PESMOD (PExels Small Moving Object Detection) dataset consists of high resolution aerial images in which moving objects are labelled manually. The aim of this work is to provide a different and challenging dataset for moving object detection methods evaluation. Each moving object is labelled for each frame with PASCAL VOC format in a XML file. Dataset consists of 8 sequence detailed below.
|Sequence name||Number of frames||Number of moving objects|
Click here to download the dataset
Citing PESMOD Dataset
If you find this dataset or method (proposed in the paper) useful in your work, please cite the paper:
Preprint paper on arxiv
If you find any mistakes in the labels, you can report it in the issues section.
Script to view dataset, build and run performance code to evaluate your own method with foreground mask
To view dataset after downloading:
python view-dataset.py --path "/home/ibrahim/PESMOD/Pexels-Welton/"
Build performance code with following commands:
cd performance mkdir build cmake .. make .
Run with (-d for dataset main folder, -m for masks main folder, -f for sequence name, -o if you apply morphological opening):
./performance -d "/home/ibrahim/PESMOD/" -m "/home/ibrahim/SCBU-PESMOD-results/" -f "Pexels-Marian"