Fully Decoupled Residual ConvNet for Real-Time Railway Scene Parsing of UAV Aerial Images

2021 ◽  
pp. 1-14
Author(s):  
Lei Tong ◽  
Zhipeng Wang ◽  
Limin Jia ◽  
Yong Qin ◽  
Yanbin Wei ◽  
...  
Keyword(s):  
Real Time ◽  
Aerial Images ◽  
Scene Parsing

RSNet: Rail semantic segmentation network for extracting aerial railroad images

2021 ◽  
pp. 1-18
Author(s):  
R.S. Rampriya ◽  
Sabarinathan ◽  
R. Suganya
Keyword(s):  
Real Time ◽  
Visual Processing ◽  
Feature Fusion ◽  
Semantic Segmentation ◽  
Vital Role ◽  
Obstacle Detection ◽  
Aerial Images ◽  
Computationally Efficient ◽  
Fusion Algorithm ◽  
Uav Images

In the near future, combo of UAV (Unmanned Aerial Vehicle) and computer vision will play a vital role in monitoring the condition of the railroad periodically to ensure passenger safety. The most significant module involved in railroad visual processing is obstacle detection, in which caution is obstacle fallen near track gage inside or outside. This leads to the importance of detecting and segment the railroad as three key regions, such as gage inside, rails, and background. Traditional railroad segmentation methods depend on either manual feature selection or expensive dedicated devices such as Lidar, which is typically less reliable in railroad semantic segmentation. Also, cameras mounted on moving vehicles like a drone can produce high-resolution images, so segmenting precise pixel information from those aerial images has been challenging due to the railroad surroundings chaos. RSNet is a multi-level feature fusion algorithm for segmenting railroad aerial images captured by UAV and proposes an attention-based efficient convolutional encoder for feature extraction, which is robust and computationally efficient and modified residual decoder for segmentation which considers only essential features and produces less overhead with higher performance even in real-time railroad drone imagery. The network is trained and tested on a railroad scenic view segmentation dataset (RSSD), which we have built from real-time UAV images and achieves 0.973 dice coefficient and 0.94 jaccard on test data that exhibits better results compared to the existing approaches like a residual unit and residual squeeze net.

scholarly journals Utilizing drone technology in the civil engineering

2019 ◽  
Vol 14 (1) ◽  
pp. 27-37
Author(s):  
Matúš Tkáč ◽  
Peter Mésároš
Keyword(s):  
Real Time ◽  
Unmanned Aerial Vehicle ◽  
Civil Engineering ◽  
Aerial Images ◽  
General Overview ◽  
Aerial Photogrammetry ◽  
Different Types ◽  
Aerial Vehicle

Abstract An unmanned aerial vehicle (UAVs), also known as drone technology, is used for different types of application in the civil engineering. Drones as a tools that increase communication between construction participants, improves site safety, uses topographic measurements of large areas, with using principles of aerial photogrammetry is possible to create buildings aerial surveying, bridges, roads, highways, saves project time and costs, etc. The use of UAVs in the civil engineering can brings many benefits; creating real-time aerial images from the building objects, overviews reveal assets and challenges, as well as the broad lay of the land, operators can share the imaging with personnel on site, in headquarters and with sub-contractors, planners can meet virtually to discuss project timing, equipment needs and challenges presented by the terrain. The aim of this contribution is to create a general overview of the use of UAVs in the civil engineering. The contribution also contains types of UAVs used for construction purposes, their advantages and also disadvantages.

Real-Time 3-D Semantic Scene Parsing With LiDAR Sensors

2020 ◽  
pp. 1-13
Author(s):  
Fei Wang ◽  
Yan Zhuang ◽  
Hong Zhang ◽  
Hong Gu
Keyword(s):  
Real Time ◽  
Scene Parsing ◽  
Semantic Scene

scholarly journals A Novel Tilt Correction Technique for Irradiance Sensors and Spectrometers On-Board Unmanned Aerial Vehicles

