Find research datasets worth reusing

Figure 5. Images binarized by SVM.-Design and Implementation of a Fully Autonomous UAV's Navigator Based on Omni-directional Vision System

In instance, the image in Fig. 4 was binarized manually (however, the person in charge of color adjustment is professional) and by using SVM resulting in Fig.5

Figure 4. Images binarized by hand.-Design and Implementation of a Fully Autonomous UAV's Navigator Based on Omni-directional Vision System

In instance, the image in Fig. 4 was binarized manually (however, the person in charge of color adjustment is professional) and by using SVM resulting in Fig.5

Design and Implementation of a Fully Autonomous UAV's Navigator Based on Omni-directional Vision System-Figure 3. The principle of SVM

Manual segmentation training was hard and very time consuming and rely to operator's accuracy, so we developed a color calibration algorithm using SVM(Support Vector Machine). In this subsection, we present a color recognition algorithm using the support vector machine (SVM).SVM is one of the classification algorithms which it has high generality since it can calculate a super plane that maximizes the margin of classes, Fig.3.[8] In our algorithm, the SVM is trained by the H'SY values of the classes and the mean of the obtained image H'SY values. After training, the obtained image is binarized by setting the maximum and minimum value in the distribution of each class as a threshold.

Figure 2. Catadioptric projection modelled by the unit sphere-Design and Implementation of a Fully Autonomous UAV's Navigator Based on Omni-directional Vision System

Since the beginning of UAV, the map building was one of the most addressed problems by researchers. Several researchers used Omni directional vision for robot navigation and map building. Because of the wide field of view in Omni directional sensors, the robot does not need to look around using moving parts (cameras or mirrors) or turning the moving parts. The global view offered by Omni directional vision is especially suitable for highly dynamic environments. The Omni directional vision system consists of a hyperbolic mirror, a USB color digital camera (Logitech C905) and a regulation device.

Figure 1. The use of visual servo control for helicopter stabilization-Design and Implementation of a Fully Autonomous UAV's Navigator Based on Omni-directional Vision System

Visual servoing is an approach to control motion of a helicopter using information feedback from a camera mounted on it. For their tremendous potential applications in various areas including environmental monitoring and anti-terrorism, unmanned small helicopters are being extensively studied in robotics and control in recent years. However, the research advance in dynamic control of small helicopters is limited due to highly coupled non- linear dynamics and the existence of various uncertain- ties. Many people studied controller design based on a Publisher Item Identifier. linearized or simplified model, but the controllers developed under linearized models cannot guarantee dynamic stability rigorously. Another effort is application of modern non-linear control theory to helicopter control because small helicopter are good test beds for sophisticated control techniques for their small size and highly coupled dynamics [4].

opencc-by-4.0Jun 2024View details →

Raw GNSS data divided into observation data in CRX, RINEX and mat format and navigation data in SP3 format and both group of the data in mat format

Open the record for dataset details and reuse information.

Fig. 3 in Navigating through ocean literacy gaps: an analysis of elementary school textbooks in Croatian education Abstract

Fig. 3: Presence of ocean literacy principles (OLP) and concepts (OLC) in higher grades of the elementary school science textbooks in Croatia (grades 5-8). Results are presented as average occurrence and standard deviation of books analysed for each grade.

Fig. 2 in Navigating through ocean literacy gaps: an analysis of elementary school textbooks in Croatian education Abstract

Fig. 2: Presence of ocean literacy principles (OLP) and concepts (OLC) in lower grades of the elementary school science textbooks in Croatia (grades 1-4). Results are presented as average occurrence and standard deviation of books analysed for each grade.

Fig. 1 in Navigating through ocean literacy gaps: an analysis of elementary school textbooks in Croatian education Abstract

Fig. 1: Mean contribution of pages with ocean-related topics in the text (A) and illustration (B) in the Croatian elementary school textbooks. Error bars represent the standard deviation among different publishers or textbook lines.

