Satellite Imagery Feature Detection using Deep Convolutional Neural Network: A Kaggle Competition

2017/06/19 by Vladimir Iglovikov, Iglovikov, Vladimir, Sergey Mushinskiy +3 · 4 citations
Computer Science · Engineering · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Geochemistry and Geologic Mapping #Remote-Sensing Image Classification #cs.CV

paper · pdf · doi:10.48550/arxiv.1706.06169

arxiv created 2017/06/19 · openalex publication_date 2017/06/19 · arxiv updated 2017/06/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper describes our approach to the DSTL Satellite Imagery Feature Detection challenge run by Kaggle. The primary goal of this challenge is accurate semantic segmentation of different classes in satellite imagery. Our approach is based on an adaptation of fully convolutional neural network for multispectral data processing. In addition, we defined several modifications to the training objective and overall training pipeline, e.g. boundary effect estimation, also we discuss usage of data augmentation strategies and reflectance indices. Our solution scored third place out of 419 entries. Its accuracy is comparable to the first two places, but unlike those solutions, it doesn't rely on complex ensembling techniques and thus can be easily scaled for deployment in production as a part of automatic feature labeling systems for satellite imagery analysis.

Citations

• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)

Cited by

• Synthetic Data Matters: Re-training with Geo-typical Synthetic Labels for Building Detection
• Mapping the walk: A scalable computer vision approach for generating sidewalk network datasets from aerial imagery
• Deep Neural Networks for automatic extraction of features in time series satellite images
• Flaws in the LLM Automation Narrative

Related

• Balanced Multi-Task Attention for Satellite Image Classification: A Systematic Approach to Achieving 97.23% Accuracy on EuroSAT Without Pre-Training
• Object Detection in Satellite Imagery using 2-Step Convolutional Neural Networks
• Convolutional Neural Network Segmentation for Satellite Imagery Data to Identify Landforms Using U-Net Architecture
• Convolutional Neural Networks for Large-Scale Remote-Sensing Image Classification
• Semantic segmentation on multi-resolution optical and microwave data using deep learning