Classification of Micromobility Vehicles in Thermal-Infrared Images Based on Combined Image and Contour Features Using Neuromorphic Processing
Trends of environmental awareness, combined with a focus on personal fitness and health, motivate many people to switch from cars and public transport to micromobility solutions, namely bicycles, electric bicycles, cargo bikes, or scooters. To accommodate urban planning for these changes, cities and...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/6/3795 |
| _version_ | 1797613661591699456 |
|---|---|
| author | Bastian Stahl Jürgen Apfelbeck Robert Lange |
| author_facet | Bastian Stahl Jürgen Apfelbeck Robert Lange |
| author_sort | Bastian Stahl |
| collection | DOAJ |
| description | Trends of environmental awareness, combined with a focus on personal fitness and health, motivate many people to switch from cars and public transport to micromobility solutions, namely bicycles, electric bicycles, cargo bikes, or scooters. To accommodate urban planning for these changes, cities and communities need to know how many micromobility vehicles are on the road. In a previous work, we proposed a concept for a compact, mobile, and energy-efficient system to classify and count micromobility vehicles utilizing uncooled long-wave infrared (LWIR) image sensors and a neuromorphic co-processor. In this work, we elaborate on this concept by focusing on the feature extraction process with the goal to increase the classification accuracy. We demonstrate that even with a reduced feature list compared with our early concept, we manage to increase the detection precision to more than 90%. This is achieved by reducing the images of 160 × 120 pixels to only 12 × 18 pixels and combining them with contour moments to a feature vector of only 247 bytes. |
| first_indexed | 2024-03-11T06:58:59Z |
| format | Article |
| id | doaj.art-d6b566ced42943c48514563fb4b79488 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T06:58:59Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-d6b566ced42943c48514563fb4b794882023-11-17T09:27:03ZengMDPI AGApplied Sciences2076-34172023-03-01136379510.3390/app13063795Classification of Micromobility Vehicles in Thermal-Infrared Images Based on Combined Image and Contour Features Using Neuromorphic ProcessingBastian Stahl0Jürgen Apfelbeck1Robert Lange2Hochschule Bonn-Rhein-Sieg, 53757 Sankt Augustin, GermanyHochschule Bonn-Rhein-Sieg, 53757 Sankt Augustin, GermanyHochschule Bonn-Rhein-Sieg, 53757 Sankt Augustin, GermanyTrends of environmental awareness, combined with a focus on personal fitness and health, motivate many people to switch from cars and public transport to micromobility solutions, namely bicycles, electric bicycles, cargo bikes, or scooters. To accommodate urban planning for these changes, cities and communities need to know how many micromobility vehicles are on the road. In a previous work, we proposed a concept for a compact, mobile, and energy-efficient system to classify and count micromobility vehicles utilizing uncooled long-wave infrared (LWIR) image sensors and a neuromorphic co-processor. In this work, we elaborate on this concept by focusing on the feature extraction process with the goal to increase the classification accuracy. We demonstrate that even with a reduced feature list compared with our early concept, we manage to increase the detection precision to more than 90%. This is achieved by reducing the images of 160 × 120 pixels to only 12 × 18 pixels and combining them with contour moments to a feature vector of only 247 bytes.https://www.mdpi.com/2076-3417/13/6/3795micromobilitythermal imaginglong-wave infraredneuromorphic processingmachine learningmachine vision |
| spellingShingle | Bastian Stahl Jürgen Apfelbeck Robert Lange Classification of Micromobility Vehicles in Thermal-Infrared Images Based on Combined Image and Contour Features Using Neuromorphic Processing Applied Sciences micromobility thermal imaging long-wave infrared neuromorphic processing machine learning machine vision |
| title | Classification of Micromobility Vehicles in Thermal-Infrared Images Based on Combined Image and Contour Features Using Neuromorphic Processing |
| title_full | Classification of Micromobility Vehicles in Thermal-Infrared Images Based on Combined Image and Contour Features Using Neuromorphic Processing |
| title_fullStr | Classification of Micromobility Vehicles in Thermal-Infrared Images Based on Combined Image and Contour Features Using Neuromorphic Processing |
| title_full_unstemmed | Classification of Micromobility Vehicles in Thermal-Infrared Images Based on Combined Image and Contour Features Using Neuromorphic Processing |
| title_short | Classification of Micromobility Vehicles in Thermal-Infrared Images Based on Combined Image and Contour Features Using Neuromorphic Processing |
| title_sort | classification of micromobility vehicles in thermal infrared images based on combined image and contour features using neuromorphic processing |
| topic | micromobility thermal imaging long-wave infrared neuromorphic processing machine learning machine vision |
| url | https://www.mdpi.com/2076-3417/13/6/3795 |
| work_keys_str_mv | AT bastianstahl classificationofmicromobilityvehiclesinthermalinfraredimagesbasedoncombinedimageandcontourfeaturesusingneuromorphicprocessing AT jurgenapfelbeck classificationofmicromobilityvehiclesinthermalinfraredimagesbasedoncombinedimageandcontourfeaturesusingneuromorphicprocessing AT robertlange classificationofmicromobilityvehiclesinthermalinfraredimagesbasedoncombinedimageandcontourfeaturesusingneuromorphicprocessing |