Path planning and obstacle avoidance are essential for autonomous driving cars. On the base of a self‐constructed smart obstacle avoidance car, which used a LeTMC‐520 depth camera and Jetson controller, this paper established a map of an unknown indoor environment based on depth information via SLAM technology. The Dijkstra algorithm is used as the global path planning algorithm and the dynamic window approach (DWA) as its local path planning algorithm, which are applied to the smart car, enabling it to successfully avoid obstacles from the planned initial position and reach the designated position. The tests on the smart car prove that the system can complete the functions of environment map establishment, path planning and navigation, and obstacle avoidance.

The energy sector of todays Rwanda has made a remarkable growth to some extent in recent years. Although Rwanda has natural energy resources (e.g., hydro, solar, and methane gas, etc.), the country currently has an installed electricity generation capacity of only 226.7MW from its 45 power plants for a population of about 13 million in 2021. The current national rate of electrification in Rwanda is estimated to 54.5 (i.e.; 39.7 grid-connected and 14.8 off-grid connected systems). This clearly demonstrates that having access to electricity is still a challenge to numerous people not to mention some blackout-related problems. With the ambition of having electricity for all, concentrated solar power (CSP) and photovoltaic (PV) systems are regarded as solutions to the lack of electricity. The production of CSP has still not been seriously considered in Rwanda, even though the technology has attracted significant global attention. Heavy usage of conventional power has led to the depletion of fossil fuels. At the same time, it has highlighted its unfriendly relationship with the environment because of carbon dioxide (CO₂) emission, which is a major cause of global warming. Solar power is another source of electricity that has the potential to generate electricity in Rwanda. Firstly, this paper summarizes the present status of CSP and PV systems in Rwanda. Secondly, we conducted a technoeconomic analysis for CSP and PV systems by considering their strengths, weaknesses, opportunities, and threats (SWOT). The input data of the SWOT analysis were obtained from relevant shareholders from the government, power producers, minigrid, off-grid, and private companies in Rwanda. Lastly, the technical and economical feasibilities of CSP and PV microgrid systems in off-grid areas of Rwanda were conducted using the system advisor model (SAM). The simulation results indicate that the off-grid PV microgrid system for the rural community is the most cost-effective because of its low net present cost (NPC). According to the past literature, the outcomes of this paper through the SWOT analyses and the results obtained from the SAM model, both the CSP and PV systems could undoubtedly play a vital role in Rwandas rural electrification. In fact, PV systems are strongly recommended in Rwanda because they are rapid and cost-effective ways to provide utility-scale electricity for off-grid modern energy services to the millions of people who lack electricity access.

This study proposes a novel log end face feature extraction and matching method based on Swin Transformer V2, aiming to address limitations in accuracy and speed faced by traditional deep learning models, like InceptionResNetV2 and Vision Transformer. Accurate log identification is crucial for forestry and wood supply chain management, especially given the growing reliance on timber imports to meet industrial demands in construction, furniture manufacturing, and paper production. Our dataset comprises images of coniferous timber, specifically Scots pine (Pinus sylvestris L.), reflecting its significance as an essential imported resource in China’s timber industry. By leveraging Swin Transformer V2 as the backbone, our method enhances feature extraction and achieves a significant accuracy improvement from 84.0% to 97.7% under random rotation angles while reducing the average matching time per log to 0.249 s. The model was evaluated under fixed and random rotation augmentations, and the results demonstrated Swin Transformer V2’s superior clustering ability, as confirmed by t-SNE visualization. Unlike InceptionResNetV2, the proposed model maintains high accuracy and efficiency even as the feature database size increases, making it suitable for large-scale applications. This approach provides a more accurate and efficient solution for log end-face recognition, supporting the development of high-throughput wood identification systems critical for forestry automation and the global timber trade.

In order to address the challenges posed by elevated manual labor costs and limited automation in traditional log diameter grading and sorting processes, this paper centers on the design and research of an intelligent log diameter grading and sorting line utilizing machine vision. The study focuses on logs with smaller diameters located in Fujian province, China. By analyzing production requirements, the study formulates the structure of the feeding, alignment, detection, and sorting zones to fulfill sorting functions. Using the YOLOv5 model, the system achieves accurate log end face positioning, and the diameter is computed through a designated algorithm. The operational process of the system is examined, and the control logic governing the production line is elucidated. Evaluating the practical performance of the production line, the study assesses the accuracy of diameter recognition, precision in grading, and operational efficiency. The results reveal that the absolute error in diameter detection for the sorting line averages 1.12 mm, with sorting accuracy exceeding 95%. The sorting line can automatically categorize logs with diameters ranging from 60 mm to 300 mm and lengths ranging from 2 m to 6 m, achieving an annual sorting capacity of 120,000 to 130,000 cubic meters. The research findings illustrate that the system fulfills the industry’s demands for log diameter grading and sorting, thereby enhancing economic efficiency for enterprises.

Narrowband image extraction is an essential preprocessing for multispectral imaging of filter array. This paper proposes an automatic method to extract narrowband images from a multispectral image. During offline phase, the method first employs horizontal and vertical projections to obtain initial positions of subsampling points. Then, integerpixel searching and half-pixel searching optimizes subsampling location. During on-line phase, 1:4 or 1:16 interpolation generates interpolation grids. Finally, four narrowband images are obtained according to the optimized subsampling points and interpolation grids. The experimental result indicates that this method effectively extracts narrowband images from originally mosaic images of multiple spectrums.

A new hardware algorithm architecture based on field programmable gate array (FPGA) is proposed to address the complex background situation where the traditional edge detection algorithm on a software platform is less effective for UAV apron localization and cannot meet the demand for real-time processing when the image data volume is too large. The architecture uses a combination of morphology and edge detection to ensure high-precision localization of the UAV apron while considering real-time localization. The hardware test results show that the system achieves 96.5% accuracy in image localization of the UAV apron and 13.06ms localization time.