Published October 31, 2023 | Version 1.0
Dataset Open

TAMPAR: Visual Tampering Detection for Parcels Logistics in Postal Supply Chains

Creators

  • 1. FZI Research Center for Information Technology
  • 2. ROR icon Karlsruhe Institute of Technology

Description

TAMPAR is a real-world dataset of parcel photos for tampering detection with annotations in COCO format. For details see our paper and for visual samples our project page. Features are: 

  • >900 annotated real-world images with >2,700 visible parcel side surfaces
  • 6 different tampering types
  • 6 different distortion strengths

Relevant computer vision tasks:

  • bounding box detection
  • classification
  • instance segmentation
  • keypoint estimation
  • tampering detection and classification

If you use this resource for scientific research, please consider citing our WACV 2024 paper "TAMPAR: Visual Tampering Detection for Parcel Logistics in Postal Supply Chains".

Files

tampar.zip

Files (6.4 GB)

Name Size Download all
md5:7a92e796a263998ab5437399f1771fcb
6.4 GB Preview Download

Additional details

Related works

Is supplement to
Conference paper: https://a-nau.github.io/tampar (URL)
Conference paper: arXiv:2311.03124 (arXiv)