Object Size-Driven Design of Convolutional Neural Networks: Virtual Axle
Detection based on Raw Data
- URL: http://arxiv.org/abs/2309.01574v2
- Date: Mon, 18 Dec 2023 08:32:34 GMT
- Title: Object Size-Driven Design of Convolutional Neural Networks: Virtual Axle
Detection based on Raw Data
- Authors: Henik Riedel, Robert Steven Lorenzen and Clemens H\"ubler
- Abstract summary: This paper presents a new approach for detecting axles, enabling real-time application of Bridge Weigh-In-Motion (BWIM) systems without dedicated axle detectors.
The proposed Virtual Axle Detector with Enhanced Receptive Field (VADER) is independent of bridge type and sensor placement.
By using raw data instead of spectograms as input, the receptive field can be enhanced without increasing the number of parameters.
- Score: 0.0
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Rising maintenance costs of ageing infrastructure necessitate innovative
monitoring techniques. This paper presents a new approach for detecting axles,
enabling real-time application of Bridge Weigh-In-Motion (BWIM) systems without
dedicated axle detectors. The proposed Virtual Axle Detector with Enhanced
Receptive Field (VADER) is independent of bridge type and sensor placement
while only using raw acceleration data as input. By using raw data instead of
spectograms as input, the receptive field can be enhanced without increasing
the number of parameters. We also introduce a novel receptive field (RF) rule
for an object-size driven design of Convolutional Neural Network (CNN)
architectures. We were able to show, that the RF rule has the potential to
bridge the gap between physical boundary conditions and deep learning model
development. Based on the RF rule, our results suggest that models using raw
data could achieve better performance than those using spectrograms, offering a
compelling reason to consider raw data as input. The proposed VADER achieves to
detect 99.9 % of axles with a spatial error of 4.13 cm using only acceleration
measurements, while cutting computational and memory costs by 99 % compared to
the state-of-the-art using spectograms.
Related papers
- SIRST-5K: Exploring Massive Negatives Synthesis with Self-supervised
Learning for Robust Infrared Small Target Detection [53.19618419772467]
Single-frame infrared small target (SIRST) detection aims to recognize small targets from clutter backgrounds.
With the development of Transformer, the scale of SIRST models is constantly increasing.
With a rich diversity of infrared small target data, our algorithm significantly improves the model performance and convergence speed.
arXiv Detail & Related papers (2024-03-08T16:14:54Z) - UnLoc: A Universal Localization Method for Autonomous Vehicles using
LiDAR, Radar and/or Camera Input [51.150605800173366]
UnLoc is a novel unified neural modeling approach for localization with multi-sensor input in all weather conditions.
Our method is extensively evaluated on Oxford Radar RobotCar, ApolloSouthBay and Perth-WA datasets.
arXiv Detail & Related papers (2023-07-03T04:10:55Z) - RadarGNN: Transformation Invariant Graph Neural Network for Radar-based
Perception [0.0]
A novel graph neural network is proposed that does not just use the information of the points themselves but also the relationships between them.
The model is designed to consider both point features and point-pair features, embedded in the edges of the graph.
The RadarGNN model outperforms all previous methods on the RadarScenes dataset.
arXiv Detail & Related papers (2023-04-13T13:57:21Z) - Radar Image Reconstruction from Raw ADC Data using Parametric
Variational Autoencoder with Domain Adaptation [0.0]
We propose a parametrically constrained variational autoencoder, capable of generating the clustered and localized target detections on the range-angle image.
To circumvent the problem of training the proposed neural network on all possible scenarios using real radar data, we propose domain adaptation strategies.
arXiv Detail & Related papers (2022-05-30T16:17:36Z) - FOVEA: Foveated Image Magnification for Autonomous Navigation [53.69803081925454]
We propose an attentional approach that elastically magnifies certain regions while maintaining a small input canvas.
Our proposed method boosts the detection AP over standard Faster R-CNN, with and without finetuning.
On the autonomous driving datasets Argoverse-HD and BDD100K, we show our proposed method boosts the detection AP over standard Faster R-CNN, with and without finetuning.
arXiv Detail & Related papers (2021-08-27T03:07:55Z) - DAAIN: Detection of Anomalous and Adversarial Input using Normalizing
Flows [52.31831255787147]
We introduce a novel technique, DAAIN, to detect out-of-distribution (OOD) inputs and adversarial attacks (AA)
Our approach monitors the inner workings of a neural network and learns a density estimator of the activation distribution.
Our model can be trained on a single GPU making it compute efficient and deployable without requiring specialized accelerators.
arXiv Detail & Related papers (2021-05-30T22:07:13Z) - Dense Label Encoding for Boundary Discontinuity Free Rotation Detection [69.75559390700887]
This paper explores a relatively less-studied methodology based on classification.
We propose new techniques to push its frontier in two aspects.
Experiments and visual analysis on large-scale public datasets for aerial images show the effectiveness of our approach.
arXiv Detail & Related papers (2020-11-19T05:42:02Z) - Contextual-Bandit Anomaly Detection for IoT Data in Distributed
Hierarchical Edge Computing [65.78881372074983]
IoT devices can hardly afford complex deep neural networks (DNN) models, and offloading anomaly detection tasks to the cloud incurs long delay.
We propose and build a demo for an adaptive anomaly detection approach for distributed hierarchical edge computing (HEC) systems.
We show that our proposed approach significantly reduces detection delay without sacrificing accuracy, as compared to offloading detection tasks to the cloud.
arXiv Detail & Related papers (2020-04-15T06:13:33Z) - Semi-supervised Grasp Detection by Representation Learning in a Vector
Quantized Latent Space [1.3048920509133808]
In this paper, a semi-supervised learning based grasp detection approach has been presented.
To the best of our knowledge, this is the first time a Variational AutoEncoder (VAE) has been applied in the domain of robotic grasp detection.
The model performs significantly better than the existing approaches which do not make use of unlabelled images to improve the grasp.
arXiv Detail & Related papers (2020-01-23T12:47:13Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.