Fig. 4 in Navigating through ocean literacy gaps: an analysis of elementary school textbooks in Croatian education Abstract

Fig. 4: Best-case scenario of presence of ocean sciences topics according to OL principles and concepts in the elementary school textbooks in Croatia.

Figure 9. Experimental Page Rank dependency on Markov Chain length with balanced distribution-Study of a Random Navigation on the Web Using Software Simulation

This paper explored different implementation choices for analyzing the most important parameters about a web. Many researchers explored the use of new search engines for studying the evolution of the web (Ntoulas, Cho and Olston, 2004). Another important research is realized about the Link Structure Graph (LSG). The LSG captures a complete hyperlink structure from the web and models link associations reflected in the page layout (Rodrigues, Milic-Frayling and Fortuna, 2007). For further works ideas like extrapolation methods for accelerating page rank calculation can be developed (Kamvar et al., 2003).

Figure 7. Experimental Page Rank dependency on Markov Chain length-Study of a Random Navigation on the Web Using Software Simulation

The next diagram proves that the values for Experimental Page Rank depend on the length of the Markov Chain, while Algorithmic Page Rank remains constant.

Figure 6. Outlinks degree distribution for all web sites-Study of a Random Navigation on the Web Using Software Simulation

Some of the most important aspects of the analysis is obtaining the parameters which can give the main information about a web. In the simulation implementation information as: page, number of inlinks, number of outlinks, value for Algorithmic Page Rank and Experimental Page Rank will be processed for obtaining the results of the analysis. For the first part it was necessary to use experimental values as: inlinks, outlinks and in and out frequencies.

Figure 1. Markov Chain Model&Figure 2. Transition matrix-Study of a Random Navigation on the Web Using Software Simulation

For a good simulation it is very important to find methods for navigating through the web (Levene and Wheeldon, 2004). John Kemeny and Laurie Snell have proposed the use of Markov models for web simulations (Kemeny and Snell, 1960). Cadez et al. (2000) used Markov models for classifying the sessions into different categories for browsers. Some other proposed techniques choose to combine different order Markov models for obtaining low state complexity and improving accuracy, as Deshpande and Karypis (2004). Dongshan and Junyi (2002) used for predicting the access providing good scalability and high coverage a hybrid-order tree-like Markov model. As an alternative to the Markov model Pitkow proposed a longest subsequence model (Pitkow and Pirolli, 1999), also for predicting the next page accessed by the user Sarukkai chose Markov models (Sarukkai, 2000). Transitions are simulated using the Markov Chain nodes, Google matrix and an arbitrary initial probability distribution. Examples can be seen in Figure 1 and Figure 2.

Fig. 8. Algorithmic Page Rank-Study of a Random Navigation on the Web Using Software Simulation

Another diagram shows that for each site there is only one constant value independent of the length of Markov Chain. Algorithmic Page Rank only depends on the number of inlinks and outlinks.Table 4 contains the values for Experimental Page Rank with balanced distribution. In the following figure it is shown the diagram for the values obtained for Experimental Page Rank. The Experimental Page Rank values oscillate between the same limits independently of the change of Markov Chain length (N).

opencc-by-4.0Dec 2016View details →

A dataset for robotic outdoor visual navigation with multiple passages through trajectory segments

