Effectively identifying and locating plants on the forest floor is essential for successful reforestation efforts and forest health assessment. This task is challenging due to the diverse range of plants, the high variance in appearance, the limited availability of accurately labeled data, and the complexity of data collection in post-harvest forest areas. These challenges are addressed by integrating field-surveyed plant data with images captured by Unmanned Aerial Vehicles (UAVs) to produce labeled training data. A custom Faster-RCNN model is trained using the aforementioned data to detect individual plants and clustered plant groups. Two different annotation approaches (unified class and distinct classes) are explored to address plant groupings and compare their performance using Mean Average Precision at 50% overlap (mAP50) and F1 score. The model trained using the unified class approach shows promise in detecting plants and plant groups larger than 0.15 square meters (F1 score: 0.44) but struggles with those smaller than 0.15 square meters. The inclusion of field-labeled data makes detection more challenging but ensures reliability. Meanwhile, the distinct class approach shows limited success. This work underscores the value of high-resolution imagery and comprehensive temporal analysis in enhancing detection accuracy and reliability.

Over the past few years, forests have become increasingly susceptible to various natural stress factors, mainly due to climate change induced events such as drought. Quantifying the objects that lay on the forest floor such as soil, vegetation, wooden debris and tree stumps is a viable method for estimating the extent of the stress factors. Remote sensing is an established modus operandi for collecting data in forest environments. In this work, we focus on Unmanned Aerial Vehicles (UAV) as remote sensing platforms aiming to detect tree stumps in varying stages of decay within a forest calamity area. The platform provides us with both high-resolution images from RGB and multispectral cameras and height data. In addition, a vegetation index for wood is proposed to better highlight the presence of tree stumps using multispectral data. Object detection is performed with feature-level fusion after which Object-Based Image Analysis (OBIA) is carried out. The fused multispectral and RGB data resulted in 53.68% recall and 31.0% precision in detecting tree stumps. In comparison, the fused RGB and height data resulted in 50.0% recall and 20.9% precision.

Climate change induced events such as drought lead to stress in forest trees, causing major catastrophic outbreaks of bark beetle insects. Current efforts to mitigate the infestation is to mass log an affected area. As a result the forest floor of a post-harvest area is cluttered with various objects such as tree logs and twigs. This study is aimed towards exploring basic computer vision methods that make use of shape, elevation and color to detect and segment objects on the forest floor. Such methods have advantages over learning methods due to their simplicity and speed in producing initial usable results, in addition to the low requirement of computational resources and training data. The highest intersection over union result of the multi-class detection and segmentation method is 0.64 for the road class. Such methods prove the feasibility of deploying basic computer vision techniques to acquire fast and reliable results.

Agricultural fields suffer from damage due to changing climate conditions and wildlife foraging. Damage incurred by wild boar is classified as the main contributing factor to grasslands damage. Such damage results in losses for farmers due to reduced yield potential and repair costs. The extent of wild boar damage is typically estimated manually by using ground based approaches (e.g. GPS measurements), which is a time consuming task with questionable accuracy. Building upon our previous work, we present an autonomous approach to detect and classify the cause of damage to grasslands (wild boar, mole etc.). The approach entails utilizing convolutional neural networks for semantic segmentation of grasslands. An RGB baseline was established, in addition to evaluating multimodal architectures that incorporate different surface model feature representations, leading to a joint representation of spectral and elevation information. Testing and experimentation was performed in real-world grasslands around Bonn, Germany. The results show that incorporating elevation features with late fusion enhances the overall performance of the network over the RGB baselines.

Damage to grasslands is mainly caused by wild boar during foraging. Farmers in Germany thereby register yield losses and expenses for damage repair. This contribution analyzes the acquisition and processing of aerial images to orthomosaics and image segmentation to perform spatial measurements of damaged patches in grasslands. A sample set of manually annotated orthomosaics is analyzed. Preliminary classification results applying a convolutional neural network approach to segment damaged patches are presented. First results show the applicability of the applied methods in the detection of damage caused by wild boar and suggest that other damage causes (e.g., mole damage) should be considered to improve results.

Navigation of Unmanned Ground Vehicles (UGV) in unknown environments is an active area of research for mobile robotics. A main hindering factor for UGV navigation is the limited range of the on-board sensors that process only restricted areas of the environment at a time. In addition, most existing approaches process sensor information under the assumption of a static environment. This restrains the exploration capability of the UGV especially in time-critical applications such as search and rescue. The cooperation with an Unmanned Aerial Vehicle (UAV) can provide the UGV with an extended perspective of the environment which enables a better-suited path planning solution that can be adjusted on demand. In this work, we propose a UAV-UGV cooperative path planning approach for dynamic environments by performing semantic segmentation on images acquired from the UAV’s view via a deep neural network. The approach is evaluated in a car park scenario, with the goal of providing a path plan to an empty parking space for a ground-based vehicle. The experiments were performed on a created dataset of real-world car park images located in Croatia and Germany, in addition to images from a simulated environment. The segmentation results demonstrate the viability of the proposed approach in producing maps of the dynamic environment on demand and accordingly generating path plans for ground-based vehicles.