2018 ◽  
Vol 10 (12) ◽  
pp. 2068 ◽  
Author(s):  
Juha Suomalainen ◽  
Teemu Hakala ◽  
Raquel Alves de Oliveira ◽  
Lauri Markelin ◽  
Niko Viljanen ◽  
...  
Keyword(s):  
Real Time ◽  
Remote Sensing Data ◽  
Correction Method ◽  
Aerial Images ◽  
Aerial Image ◽  
Optical Remote Sensing ◽  
Processing Unit ◽  
Atmospheric Conditions ◽  
Tilt Correction ◽  
Correction Technique

In unstable atmospheric conditions, using on-board irradiance sensors is one of the only robust methods to convert unmanned aerial vehicle (UAV)-based optical remote sensing data to reflectance factors. Normally, such sensors experience significant errors due to tilting of the UAV, if not installed on a stabilizing gimbal. Unfortunately, such gimbals of sufficient accuracy are heavy, cumbersome, and cannot be installed on all UAV platforms. In this paper, we present the FGI Aerial Image Reference System (FGI AIRS) developed at the Finnish Geospatial Research Institute (FGI) and a novel method for optical and mathematical tilt correction of the irradiance measurements. The FGI AIRS is a sensor unit for UAVs that provides the irradiance spectrum, Real Time Kinematic (RTK)/Post Processed Kinematic (PPK) GNSS position, and orientation for the attached cameras. The FGI AIRS processes the reference data in real time for each acquired image and can send it to an on-board or on-cloud processing unit. The novel correction method is based on three RGB photodiodes that are tilted 10° in opposite directions. These photodiodes sample the irradiance readings at different sensor tilts, from which reading of a virtual horizontal irradiance sensor is calculated. The FGI AIRS was tested, and the method was shown to allow on-board measurement of irradiance at an accuracy better than ±0.8% at UAV tilts up to 10° and ±1.2% at tilts up to 15°. In addition, the accuracy of FGI AIRS to produce reflectance-factor-calibrated aerial images was compared against the traditional methods. In the unstable weather conditions of the experiment, both the FGI AIRS and the on-ground spectrometer were able to produce radiometrically accurate and visually pleasing orthomosaics, while the reflectance reference panels and the on-board irradiance sensor without stabilization or tilt correction both failed to do so. The authors recommend the implementation of the proposed tilt correction method in all future UAV irradiance sensors if they are not to be installed on a gimbal.

scholarly journals Real-time and automatic map stitching through aerial images from UAV

2021 ◽  
Vol 2120 (1) ◽  
pp. 012025
Author(s):  
J N Goh ◽  
S K Phang ◽  
W J Chew
Keyword(s):  
Real Time ◽  
Matrix Multiplication ◽  
Image Features ◽  
Aerial Images ◽  
Aerial Image ◽  
Process Time ◽  
Image Stitching ◽  
Singular Value Decomposition Method ◽  
Value Decomposition ◽  
Computational Resources

Abstract Real-time aerial map stitching through aerial images had been done through many different methods. One of the popular methods was a features-based algorithm to detect features and to match the features of two and more images to produce a map. There are several feature-based methods such as ORB, SIFT, SURF, KAZE, AKAZE and BRISK. These methods detect features and compute homography matrix from matched features to stitch images. The aim for this project is to further optimize the existing image stitching algorithm such that it will be possible to run in real-time as the UAV capture images while airborne. First, we propose to use a matrix multiplication method to replace a singular value decomposition method in the RANSAC algorithm. Next, we propose to change the workflow to detect the image features to increase the map stitching rate. The proposed algorithm was implemented and tested with an online aerial image dataset which contain 100 images with the resolution of 640 × 480. We have successfully achieved the result of 1.45 Hz update rate compared to original image stitching algorithm that runs at 0.69 Hz. The improvement shown in our proposed improved algorithm are more than two folds in terms of computational resources. The method introduced in this paper was successful speed up the process time for the program to process map stitching.

scholarly journals TERRAIN AWARE IMAGE CLIPPING FOR REAL-TIME AERIAL MAPPING

2018 ◽  
Vol IV-1 ◽  
pp. 61-68
Author(s):  
D. Hein ◽  
R. Berger
Keyword(s):  
Real Time ◽  
Image Data ◽  
Aerial Images ◽  
Aerial Image ◽  
Sensing Applications ◽  
Data Links ◽  
Map Generation ◽  
Aerial Mapping ◽  
Using Data ◽  
Terrain Elevation

