BARS: a benchmark for airport runway segmentation
نویسندگان
چکیده
Airport runway segmentation can effectively reduce the accident rate during landing phase, which has largest risk of flight accidents. With rapid development deep learning (DL), related methods achieve good performance on tasks and be well adapted to complex scenes. However, lack large-scale, publicly available datasets in this field makes based DL difficult. Therefore, we propose a benchmark for airport segmentation, named BARS. Additionally, semiautomatic annotation pipeline is designed workload. BARS dataset with richest categories only instance field. The dataset, was collected using X-Plane simulation platform, contains 10,256 images 30,201 instances three categories. We evaluate eleven representative analyze their performance. Based characteristic an regular shape, plug-and-play smoothing postprocessing module (SPM) contour point constraint loss (CPCL) function smooth results mask-based contour-based methods, respectively. Furthermore, novel evaluation metric average smoothness (AS) developed measure smoothness. experiments show that existing prediction SPM CPCL enhance AS while modestly improving accuracy. Our work will at https://github.com/c-wenhui/BARS .
منابع مشابه
Runway Scheduling for Charlotte Douglas International Airport
This paper explores a multiple runway scheduling problem and generates the schedule for arrivals, departures and crossing aircraft planning to use the runways within a given planning horizon. We present a mixed integer linear programming-based model that explicitly considers separation criteria between pairs of aircraft and also incorporates various Traffic Management Initiatives. It also inclu...
متن کاملOptimal Selection of Airport Runway Configurations
We present a mixed integer programming (MIP) model to solve the problems of (i) selecting an airport’s optimal sequence of runway configurations and (ii) determining the optimal balance of arrivals and departures to be served at any moment. These problems, the runway configuration management (RCM) problem and the arrival/departure runway balancing (ADRB) problem, respectively, are of critical i...
متن کاملAirport Signs and Markings Recognition for Enhanced Runway Incursion Avoidance
A runway incursion is defined as any occurrence in the airport runway environment involving an aircraft, vehicle, person, or object on the ground that creates a collision hazard or results in a loss of required separation with an aircraft taking off, intending to take off, landing, or intending to land. Multiple factors could contribute to runway incursion, including pilots’ failure to accurate...
متن کاملDetection Algorithm of Airport Runway in Remote Sensing Images
This article describes a rapid detection method of the airport runway for remote sensing images. The specific algorithm implementation steps are: Firstly, we use the Otsu's method to separate the runway from the images. Then we use the fractional differential gradient operator, which has good anti-noise performance and effective edge extraction ability, to extract the edge information of image,...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Applied Intelligence
سال: 2023
ISSN: ['0924-669X', '1573-7497']
DOI: https://doi.org/10.1007/s10489-023-04586-5