Real-world optimization problems are becoming increasingly complex and require effective and versatile algorithms to provide reliable solutions. However, the no-free-lunch theorem indicates that no single optimization algorithm can solve all optimization problems accurately. Consequently, new optimization methods are required. Inspired by the search mechanism of the Rapidly-exploring Random Trees (RRT) algorithm commonly used in robot path planning, we propose a novel metaheuristic algorithm called RRT-based Optimizer (RRTO). This is the first time that the concept of the RRT algorithm has been integrated with metaheuristic algorithms. The key innovation of RRTO is its three position update strategies: adaptive step size wandering, absolute difference-based adaptive step size, and boundary-based adaptive step size. These strategies enable RRTO to efficiently explore the search space while guiding the population toward high-quality solutions. To evaluate its effectiveness, the RRTO is tested on 23 standard benchmark functions, the CEC2017 test suite, and six constrained optimization problems. In comparison with more than eight peer metaheuristic algorithms, RRTO achieves competitive results across diverse problems. Specifically, among the 35 metrics across the six constrained optimization problems, RRTO ranks first in 26 and second in 4. The source code and associated files for RRTO are publicly available at: https://ww2.mathworks.cn/matlabcentral/fileexchange/169548-rrt-based-optimizer.

Semi-global matching (SGM) has been widely used in binocular vision. In spite of its good efficiency, SGM still has difficulties in dealing with low-texture regions. In this paper, an SGM algorithm based on multi-scale information fusion (MSIF), named SGM-MSIF, is proposed by combining multi-path cost aggregation and cross-scale cost aggregation (CSCA). Firstly, the stereo pairs at different scales are obtained by Gaussian pyramid down-sampling. The initial matching cost volumes at different scales are computed by combining census transform and color information. Then, the multi-path cost aggregation in SGM is introduced into the cost aggregation at each scale and the aggregated cost volumes are fused by CSCA. Thirdly, the disparity map is optimized by internal left-right consistency check and median filter. Finally, experiments are conducted on Middlebury datasets to evaluate the proposed algorithm. Experimental results show that the average error matching rate (EMR) of the proposed SGM-MSIF algorithm reduced by 1.96% compared with SGM. Compared with classical cross-scale stereo matching algorithm, the average EMR of SGM-MSIF algorithm reduced by 0.92%, while the processing efficiency increased by 58.7%. In terms of overall performance, the proposed algorithm outperforms the classic SGM and CSCA algorithms. It can achieve high matching accuracy and high processing efficiency for binocular vision applications, especially for those with low-texture regions.

As a crucial technology for improving the autonomous sensing capability of optical sensors on unmanned aerial vehicles (UAVs), object detection has emerged as a research focus in the UAV patrol inspection. To address the problem of high computational complexity in detection models carried by UAV, a lightweight network model based on YOLO v7 is designed. Based on this model, a smoke detection algorithm is developed. Firstly, a new multi-parameter gated activation function (Better-mish) based on Mish function is constructed. Secondly, CBS and CA modules are improved based on the Better-mish. The Improved-CA is replaced with the Conv in MPConv to build CA-MPConv. The improved modules are added into backbone of the model. Thirdly, the backbone is reconstructed in combination with RepVGG module. An improved YOLOv7 lightweight model is proposed and a smoke detection algorithm based on this model is developed. Finally, several experiments are conducted on Smoke and COCO datasets. Experimental results show three key points as follows. 1) Compared with SiLU, Mish and other activation functions, Better-mish can alleviate the gradient disappearance of neural networks in the saturation region. 2) Compared with YOLO v7, the improved YOLO v7 model reduces computational complexity by 93.24 % and only increases model parameters by less than 2 %. 3) The algorithm can maintain effective recognition of smoke images at low computational complexity. The smoke detection algorithm provides a theoretical basis and an effective algorithm for the early warning of fire hazards in the UAV patrol inspection.

Detecting small objects within extensive remote sensing images captured by unmanned aerial vehicle (UAV) optical sensors is crucial for a variety of military and civilian purposes, but it poses considerable challenges. To address the difficulties associated with the numerous parameters and the high computational requirements of existing object detection models, as well as the inadequate performance in identifying small objects in remote sensing images (RSIs) captured by UAV optical sensors, this paper proposes a lightweight model for small object detection. Firstly, Focal Scalable Intersection over Union Loss (SIoU) loss derived by integrating the concept of Focal loss into the traditional SIoU loss. Secondly, this study utilizes channel attention (CA) and GhostNet to reconstruct the backbone. A layer specifically designed for detecting small objects is incorporated into YOLOv5s utilized a depth residual network neck. Furthermore, this study establishes a small fire dataset and evaluate this model on the small fire, AI-TOD dataset and DOTA dataset. Experimental results show that the proposed model achieves the lightweight goal while maintaining high detection performance for small objects.

As the most common serious disaster, fire may cause a lot of damages. Early detection and treatment of fires are of great significance to ensure public safety and to reduce losses caused by fires. However, traditional fire detectors are facing some focus issues such as low sensitivity and limited detection scenes. To overcome these problems, a video fire detection hybrid method based on random forest (RF) feature selection and back propagation (BP) neural network is proposed. The improved flame color model in RGB and HSI space and the visual background extractor (ViBe) in moving target detection algorithm are used to segment the suspected flame regions. Then, multidimensional features of flames are extracted from the suspected regions, and these extracted features are combined and selected according to the RF feature importance analysis. Finally, a BP neural network model is constructed for multifeature fusion and fire recognition. The test results on several experimental video sets show that the proposed method can effectively avoid feature interference and has an excellent recognition effect on fires in a variety of scenarios. The proposed method is applicable for fire recognition applied in video surveillance and detection robots.