Deep Single Models vs. Ensembles: Insights for a Fast Deployment of Parking Monitoring Systems

• URL: http://arxiv.org/abs/2309.16495v1
• Date: Thu, 28 Sep 2023 14:59:53 GMT
• Title: Deep Single Models vs. Ensembles: Insights for a Fast Deployment of Parking Monitoring Systems
• Authors: Andre Gustavo Hochuli, Jean Paul Barddal, Gillian Cezar Palhano, Leonardo Matheus Mendes, Paulo Ricardo Lisboa de Almeida
• Abstract summary: Intelligent parking monitoring is still a challenge since most approaches involve collecting and labeling large amounts of data. Our study aims to uncover the challenges in creating a global framework, trained using publicly available labeled parking lot images. We found that models trained on diverse datasets can achieve 95% accuracy without the burden of data annotation and model training on the target parking lot.
• Score: 3.00363876980149
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Searching for available parking spots in high-density urban centers is a stressful task for drivers that can be mitigated by systems that know in advance the nearest parking space available. To this end, image-based systems offer cost advantages over other sensor-based alternatives (e.g., ultrasonic sensors), requiring less physical infrastructure for installation and maintenance. Despite recent deep learning advances, deploying intelligent parking monitoring is still a challenge since most approaches involve collecting and labeling large amounts of data, which is laborious and time-consuming. Our study aims to uncover the challenges in creating a global framework, trained using publicly available labeled parking lot images, that performs accurately across diverse scenarios, enabling the parking space monitoring as a ready-to-use system to deploy in a new environment. Through exhaustive experiments involving different datasets and deep learning architectures, including fusion strategies and ensemble methods, we found that models trained on diverse datasets can achieve 95\% accuracy without the burden of data annotation and model training on the target parking lot

Related papers

• Unsupervised Domain Adaptation for Self-Driving from Past Traversal Features [69.47588461101925]
  We propose a method to adapt 3D object detectors to new driving environments. Our approach enhances LiDAR-based detection models using spatial quantized historical features. Experiments on real-world datasets demonstrate significant improvements.
  arXiv  Detail & Related papers  (2023-09-21T15:00:31Z)
• Self-Supervised Representation Learning from Temporal Ordering of Automated Driving Sequences [49.91741677556553]
  We propose TempO, a temporal ordering pretext task for pre-training region-level feature representations for perception tasks. We embed each frame by an unordered set of proposal feature vectors, a representation that is natural for object detection or tracking systems. Extensive evaluations on the BDD100K, nuImages, and MOT17 datasets show that our TempO pre-training approach outperforms single-frame self-supervised learning methods.
  arXiv  Detail & Related papers  (2023-02-17T18:18:27Z)
• Uncertainty-aware Perception Models for Off-road Autonomous Unmanned Ground Vehicles [6.2574402913714575]
  Off-road autonomous unmanned ground vehicles (UGVs) are being developed for military and commercial use to deliver crucial supplies in remote locations. Current datasets used to train perception models for off-road autonomous navigation lack of diversity in seasons, locations, semantic classes, as well as time of day. We investigate how to combine multiple datasets to train a semantic segmentation-based environment perception model. We show that training the model to capture uncertainty could improve the model performance by a significant margin.
  arXiv  Detail & Related papers  (2022-09-22T15:59:33Z)
• Towards an Error-free Deep Occupancy Detector for Smart Camera Parking System [0.26249027950824505]
  We propose an end-to-end smart camera parking system where we provide an autonomous detecting occupancy by an object detector called OcpDet. Our detector also provides meaningful information from contrastive modules: training and spatial knowledge, which avert false detections during inference. We benchmark OcpDet on the existing PKLot dataset and reach competitive results compared to traditional classification solutions.
  arXiv  Detail & Related papers  (2022-08-17T11:02:29Z)
• Federated Deep Learning Meets Autonomous Vehicle Perception: Design and Verification [168.67190934250868]
  Federated learning empowered connected autonomous vehicle (FLCAV) has been proposed. FLCAV preserves privacy while reducing communication and annotation costs. It is challenging to determine the network resources and road sensor poses for multi-stage training.
  arXiv  Detail & Related papers  (2022-06-03T23:55:45Z)
• Scalable Vehicle Re-Identification via Self-Supervision [66.2562538902156]
  Vehicle Re-Identification is one of the key elements in city-scale vehicle analytics systems. Many state-of-the-art solutions for vehicle re-id mostly focus on improving the accuracy on existing re-id benchmarks and often ignore computational complexity. We propose a simple yet effective hybrid solution empowered by self-supervised training which only uses a single network during inference time.
  arXiv  Detail & Related papers  (2022-05-16T12:14:42Z)
• A Systematic Review on Computer Vision-Based Parking Lot Management Applied on Public Datasets [5.379463265037841]
  We surveyed and compared robust publicly available image datasets crafted to test computer vision-based methods for parking lot management approaches. The literature review identified relevant gaps that require further research.
  arXiv  Detail & Related papers  (2022-03-12T15:35:29Z)
• Smart Parking Space Detection under Hazy conditions using Convolutional Neural Networks: A Novel Approach [0.0]
  This paper investigates the use of dehazing networks that improves the performance of parking space occupancy under hazy conditions. The proposed system is deployable as part of existing smart parking systems where limited number of cameras are used to monitor hundreds of parking spaces.
  arXiv  Detail & Related papers  (2022-01-15T14:15:46Z)
• SODA10M: Towards Large-Scale Object Detection Benchmark for Autonomous Driving [94.11868795445798]
  We release a Large-Scale Object Detection benchmark for Autonomous driving, named as SODA10M, containing 10 million unlabeled images and 20K images labeled with 6 representative object categories. To improve diversity, the images are collected every ten seconds per frame within 32 different cities under different weather conditions, periods and location scenes. We provide extensive experiments and deep analyses of existing supervised state-of-the-art detection models, popular self-supervised and semi-supervised approaches, and some insights about how to develop future models.
  arXiv  Detail & Related papers  (2021-06-21T13:55:57Z)
• FADACS: A Few-shot Adversarial Domain Adaptation Architecture for Context-Aware Parking Availability Sensing [5.160087162892865]
  We design an end-to-end transfer learning framework for parking availability sensing to predict parking occupancy in areas in which the parking data is insufficient to feed into data-hungry models. This framework overcomes two challenges: 1) many real-world cases cannot provide enough data for most existing data-driven models, and 2) it is difficult to merge sensor data and heterogeneous contextual information.
  arXiv  Detail & Related papers  (2020-07-13T08:25:26Z)
• Training-free Monocular 3D Event Detection System for Traffic Surveillance [93.65240041833319]
  Existing event detection systems are mostly learning-based and have achieved convincing performance when a large amount of training data is available. In real-world scenarios, collecting sufficient labeled training data is expensive and sometimes impossible. We propose a training-free monocular 3D event detection system for traffic surveillance.
  arXiv  Detail & Related papers  (2020-02-01T04:42:57Z)

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.