To address the safety hazards posed by unauthorized "black flight" of unmanned aerial vehicle (UAV) clusters, as well as the limitations of existing detection methods in tiny target recognition and complex environment adaptability, this paper proposes a real-time detection and counting method based on a feature fusion framework. The core contribution of this work is a novel multi-level fusion architecture that aggregates multi-scale visual features to enhance detection robustness under challenging conditions. First, we construct a multi scene UAV data set containing 7,113 images, and design a dedicated feature fusion module based on improved YOLOv9 backbone. The Haar Wavelet Down-sampling (H... More >

To address severe fire safety risks caused by electric motorcycles (EMs) and their batteries being illegally brought into building elevators, this paper presents a real-time EM detection and alarm system for elevator environments, built upon a multi-source information fusion framework and an improved YOLOv9. To elevate detection accuracy for EMs in confined elevator spaces, two core optimizations are embedded into the network: the Programmable Gradient Information (PGI) training strategy, and a lightweight Generalized Efficient Layer Aggregation Network (GELAN) backbone enhanced with depthwise separable convolution (DSConv). A dedicated dataset consisting of roughly 2,000 images is establish... More >