A multi-layered approach for site detection in UAS emergency landing scenarios using geometry-based image segmentation

Abstract

This paper presents an alternative approach to image segmentation by using the spatial distribution of edge pixels as opposed to pixel intensities. The segmentation is achieved by a multi-layered approach and is intended to find suitable landing areas for an aircraft emergency landing. We combine standard techniques (edge detectors) with novel developed algorithms (line expansion and geometry test) to design an original segmentation algorithm. Our approach removes the dependency on environmental factors that traditionally influence lighting conditions, which in turn have negative impact on pixel-based segmentation techniques. We present test outcomes on realistic visual data collected from an aircraft, reporting on preliminary feedback about the performance of the detection. We demonstrate consistent performances over 97% detection rate.

Enabling Aircraft Emergency Landings Using Active Visual Site Detection

“…As the first stage of detection of potential landing sites, the SDS includes a 2D candidate identifier based on canny-edge detection, which forms a significant component of a 2D binary landing site classifier already presented in the literature [11,10]. The use of texture analysis and contrast descriptors to identify suitable landing areas has also been used by Garcia-Pardo et al [4].…”

“…The 2D landing site classifier has already been described in the literature [11,10]. It operates purely on 2D imagery, without any temporal information, to classify the pixels in an image into a binary safe/not-safe classification by detecting Canny Edges in the camera image and performing a dilation to expand the local unsafe region.…”

Visual Multiple Target Tracking From a Descending Aerial Platform

“…The landing approach taken by Scherer et al [7] uses lidar for non-cooperative sensing to autonomously land a full-scale helicopter at unprepared sites. Mejias et al [8] demonstrate a camera-based landing zone detection algorithm for UAS in emergency landing scenarios. In this work, a visual multiple target tracker is used to perceive information about moving ground targets.…”

Safe landing site detection using SRTM data for the Unmanned Aerial Vehicles

“…Sınıflandırıcı olarak Naive Bayes sınıflandırıcı kullanılmıştır. Luis Mejias ve arkadaşları [6], bir İHA'nın zorunlu iniş yapabileceği alanın tespit edilmesi için görüntü bölümleme (segmentation) tabanlı bir uygulama geliştirmiştir. Çalışmada inilebilecek uygun alan veya alanların tespiti için İHA'dan alınan anlık görüntüler kullanılmıştır.…”