Ground Truth of Powerline Dataset (Infrared-IR and Visible Light-VL)

Despite a relatively crowded literature about detection of power lines for aircraft safety, the works are mostly optimized with very few training images; some even use artificially generated images. The IR imaging case is even less utilized. The reason is clearly the tremendous workload to obtain real images. With this demand in mind, the authors cooperated with the Turkish Electricity Transmission Company (TEIAS) to obtain video captures from actual aircraft. Later, the authors made a thorough inspection over the video frames to isolate, capture and clean thousands of valuable images. In this content, 400 IR and 400 VL images are acquired and scaled to a size of 512x512. The IR folder contains IR images with power line, ground truths and overlay images of these images. The VL folder contains VL images with power line, ground truths and overlay images of these images. The IR and VL groups were deliberately constructed to contain both regular and especially confusing scenes. "TY" shows that there are no power lines in the images. "TV" shows that there are power lines in the images. The videos were captured from 21 different regions all over Turkey at different seasonal days. Due to varying background behavior, varying temperatures and weather conditions, and varying lighting conditions, the achieved positive set contains several difficult scenes where low contrast causes close to invisibility for power lines. The original video resolutions were 576x325 for IR and full HD for VL, however, the captured frames were scaled down to smaller sizes and the effect of resizing was tested for various image sizes. An image size of 512x512 is sufficient for a consistently accurate power line detection The program developed by Assistant Professor Cihan Topal from Anadolu University Electrical and Electronics Department was used to draw ground truths.

尽管当前针对航空器安全的电力线检测相关研究文献已相对丰富，但现有工作大多仅通过极少量训练图像进行优化，部分研究甚至采用人工生成的图像。红外（IR）成像场景的相关研究更是稀缺，其核心原因在于获取真实红外图像的工作量极其庞大。针对这一需求，本文作者与土耳其电力输电公司（Turkish Electricity Transmission Company, TEIAS）合作，获取了实际航空器搭载拍摄的视频素材。随后，作者对视频帧进行了全面筛查，从中提取、筛选并清洗出数千张高价值图像。本次构建的数据集共包含400张红外图像与400张可见光（VL）图像，所有图像均被统一缩放至512×512分辨率。红外图像文件夹中包含含电力线的红外图像、对应ground truth（真值标签）以及二者的叠加可视化图像；可见光图像文件夹则包含含电力线的可见光图像、对应真值标签及其叠加可视化图像。红外与可见光数据集组均刻意设计为同时包含常规场景与极具挑战性的混淆场景。其中，标签"TY"代表图像中无电力线，"TV"代表图像中存在电力线。所有视频素材均拍摄自土耳其全境21个不同区域，拍摄时间覆盖不同季节。由于拍摄时背景环境、温度、天气条件及光照条件均存在差异，最终构建的正样本集包含诸多高难度场景：部分场景中电力线与背景对比度极低，几乎难以被辨识。原始视频的分辨率分别为：红外视频576×325，可见光视频为全高清（Full HD）。不过，所有提取的帧均被缩放至更小尺寸，且作者针对多种图像尺寸验证了缩放操作的影响。实验结果表明，512×512的图像尺寸足以实现稳定且精准的电力线检测。本数据集的真值标签由安纳多卢大学电气与电子工程系助理教授Cihan Topal开发的程序绘制完成。

搜集汇总

背景与挑战

背景概述

该数据集是一个用于电力线检测的真实图像集合，包含400张红外图像和400张可见光图像，每张图像尺寸为512x512，并附带地面实况和叠加图像。数据集特别设计以涵盖常规和混淆场景，覆盖了21个土耳其不同地区在不同季节和天气条件下的拍摄，适用于计算机视觉和机器学习任务，旨在解决现有研究中训练图像不足的问题。