Conference paper Open Access

Tracking and Classification of Aerial Objects

Baptista, Marcia; Fernandes, Luis; Chaves, Paulo


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/eb65558d-5c33-46d6-9189-7f610968e937/Tracking-and-Classification-of-Aerial-Objects.pdf"
      }, 
      "checksum": "md5:c21bab287c7bd1686f2ecb3ed3e3305f", 
      "bucket": "eb65558d-5c33-46d6-9189-7f610968e937", 
      "key": "Tracking-and-Classification-of-Aerial-Objects.pdf", 
      "type": "pdf", 
      "size": 532512
    }
  ], 
  "owners": [
    26965
  ], 
  "doi": "10.5281/zenodo.3821145", 
  "stats": {
    "version_unique_downloads": 151.0, 
    "unique_views": 77.0, 
    "views": 88.0, 
    "version_views": 88.0, 
    "unique_downloads": 151.0, 
    "version_unique_views": 77.0, 
    "volume": 84669408.0, 
    "version_downloads": 159.0, 
    "downloads": 159.0, 
    "version_volume": 84669408.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.3821145", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.3821144", 
    "bucket": "https://zenodo.org/api/files/eb65558d-5c33-46d6-9189-7f610968e937", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.3821144.svg", 
    "html": "https://zenodo.org/record/3821145", 
    "latest_html": "https://zenodo.org/record/3821145", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.3821145.svg", 
    "latest": "https://zenodo.org/api/records/3821145"
  }, 
  "conceptdoi": "10.5281/zenodo.3821144", 
  "created": "2020-05-12T06:18:07.664188+00:00", 
  "updated": "2020-05-13T20:20:37.434110+00:00", 
  "conceptrecid": "3821144", 
  "revision": 2, 
  "id": 3821145, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.3821145", 
    "description": "<p>Unauthorized drone flying can prompt disruptions in critical facilities such as airports or railways. To prevent these situations, we propose a surveillance system that can sense malicious and/or illicit aerial targets. The idea is to track moving aerial objects using a static camera and when a tracked object is considered suspicious, the camera zooms in to take a snapshot of the target. This snapshot is then classified as an aircraft, drone, bird or cloud. In this work, we propose the classical technique of two-frame background subtraction to detect moving objects. We use the discrete Kalman filter to predict the location of each object and the Jonker-Volgenant algorithm to match objects between consecutive image frames. A deep residual network, trained with transfer learning, is used for image classification. The residual net ResNet-50 developed for the ILSVRC competition was retrained for this purpose. The performance of the system was evaluated with positive results in real-world conditions. The system was able to track multiple aerial objects with acceptable accuracy and the classification system also exhibited high performance.</p>", 
    "alternate_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.1007/978-3-030-38822-5_18"
      }
    ], 
    "title": "Tracking and Classification of Aerial Objects", 
    "language": "eng", 
    "relations": {
      "version": [
        {
          "count": 1, 
          "index": 0, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "3821144"
          }, 
          "is_last": true, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "3821145"
          }
        }
      ]
    }, 
    "access_right": "open", 
    "communities": [
      {
        "id": "alfa"
      }
    ], 
    "grants": [
      {
        "code": "700002", 
        "links": {
          "self": "https://zenodo.org/api/grants/10.13039/501100000780::700002"
        }, 
        "title": "Advanced Low Flying Aircrafts Detection and Tracking", 
        "acronym": "ALFA", 
        "program": "H2020", 
        "funder": {
          "doi": "10.13039/501100000780", 
          "acronyms": [], 
          "name": "European Commission", 
          "links": {
            "self": "https://zenodo.org/api/funders/10.13039/501100000780"
          }
        }
      }
    ], 
    "keywords": [
      "Object Tracking", 
      "Deep Learning", 
      "Residual Networks"
    ], 
    "publication_date": "2020-01-10", 
    "creators": [
      {
        "affiliation": "INOV Inesc Inovacao", 
        "name": "Baptista, Marcia"
      }, 
      {
        "affiliation": "INOV Inesc Inovacao", 
        "name": "Fernandes, Luis"
      }, 
      {
        "affiliation": "INOV Inesc Inovacao", 
        "name": "Chaves, Paulo"
      }
    ], 
    "meeting": {
      "acronym": "INTSYS 2019", 
      "dates": "4-6 December 2019", 
      "place": "Braga, Portugal", 
      "title": "3rd EAI International Conference on Intelligent Transport Systems"
    }, 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "resource_type": {
      "subtype": "conferencepaper", 
      "type": "publication", 
      "title": "Conference paper"
    }, 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.3821144", 
        "relation": "isVersionOf"
      }
    ]
  }
}
88
159
views
downloads
All versions This version
Views 8888
Downloads 159159
Data volume 84.7 MB84.7 MB
Unique views 7777
Unique downloads 151151

Share

Cite as