This work addresses the issue of finding an optimal flight zone for a side-by-side tracking and following Unmanned Aerial Vehicle(UAV) adhering to space-restricting factors brought upon by a dynamic Vector Field Extraction (VFE) algorithm. The VFE algorithm demands a relatively perpendicular field of view of the UAV to the tracked vehicle, thereby enforcing the space-restricting factors which are distance, angle and altitude. The objective of the UAV is to perform side-byside tracking and following of a lightweight ground vehicle while acquiring high quality video of tufts attached to the side of the tracked vehicle. The recorded video is supplied to the VFE algorithm that produces the positions and deformations of the tufts over time as they interact with the surrounding air, resulting in an airflow model of the tracked vehicle. The present limitations of wind tunnel tests and computational fluid dynamics simulation suggest the use of a UAV for real world evaluation of the aerodynamic properties of the vehicle's exterior. The novelty of the proposed approach is alluded to defining the specific flight zone restricting factors while adhering to the VFE algorithm, where as a result we were capable of formalizing a locally-static and a globally-dynamic geofence attached to the tracked vehicle and enclosing the UAV.

In this paper we present work towards finding an optimal flight zone of an Unmanned Aerial Vehicle (UAV) as adhering to space-restricting factors brought upon by a dynamic vector field extraction algorithm. The objective of the UAV is to perform side-by-side tracking and following of a lightweight ground vehicle while acquiring high quality video of tufts attached to the side of the tracked vehicle. The recorded video is supplied to a dynamic vector field extraction algorithm that produces the positions and deformations of the tufts over time as they interact with the surrounding air, resulting in an airflow model of the tracked vehicle. The present limitations of wind tunnel tests and computational fluid dynamics simulation suggest the use of a UAV for real world evaluation of the aerodynamic properties of the shell of the vehicles exterior. The novelty of the proposed approach is alluded to defining specific flight zone restricting factors while adhering to the vector field extraction algorithm, where as a result we were capable of formalizing a locally-static and a globally-dynamic geofence attached to the tracked vehicle and enclosing the UAV. Moreover, a drone video quality and stability analysis tool was implemented to aid in quantifying the quality of the drone video and in constructing the geofence.

The objective of this paper is to deal with a new technique based on Model-Free Control (MFC). The concept of this controller is to use a basic controller along with an ultra-local model to compensate for system's uncertainties and disturbances. In this paper, a proposed algorithm is introduced based on an integrated structure between the Nonlinear Integral-Backstepping technique (NIB) and the MFC. The LQR, NIB, LQR-MFC, and NIB-MFC are implemented on a real quadrotor UAV. Various real-time flight tests are conducted to validate the importance of using the MFC side by side with NIB. The proposed combination shows robust performance compared to the other algorithms under fault-free and actuator fault conditions.

The two major occurring faults with relevance to UAVs are actuator and sensor faults. This paper presents a fault diagnostic and fault tolerant control algorithm on the altitude sensor of a quadrotor UAV. The quadrotor used is QUANSER's Qball-X4, which is part of the Unmanned Vehicles Lab (UVL) at UAE University. The proposed fault tolerant control is based on hardware redundancy of three altitude sensors. Residuals are generated based on the three altitude measurements, which are then used to compute indicators about fault occurrences. These indicators serve the fault isolation algorithm to determine the faulty sensor, and in return allows for automatic switching between the sensors in case the faulty sensor is used in the closed-loop system. The effectiveness of the proposed algorithm is demonstrated by means of real flight tests.

There are many advantages for having collaborative flight of multiple Unmanned Arial Vehicles (UAVs) rather than a single UAV. In this paper, a proposed formation flight algorithm is tested and a Graphical User Interface (GUI) is implemented on the ground station to allow for path planning and flight control. The proposed algorithm is based on a Hierarchal Leader-Follower formation, where the leader has more flexibility and independence, while the follower is completely dependent on the path taken by the leader. The path planning and the proposed formation flight algorithm are implemented on one axis and tested on two quadrotors. The proposed algorithm is implemented on real quadrotors and its ability to track the given path will be shown.

This paper proposes an integrated structure between the Nonlinear Integral-Backstepping technique (NIB) and the Model-Free Control (MFC) to control the Qball-X4 quadrotor system. The recursive nature of the backstepping theory ensures the system stability according to the Lyapunov theory, and the integral action will compensate for the steady state error. In addition, the MFC aims to handle the un-modeled system dynamics and disturbances. A comparison between the NIB algorithm and the NIB-MFC combination will be implemented and tested on the Qball-X4 vehicle. Various real-time flight tests are conducted to validate the importance of using the MFC side by side with NIB. The proposed combination shows better performance than the sole NIB in controlling the quadrotor under normal and disturbed flight conditions.

This paper proposes a nonlinear control technique to control the position of the Qball-X4 quadrotor using a cascaded methodology of two Adaptive Integral Backstepping Controllers (AIBC). The nonlinear algorithm uses the principle of Lyapunov methodology in the backstepping technique to ensure the stability of the vehicle, and utilizes the integral action to eliminate the steady state error that caused by the disturbances and model uncertainties, as well as, the adaptation law will estimate the modeling errors caused by assumptions in simplifying the complexity of the quadrotor model. The algorithm goes through two stages of cascaded AIBCs; the first stage aims to stabilize the attitude and the altitude of the quadrotor, and the second stage feeds the first stage with the desired attitude values to control the position of the quadrotor. Flight test results show that the proposed algorithm is capable of controlling the position of the nonlinear quadrotor model.

In this paper, the Model-Free Control (MFC) is used and tested on a Multi-Input-Multi-Output (MIMO) nonlinear system, which is a quadrotor vehicle. The system is decomposed into different-dependent Single-Input-Single-Output (SISO) sub-systems, where the MFC algorithm is applied on each one of them. MFC aims at compensating the time-varying disturbances and un-modeled system dynamics that the optimal feedback controller fails to cope with. A comparison between LQR feedback controller with and without the MFC will be implemented and tested on a real quadrotor vehicle. Different flight test results validate the importance of using the MFC, and its capability to control the quadrotor system that is using a degraded feedback controller, as well.