SEARCH AND RESCUE IMAGE DATASET FOR PERSON DETECTION - SARD

Citation Author(s):
Sasa
Sambolek
Department of Informatics University of Rijeka
Marina
Ivasic-Kos
Department of Informatics University of Rijeka
Submitted by:
Sasa Sambolek
Last updated:
Mon, 03/01/2021 - 07:30
DOI:
10.21227/ahxm-k331
Data Format:
License:
0
0 ratings - Please login to submit your rating.

Abstract 

For the task of detecting casualties and persons in search and rescue scenarios in drone images and videos, our database called SARD was built. The actors in the footage have simulate exhausted and injured persons as well as "classic" types of movement of people in nature, such as running, walking, standing, sitting, or lying down. Since different types of terrain and backgrounds determine possible events and scenarios in captured images and videos, the shots include persons on macadam roads, in quarries, low and high grass, forest shade, and the like. The obtained dataset comprises 1,981 manually labeled images extracted from video frames.

To increase the robustness of the SARD data, an extension of the SARD set, called Corr, was created that includes images that further simulate different weather conditions that may occur in actual search and rescue situations such as fog, snow, and ice. Also, blur images are included in the Corr set that occur in real conditions as a result of camera movement and aerial shooting in motion.

 

Instructions: 

From the recordings with a total length of about 35 minutes, 1,981 single frames with people on them were singled out. In the selected images, the persons were manually tagged so that the set could be used to train the supervised model. Tagging of persons was done using the LabelImg tool. The image annotation consists of the position of the bounding box around each object of interest, the size of the bounding box in terms of width and height, and the corresponding class designation (Standing, Walking, Running, Sitting, Lying, Not Defined) for the person.

Comments

1

Submitted by Tais Pinheiro on Sun, 04/11/2021 - 13:29