to the 1D case is proposed and analyzed. The result shows that the fast convergence offers efficient image reconstruction. The tensor type decomposing terms are mutually orthogonal, giving rise to 2D positive frequency decomposition. The comparison results show that the proposed method outperforms the standard greedy algorithm and the most commonly used methods in the Fourier category. An application in watermarking is presented to demonstrate its potential in applications.
Collapse
|