Refine
Document Type
- video (57)
- Conference Proceeding (8)
Keywords
- Robotik (30)
- Flugkörper (21)
- UAV (21)
- Rettungsrobotik (8)
- 3D Modell (7)
- Rasenmäher (4)
- DRZ (3)
- Deutsches Rettungsrobotik-Zentrum (3)
- SLAM (3)
- Kartierung (2)
- Mapping (2)
- Point Clouds (2)
- Ubuntu (2)
- Vegetationsbrand (2)
- 360° Panorama (1)
- 3D-Printer (1)
- Bildverarbeitung (1)
- Inferenz <Künstliche Intelligenz> (1)
- NeRF (1)
- Ortsbestimmung (1)
- Rescue Robotics (1)
- Small UAVs (1)
- Travelling-salesman-Problem (1)
- Vegetationsbrandübung (1)
- Vegetatonsbrandübung (1)
- Visual Monocular SLAM (1)
This video shows a model computed from 124 images taken at the Tjex 2015 of the trade project (www.tradr-project.eu). The images were acquired by walking around the object and reconstruct the structure with VisualSfm software.
This video shows a model computed from 320 images taken at the Tjex 2015 of the trade project (www.tradr-project.eu). The images were acquired with a falcan 8 drone (AscTec) and reconstruct the structure with VisualSfm software. The flight was in 150 m. The Tower is about 95 meter high.
The video shows a snapshot of a 16 minute flight of a DJI Phantom 3 professional over the Schloss Birlinghoven at Sankt Augustin, Germany. The castle is located at the Fraunhofer Campus at Sankt Augustin. The 3D model is generated out of 400 key frames of the 4k video which are cut out with ffmpeg. The work is part of an evaluation in the Tradr Project (www.tradr-project.eu)
The two churches, San Francesco and Sant'Agostino in Amatrice, Italy was hit by an earthquake on August 24 2016. Both churches are in a state of partial collapse, in need of shoring to prevent potential further destruction and to preserve the national heritage. The video show the mission at 1.Sept.2016 in clips of 10 seconds.
The TRADR project was asked by the Italian firebrigade Vigili del Fuoco to provide 3D textured models of two churches.
The team entered San Francesco with two UGVs (ground robots) and one UAV (drone, flown by Prof. Surmann), teleoperating them entirely out of line of sight and partially in collaboration. We entered Sant'Agostino with one UAV (also flown by Prof. Surmann) while two other UAVs were providing a view from different angles to facilitate maneuvering them entirely out of line of sight.
Global registration of heterogeneous ground and aerial mapping data is a challenging task. This is especially difficult in disaster response scenarios when we have no prior information on the environment and cannot assume the regular order of man-made environments or meaningful semantic cues. In this work we extensively evaluate different approaches to globally register UGV generated 3D point-cloud data from LiDAR sensors with UAV generated point-cloud maps from vision sensors. The approaches are realizations of different selections for: a) local features: key-points or segments; b) descriptors: FPFH, SHOT, or ESF; and c) transformation estimations: RANSAC or FGR. Additionally, we compare the results against standard approaches like applying ICP after a good prior transformation has been given. The evaluation criteria include the distance which a UGV needs to travel to successfully localize, the registration error, and the computational cost. In this context, we report our findings on effectively performing the task on two new Search and Rescue datasets. Our results have the potential to help the community take informed decisions when registering point-cloud maps from ground robots to those from aerial robots.
This paper presents a novel approach to build consistent 3D maps for multi robot cooperation in USAR environments. The sensor streams from unmanned aerial vehicles (UAVs) and ground robots (UGV) are fused in one consistent map. The UAV camera data are used to generate 3D point clouds that are fused with the 3D point clouds generated by a rolling 2D laser scanner at the UGV. The registration method is based on the matching of corresponding planar segments that are extracted from the point clouds. Based on the registration, an approach for a globally optimized localization is presented. Apart from the structural information of the point clouds, it is important to mention that no further information is required for the localization. Two examples show the performance of the overall registration.
Venice 2018: Tradr Review
(2018)
The video shows an orthopoto and a textured 3D model of the location. 300 images were recorded in two short flights with a Mavic Pro in 50 meter height. The first one was a single grid while the camera facing down and the second one was a double grid facing the camera at an 60 degree angle. The 3D model is computed with OpenDroneMap.
This technical report is about the architecture and integration of commercial UAVs in Search and Rescue missions. We describe a framework that consists of heterogeneous UAVs, a UAV task planner, a bridge to the UAVs, an intelligent image hub, and a 3D point cloud generator. A first version of the framework was developed and tested in several training missions in the EU project TRADR.
Challenging visual localization of an UAV while flying out of a room into a snowy environment (~ 4:50). The UAV is equipped with a 360° camera. The localization is done with OpenVSLAM.
The video was recorded in Jan. 2019 at the Fire Brigade training center in Dortmund
To achieve nearly real time conditions the original resolution of 5k (30 fps) was reduced to 2k (ffmpeg -i video.mp4 -vf scale=1920:-1 -crf 25 vido-small.mp4) with high compression (-crf 25). This reduce the original size from 3.2 GB to 93MB (~ 4 MBit/s which could be transmitted online via a radio link). The localization shown did not use frameskip. With a frameskip above 1 the localization fails while the UAV is flying through the window. Indoor localization can be done with a frameskip of 3 in real time.
