High-quality 3D reconstruction of existing buildings is essential for their maintenance, restoration, and management. Effective view planning for image collection significantly impacts the quality of photogrammetry-ba...
详细信息
High-quality 3D reconstruction of existing buildings is essential for their maintenance, restoration, and management. Effective view planning for image collection significantly impacts the quality of photogrammetry-based 3D reconstruction. Intricate building structures, such as the overhangs, protrusions, and concave regions, can lead to under-sampled regions with traditional view planning methods, while excessively increasing the number of views require substantial computational resources and data collection efforts. To address these issues, this paper proposes a novel exploration-then-exploitation view planning strategy to achieve high-quality building reconstruction with minimal views. Firstly, the UAV no-fly regions and building attention regions are identified through semantic and geometric analysis of the images and coarse model during the exploration stage. Then, a novel optimization fitness function is mathematically formulated, considering building attention regions and reconstruction influential factors, including distance, incidence angle, parallax angle, and overlap. Furthermore, a modified sparrow search algorithm is proposed with the improved optimization mechanism and the integration of view planning physical model, enabling effective generation of optimal viewpoint set. Finally, the collisionfree shortest trajectory is designed, allowing the UAV to collect images and reconstruct a high-quality model during exploitation stage. Experiments in virtual and real-world scenarios validate the effectiveness of our proposed modified SSA mechanism and the view planning strategy. Results demonstrate that the modified SSA achieves higher convergence accuracy and speed compared to the original SSA, PSO and GA. Our strategy can generate more accurate and complete 3D reconstruction models with the same or fewer captured images compared to commonly used and state-of-the-art strategies.
Mobile edge computing (MEC) is an emerging technology that can be integrated with the Internet of vehicles (IoV) to enhance vehicle services with low latency and optimize task offloading efficiency. MEC technology enh...
详细信息
Mobile edge computing (MEC) is an emerging technology that can be integrated with the Internet of vehicles (IoV) to enhance vehicle services with low latency and optimize task offloading efficiency. MEC technology enhances the battery life of mobile devices by bringing storage and computational services closer to the edge of the network. However, challenges arise in areas with limited MEC server coverage. To address these challenges, this paper proposes a multi-hop task offloading model in MEC-IoV utilizing the modified sparrow search algorithm (MSSAMTO-IoV). The MSSAMTO-IoV model consists of two phases: candidate vehicle selection and task offloading. In the candidate vehicle selection mechanism, the model takes into account the k-hop wireless communication range. It identifies and selects candidate vehicles from neighboring vehicles for task offloading. The task offloading problem is then formulated as an optimization problem, aiming to minimize the delay. To solve this problem, MSSA is utilized, with modifications introduced to enhance the initial population quality and diversity of the standard SSA using the logistic map. Furthermore, an inertia weight is introduced to improve search speed, convergence rate, and exploration capabilities. The mean termination criterion is employed to avoid unnecessary iterations and minimize run-time. Additionally, a mutation strategy is employed to prevent falling into local optima. The simulation results demonstrate that MSSAMTO-IoV achieves faster convergence and outperforms BAT and SSA by approximately 2 times and 3 times, respectively. Moreover, MSSAMTO-IoV effectively reduces latency across different task sizes. For a 500 KB task, it reduces latency by approximately 5, 9, and 13% compared to basic SSA, BAT, and greedy algorithms, respectively.
The unmanned aerial vehicle (UAV) route planning problem mainly centralizes on the process of calculating the best route between the departure point and target point as well as avoiding obstructions on route to avoid ...
详细信息
The unmanned aerial vehicle (UAV) route planning problem mainly centralizes on the process of calculating the best route between the departure point and target point as well as avoiding obstructions on route to avoid collisions within a given flight area. A highly efficient route planning approach is required for this complex high dimensional optimization problem. However, many algorithms are infeasible or have low efficiency, particularly in the complex three-dimensional (3d) flight environment. In this paper, a modified sparrow search algorithm named CASSA has been presented to deal with this problem. Firstly, the 3d task space model and the UAV route planning cost functions are established, and the problem of route planning is transformed into a multi-dimensional function optimization problem. Secondly, the chaotic strategy is introduced to enhance the diversity of the population of the algorithm, and an adaptive inertia weight is used to balance the convergence rate and exploration capabilities of the algorithm. Finally, the Cauchy-Gaussian mutation strategy is adopted to enhance the capability of the algorithm to get rid of stagnation. The results of simulation demonstrate that the routes generated by CASSA are preferable to the sparrowsearchalgorithm (SSA), particle swarm optimization (PSO), artificial bee colony (ABC), and whale optimization algorithm (WOA) under the identical environment, which means that CASSA is more efficient for solving UAV route planning problem when taking all kinds of constraints into consideration.
The sparrowsearchalgorithm is a new and effective swarm intelligence method proposed in recent years and studied in many publications. Based on the basic principle of sparrowsearchalgorithm, this paper combines th...
详细信息
ISBN:
(纸本)9781450399449
The sparrowsearchalgorithm is a new and effective swarm intelligence method proposed in recent years and studied in many publications. Based on the basic principle of sparrowsearchalgorithm, this paper combines the inverse learning algorithm with the refined inverse solution to form an improved sparrowsearch (SSA) algorithm. Combining the fuzzy k-nearest neighbor method and the improved SSA, the numerical simulation of two-classes datasets and multi-classes datasets is carried out, and many numerical results are obtained, and the results are analyzed. At the same time, this paper lists the data comparison results and tables with other models. The hybrid SSA-FKNN proposed in this paper has a clear advantage in terms of accuracy (ACC).
Photovoltaic (PV) power penetration into the distribution grid has increased. PV power fluctuations, abrupt load changes, nonlinear loading, growing usage of portable electronic devices, electric cars low average powe...
详细信息
Photovoltaic (PV) power penetration into the distribution grid has increased. PV power fluctuations, abrupt load changes, nonlinear loading, growing usage of portable electronic devices, electric cars low average power and comparatively high pulse power needs, and other factors translate into severe grid instability. As a result, in these circumstances, power exchange between PV and the utility grid becomes a difficult task. Therefore, this article proposes a hydrogen/bromine (H-2/Br-2) redox flow battery and supercapacitor composite energy storage for a three phase grid tied PV system with multifunctional active power filter support to ensure grid codes. Further, the system is equipped with an unprecedented control technique that encompasses: an adaptive frequency tuned complex coefficient filter-phase locked loop that provides grid frequency and phase angle information under adverse grid conditions, a modified sparrow search algorithm tuned tilt integral derivative with filter plus double integral controllers are employed to regulate the control errors under various system dynamic and disturbance conditions, fractional order incremental conductance maximum power point tracking is incorporated to efficiently track the PV peak power irrespective of atmospheric variations, a holistic fast-acting power based energy management control employed for efficient regulation of load power and smooth out the PV power variation, and PV feedforward control dynamics to enhances system dynamics by reducing oscillations under various atmospheric conditions. The aim is to attain a smooth power transition with the grid at the unit power factor under normal and nonideal grid conditions. With reactive power injection, the control also maintains the voltage profile. During all these operations, no trade-off occurs with the system power quality. Matlab simulations and the real time simulation test bench results under unfavorable grid circumstances demonstrate the effectiveness of the pro
暂无评论