Simultaneous localization and mapping (SLAM) is a technique used to determine the location of a mobile vehicle in an unknown environment, while constructing a map of the unknown environment at the same time. Mobile platforms, which make use of SLAM algorithms, have industrial applications in autonomous maintenance, such as the inspection of flaws and defects in oil pipelines and storage tanks. An important component of SLAM is feature extraction, which is the process of detecting and extracting significant features such as corners, edges, and walls in an environment. Here, the use of sonars as sensors mounted on a mobile platform is examined, and a comparison of different algorithms currently in use is made and presented. This comparison is performed through a combination of experimental and numerical studies. The triangulation-based fusion algorithm is examined for point feature detection, and the standard Hough Transform and the triangulation Hough fusion (THF) are used for line detection. Comparisons are discussed and presented along with ongoing work.

No abstract

In recent years, there has been a lot of interest in clean energy especially in solar energy leading to the construction of numerous photovoltaic (PV) panels around the world. These panels need to be inspected to make sure they produce the desired amount of electricity. There are many methods to inspect which are manual, semi-autonomous and fully autonomous. The manual and semi-autonomous already exist but the process is tedious and requires a lot of time and resources. In this paper, we propose a fully autonomous solution where the drone will be preprogrammed to follow certain waypoints inputted via GPS data. The drone is equipped with a thermal camera where the video is recorded for postprocessing. The video is processed offline in order to detect the panels using image processing techniques such as thresholding, binary, canny edge, hough transform, and others. The novelty of this paper is on proposing a fully integrated solution for PV panel detection using a drone; it paves a way for future applications involving machine and deep learning.

Solar energy is getting a lot of traction due to the reduced cost and friendlier to the environment compared to fossil fuel. It is essential to inspect the PV farms to ensure that the correct capacity produced through early PV fault detection. We proposed a full autonomous solution, where the drone mission is programmed to follow a specific Global Positioning System (GPS) waypoints. The collected videos will undergo various image processing techniques to detect and track the PV panels. In this paper, we tried two different PV panel detection approaches. Both detections gave acceptable results. The first detection relies on various image processing techniques. The second detection relies on deep learning architecture called mask Region-based Convolution Neural Network (R-CNN). After that, we track the PV panels in every frame using camera data alone. The advantage of tracking the PV panels is to ensure unrepeated PV panel through tagging even if the drone flies over the panel again since each PV panel will be associated with a tag. The next step will be to test the PV panel’s proposed detection and tracking algorithm on a larger solar farm.

Mobile platforms that make use of concurrent localization and mapping algorithms have industrial applications for autonomous inspection and maintenance, such as the inspection of flaws and defects in oil pipelines and storage tanks. An important component of these algorithms is feature extraction, which involves detection of significant features that represent the environment. For example, points and lines can be used to represent features such as corners, edges, and walls. Feature extraction algorithms make use of relative position and angle data from sensor measurements gathered as the mobile vehicle traverses the environment. In this paper, sound navigation and ranging (SONAR) sensor data obtained from a mobile vehicle platform are considered for feature extraction and related algorithms are developed and studied. In particular, different combinations of commonly used feature extraction algorithms are examined to enhance the representation of the environment. The authors fuse the Triangulation Based Fusion (TBF), Hough Transfrom (HT), and SONAR salient feature extraction algorithms with the clustering algorithm. It is shown that the novel algorithm fusion can be used to capture walls, corners as well as features such as gaps in walls. This capability can be used to obtain additional information about the environment. Details of the algorithm fusion are discussed and presented along with results obtained through experiments.