9 Panoramen, das erste ist aus größerer Höhe aufgenommen und enthält im Himmel eine Karte mit den Positionen der aufgenommenen Punkte (gelb). Das aktuelle Bild ist im Fadenkreuz (rot). Zusätzlich noch ein paar Details zu dem aktuellen Punkt. Jedes Panorama ist 10 Sekunden lang.
Zum Betrachten die höchste Auflösungsstufe wählen und die Pausetaste verwenden. Mit dem gedrückten linken Button kann man sich im Bild bewegen.
Wie können mit Luftbildaufnahmen 3D Modelle generiert werden?
- Planen von kreisförmigen und einen rasterförmigen Flug Trajektorien.
- Autonomes Abfliegen und Aufnahme der Bilder
- Verortung der Bilder mittels GPS und Structure from Motion Algorithmen.
- Generierung von 3D Modellen mithilfe von Multi-View Stereo Algorithmen.
This technical report is about the mission and the experience gained during the reconnaissance of an industrial hall with hazardous substances after a major fire in Berlin. During this operation, only UAVs and cameras were used to obtain information about the site and the building. First, a geo-referenced 3D model of the building was created in order to plan the entry into the hall. Subsequently, the UAVs were used to fly in the heavily damaged interior and take pictures from inside of the hall. A 360° camera mounted under the UAV was used to collect images of the surrounding area especially from sections that were difficult to fly into. Since the collected data set contained similar images as well as blurred images, it was cleaned from non-optimal images using visual SLAM, bundle adjustment and blur detection so that a 3D model and overviews could be calculated. It was shown that the emergency services were not able to extract the necessary information from the 3D model. Therefore, an interactive panorama viewer with links to other 360° images was implemented where the links to the other images depends on the semi dense point cloud and located camera positions of the visual SLAM algorithm so that the emergency forces could view the surroundings.
This technical report is about the architecture and integration of very small commercial UAVs (< 40 cm diagonal) in indoor Search and Rescue missions. One UAV is manually controlled by only one single human operator delivering live video streams and image series for later 3D scene modelling and inspection. In order to assist the operator who has to simultaneously observe the environment and navigate through it we use multiple deep neural networks to provide guided autonomy, automatic object detection and classification and local 3D scene modelling. Our methods help to reduce the cognitive load of the operator. We describe a framework for quick integration of new methods from the field of Deep Learning, enabling for rapid evaluation in real scenarios, including the interaction of methods.
At the beginning of the pandemic in Feb. 2020 I had a little time and wanted to do something new i.e. bring my 3D printer, AI and computer science together somehow. The result is a printed portrait with a lot of computer science. Using style transfer I transferred the etching style of a Göthe portrait to a young girl I call Carolin. By means of image processing I made a black and white picture out of it. Then, using the problem of the traveling salesman, each black point in the picture is interpreted as a city and the whole picture is drawn by only one line. Since this line is very long, it is optimized and shortened by a so-called simulated annealing algorithm. The result is printed in 5 layers on a 3D printer.
Durch Panoramen in Kombination mit dem ORB-SLAM ist ein schnelles Tracking möglich, liefert jedoch ausschließlich spärliche Daten. Durch die Kombination mit einem neuronalen Netz soll der SLAM Algorithmus zu einem RGBD-SLAM erweitert werden, um ein besseres Tracking und eine dichtere Punktwolke zu gewährleisten.
360° Camera at a small UAV
(2021)
360° UAV Flight in a collapse test setup at the German Resuce Robotik Center
The video shows a very high resolution 3D point cloud !!! of the outdoor area of the German Rescue Robotics Center. For the recording, a 25-second POI flight was performed with a Mavic 3. From the 4K video footage captured during this flight, 77 images were cropped and localized within 4 minutes using colmap and processed using Neural Radiance Fields (NeRF). The nerfacto model of Nerfstudio was trained on an Nvidia RTX 4090 for 8 minutes. In summary, a top 3D model is available to task forces after about 13 minutes. The calculation is performed locally on site by the RobLW of the DRZ. The video shown here shows a free camera path rendered at 60 hz (Full HD).
Nerf(acto) for the 3D modeling of the Computer Science building of Westfälische Hochschule GE
(2023)
The video shows a very high resolution 3D point cloud !!! of the computer science building of the University of Applied Science Gelsenkirchen. For the recording a 3 minute flight with a M30T was performed. The 105 images taken by the wide-angle camera during this flight were localized within 3 minutes using colmap and processed using Neural Radiance Fields (NeRF). The nerfacto model of Nerfstudio was trained on an Nvidia RTX 4090 for 8 minutes. Thus, a top 3D model is available after about 15 minutes.
The video shown here shows a free camera path rendered at 60 hz (Full HD).
From the 360° images of the former video (
• German rescue robotic center captured... ) we now generate the 3D point cloud. The UAV needs 3 minutes to capture the outdoor scenario and the hall from inside and outside. The 3D point cloud generation is 5x slower than the video. It uses a VSLAM algorithm to localize the k-frames (green) and with 3 k-frames it use a 360° PatchMatch algorithm implemented at a NVIDIA graphic card (CUDA) to calculated the dense point clouds.The hall ist about 70 x 20 meters.
The video shows the first test of a small spherical UAV (35 cm) with 4 rotors for missions in complex environments such as buildings, caves or tunnels. The spherical design protects the vehicle's internal components and allows the UAV to roll over the ground when the environment allows. The drone can land and take off in any position and come into contact with objects without endangering the propellers and can restart even after crashes.
Sperical UAV: Crash Test with 1/2 liter bottle from 2 meters