The images were captured by a fisheye camera and a magnetic compass was used to acquire the orientation data. The datasets are split in two folders: 1) LEARN: In order to learn a new place, the robot camera captures 15 images over a 360 degrees panorama. During this process, the robot stays still in order to avoid distortions in the representation of the place. 2) EXPLO: When exploring the environment (i.e. the rest of the time), the robot only captures 7 images per panorama, for the purpose of faster place recognition. Images are captured while the robot is moving. Various exploration panoramas are recorded around the trajectory performed in the learning panoramas (see traj.pdf). The average distance between two learning panoramas is 0.93 +/- 0.03 meters The average distance traveled during an exploration panoramas is 0.71 +/- 0.01 meters DATASET A --------- - 20 meters long - 22 learning panoramas (i.e. sets of 15 images captured while robot is stopped) - 5 exploration trajectories - A_on_learned: 29 exploration panoramas (i.e. sets of 7 images captured while robot is moving) - A_parallel: 29 exploration panoramas - A_diagonal1: 28 exploration panoramas - A_diagonal2: 30 exploration panoramas - A_diagonal3: 29 exploration panoramas DATASET B --------- - 20 meters long - 21 learning panoramas (i.e. sets of 15 images captured while robot is stopped) - 4 exploration trajectories - B_on_learned: 29 exploration panoramas (i.e. sets of 7 images captured while robot is moving) - B_parallel: 29 exploration panoramas - B_diagonal1: 29 exploration panoramas - B_diagonal2: 29 exploration panoramas DATASET C --------- - 23.1 meters long - 25 learning panoramas (i.e. sets of 15 images captured while robot is stopped) - 2 exploration trajectories - C_on_learned: 34 exploration panoramas (i.e. sets of 7 images captured while robot is moving) - C_parallel: 34 exploration panoramas PANO_INFO FILE STRUCTURE ------------------------ Every folder containing images also contains an info file, named either learn_pano_info.SAVE or explo_pano_info.SAVE. Each line corresponds to an image. The structures is the following: - column 1: id = image_id + 1 - column 2: azimuth of the center of the image in degrees/360 (value in [0,1]) - column 3: elevation of the center of the image. irrelevant in this database (equal to 0). - column 4: type of panorama: equal to 1 if learning and to 0 if exploration. - column 5: end of panorama: equal to 1 if it corresponds to the last image of a panorama. REFERENCES ---------- The dataset was used in the paper: Belkaid, M., Cuperlier, N., and Gaussier, P. Combining local and global visual information in context-based neurorobotic navigation. In Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN), pages 4947-4954, doi: 10.1109/IJCNN.2016.7727851, 2016.

opencc-by-4.0Jan 2016View details →

Figure 1. The Statechart for the Player movement and the Navigation System-Modeling, Designing, and Implementing an Avatar-based Interactive Map

The next section describes the Unified Modelling Language (UML) diagrams designed for the project, which are a state diagrams (also known as statecharts) for the Player movement, the Navigation system (Figure 1). In addition, we used a class diagram for the Player and Camera movement (Figure 2). When the avatar-based game starts, the state of the Player is Idle, i.e., Player_IDLE. When the user selects the building, it enables the navigation path towards the destination. If the user selects any arrow keys (Right, Left & Up) the state of the player will change to running (i.e., Player_Running). Also, the path will diminish along with the player movement; hence, the state of navigation path will change to Changing_Path.

opencc-by-4.0Jan 2016View details →

Figure 4. An inside view of the "Maes building along with the Navigation Path" -Modeling, Designing, and Implementing an Avatar-based Interactive Map

Figure 4 represents the navigation path to the Department of Computer Science inside the Maes building after selecting the option “D.C.S.”, which stands for Department of Computer Science.

opencc-by-4.0Jan 2019View details →

Robot navigation measurements driving in and out of the van

This dataset is a rosbag which contains the laser scans and the pose of a Husky mobile robot, using the robot's odometry and two SICK S300 laser scans to navigate. List of available topics: <ol> <li>/colrobot/hardware/scan_pointcloud</li> <li>/colrobot/navigation/perfect_match/debug/LaserScanfiltered</li> <li>/colrobot/navigation/perfect_match/LocalisationPoseResult</li> <li>/colrobot/navigation/map</li> <li>/tf</li> <li>/tf_static</li> </ol> Topics contents: <ol> <li>Pointcloud containing the merge of the two laser scans </li> <li>Pointcloud containing the laser scans which matched with the given map</li> <li>Robot's pose estimate</li> <li>Map of the van (robot's working area)</li> <li>6. Transforms of the system</li> </ol>