An improved particle swarm optimization (IPSO) was proposed in this paper to solve the problem that the linearly decreasing inertia weight (LDIW) of particle swarm optimization algorithm cannot adapt to the complex and nonlinear optimization process. The strategy of nonlinear decreasing inertia weight based on the concave function was used in this algorithm. The aggregation degree factor of the swarm was introduced in this new algorithm. And in each iteration process, the weight is changed dynamically based on the current aggregation degree factor and the iteration times, which provides the algorithm with dynamic adaptability. The experiments on the three classical functions show that the convergence speed of IPSO is significantly superior to LDIWPSO, and the convergence accuracy is increased.

No abstract

In order to overcome the problems of low recognition rate, high spatial accuracy error and low monitoring accuracy existing in traditional methods, this paper proposes a dynamic monitoring study of environmental quality in tourist scenic spots based on UAV multi-spectral remote sensing. In this method, DJI Matrice600Pro UAV equipped with multispectral camera is used to collect remote sensing images and preprocess them to obtain hyperspectral remote sensing images. The classification regression tree method is used to extract the environmental remote sensing information of scenic spots, and the camera calibration objective function is constructed according to the world coordinates corresponding to the feature points to dynamically monitor the environmental quality. The experimental results show that the recognition rate of remote sensing image is close to 100%, the spatial accuracy error is less than 4%, the system error data value is 0.15, and the monitoring accuracy is as high as 95%.

No abstract

No abstract