<p><strong>Abstract.</strong> Many remote sensing applications demand for a fast and efficient way of generating orthophoto maps from raw aerial images. One prerequisite is direct georeferencing, which allows to geolocate aerial images to their geographic position on the earth’s surface. But this is only half the story. When dealing with a large quantity of highly overlapping images, a major challenge is to select the most suitable image parts in order to generate seamless aerial maps of the captured area. This paper proposes a method that quickly determines such an optimal (rectangular) section for each single aerial image, which in turn can be used for generating seamless aerial maps. Its key approach is to clip aerial images depending on their geometric intersections with a terrain elevation model of the captured area, which is why we call it <i>terrain aware image clipping</i> (TAC). The method has a modest computational footprint and is therefore applicable even for rather limited embedded vision systems. It can be applied for both, real-time aerial mapping applications using data links as well as for rapid map generation right after landing without any postprocessing step. Referring to real-time applications, this method also minimizes transmission of redundant image data. The proposed method has already been demonstrated in several search-and-rescue scenarios and real-time mapping applications using a broadband data link and diffent kinds of camera and carrier systems. Moreover, a patent for this technology is pending.</p>

scholarly journals AN INTEGRATED RAPID MAPPING SYSTEM FOR DISASTER MANAGEMENT

2017 ◽  
Vol XLII-1/W1 ◽  
pp. 499-504 ◽  
Author(s):  
D. Hein ◽  
S. Bayer ◽  
R. Berger ◽  
T. Kraft ◽  
D. Lesmeister
Keyword(s):  
Real Time ◽  
Disaster Management ◽  
Large Scale ◽  
Software Tool ◽  
Aerial Images ◽  
Sensor Data ◽  
Camera System ◽  
Rapid Mapping ◽  
Mapping System ◽  
Effective Assessment

Natural disasters as well as major man made incidents are an increasingly serious threat for civil society. Effective, fast and coordinated disaster management crucially depends on the availability of a real-time situation picture of the affected area. However, in situ situation assessment from the ground is usually time-consuming and of limited effect, especially when dealing with large or inaccessible areas. A rapid mapping system based on aerial images can enable fast and effective assessment and analysis of medium to large scale disaster situations. This paper presents an integrated rapid mapping system that is particularly designed for real-time applications, where comparatively large areas have to be recorded in short time. The system includes a lightweight camera system suitable for UAV applications and a software tool for generating aerial maps from recorded sensor data within minutes after landing. The paper describes in particular which sensors are applied and how they are operated. Furthermore it outlines the procedure, how the aerial map is generated from image and additional gathered sensor data.

scholarly journals DisCountNet: Discriminating and Counting Network for Real-Time Counting and Localization of Sparse Objects in High-Resolution UAV Imagery

2019 ◽  
Vol 11 (9) ◽  
pp. 1128 ◽  
Author(s):  
Maryam Rahnemoonfar ◽  
Dugan Dobbs ◽  
Masoud Yari ◽  
Michael J. Starek
Keyword(s):  
High Resolution ◽  
Real Time ◽  
State Of The Art ◽  
Sparse Matrix ◽  
Aerial Images ◽  
Heat Map ◽  
High Resolution Image ◽  
Current State ◽  
Density Map ◽  
Distinct Features

Recent deep-learning counting techniques revolve around two distinct features of data—sparse data, which favors detection networks, or dense data where density map networks are used. Both techniques fail to address a third scenario, where dense objects are sparsely located. Raw aerial images represent sparse distributions of data in most situations. To address this issue, we propose a novel and exceedingly portable end-to-end model, DisCountNet, and an example dataset to test it on. DisCountNet is a two-stage network that uses theories from both detection and heat-map networks to provide a simple yet powerful design. The first stage, DiscNet, operates on the theory of coarse detection, but does so by converting a rich and high-resolution image into a sparse representation where only important information is encoded. Following this, CountNet operates on the dense regions of the sparse matrix to generate a density map, which provides fine locations and count predictions on densities of objects. Comparing the proposed network to current state-of-the-art networks, we find that we can maintain competitive performance while using a fraction of the computational complexity, resulting in a real-time solution.

Sign in / Sign up

Export Citation Format

Share Document