Exploiting Context in Remote Sensing Object Detection

Status: open
Supervisor: Sebastian Zambanini

Problem Statement

Detecting and classifying objects in remote sensing images is a challenging task, since the objects’ optical signature is less discriminative  due to the small resolution. Common object detection methods in this area aim to find object locations by classifying local structures, while neglecting the larger surroundings of the object. However, from statistical perspective, it is evident that nearby objects provide a useful prior for object occurrence and shape. e.g. when a group of cars is parked in a row.

Goal

The goal of this work is to explore and examine methods that can be used to automatically exploit context for detecting objects in remote sensing images.

Workflow

Literature Review – getting to know the algorithms
Data Preparation
Implementation
Evaluation
Written Report/Thesis and final presentation

Literature

[1] Barnea E., Ben-Shahar O. , “Contextual Object Detection with a Few Relevant Neighbors”. Computer Vision – ACCV 2018. ACCV 2018. Lecture Notes in Computer Science, vol 11362. Springer, Cham. https://doi.org/10.1007/978-3-030-20890-5_31, 2019.
[2] S. K. Divvala, D. Hoiem, J. H. Hays, A. A. Efros and M. Hebert, “An empirical study of context in object detection,” 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1271-1278, doi: 10.1109/CVPR.2009.5206532, 2019.
[3] José Oramas M., Tinne Tuytelaars, “Recovering hard-to-find object instances by sampling context-based object proposals”,
Computer Vision and Image Understanding, Volume 152, Pages 118-130, https://doi.org/10.1016/j.cviu.2016.08.007, 2016.
[4] Kang Tong, Yiquan Wu, Fei Zhou, “Recent advances in small object detection based on deep learning: A review” Image and Vision Computing, Volume 97, https://doi.org/10.1016/j.imavis.2020.103910, 2020
[5] Zhang, G.; Lu, S.; Zhang, W. “CAD-Net: A Context-Aware Detection Network for Objects in Remote Sensing Imagery”. IEEE Trans. Geosci. Remote Sens., 57, 10015–10024, 2019.