4 results about "Flooding algorithm" patented technology

The present application relates to a smoke fire detection method based on feature matching and multi-frame time sequence fusion, which is suitable for highway fire detection scene. The method first screens out foreground change pictures based on the steady-state entropy change of video frame pixels. Then, the color and texture features of smoke fire are matched using the fast flooding algorithm to screen out candidate pictures from the foreground pictures. Next, a cache queue is established to store the candidate pictures and their timestamps, and the multi-frame time sequence image data in the queue is sent to the detection model based on the preset trigger condition. Finally, the multi-frame time sequence fusion smoke fire detection algorithm model extracts features and analyzes the time sequence fusion of the input multi-frame images, and outputs the final fire and smoke detection results. The present application realizes efficient detection through low-power cameras, reduces false alarm rate, improves complex environment monitoring distance, and has lower power cost.

The invention provides an automatic ridge line identification method and system based on hydrological analysis and density clustering, and the method comprises the steps: fusing the hydrological analysis with spatial clustering, elevation screening, morphological processing and other multi-step optimization, carrying out the automatic primary selection of ridge points through positive topography and zero convergence accumulation, and effectively removing noise and short branches through the combination of DBSCAN clustering and elevation quantile purification. A set of complete technical scheme of'preprocessing-positive terrain recognition-confluence analysis-clustering denoising-elevation screening-continuous optimization 'is constructed by utilizing a priority flood algorithm to efficiently fill pits and utilizing a skeletonization algorithm to optimize continuity, so that the adaptivity, geometric accuracy and processing efficiency of ridge line extraction are remarkably improved; a more reliable terrain skeleton data basis is provided for wind resource evaluation and fan site selection and layout, and finally the scientificity of wind power generation project planning and power generation capacity estimation is enhanced.

The application relates to a micro-power wireless hybrid routing networking method based on AI decision, which comprises the following steps: step S1, gateway beacon frame flooding issuing and node repeated packet discrimination; step S2, neighbor table collection and node state recording; step S3, AI-assisted path generation; step S4, fixed routing path registration and distribution; step S5, hybrid forwarding mechanism; step S6, AI-assisted path switching decision; and step S7, low power consumption and self-adaptive adjustment. The technical problems of the existing full flooding algorithm, such as serious broadcast storm, high node energy consumption, path redundancy, path failure in a dynamic environment, high maintenance cost and lack of intelligent switching, are solved.

The invention discloses an air quality index prediction method based on BP optimized by an improved dung beetle algorithm. Aiming at the problems that a BP neural network is difficult in parameter adjustment and poor in prediction model precision, a multi-strategy improved dung beetle optimization algorithm FLADBO is provided to optimize a prediction model of the BP neural network, Logistic chaotic mapping is introduced to solve the problem that initial population distribution is uneven, and an elite reverse strategy is introduced to improve population diversity; in the small dung beetle foraging stage, dynamic weights are used, and the optimization capacity of foraging dung beetles is improved; in order to balance the global search capability and the local search capability of the algorithm, the flood algorithm FLA is fused, and the parameter R is nonlinearly adjusted. And the global search capability and the local search capability of the algorithm are improved, so that the prediction precision and the stability of the algorithm are improved.