On December 2, 2024, it was reported that the China National Intellectual Property Administration information showed that CETC Yizhihang (Chongqing) Technology Co., Ltd. applied for a patent entitled "a target detection method oriented to UAV perspective", with the publication number of CN 119048730 A and the application date of August 2024.
The patent abstract shows that the present invention belongs to the field of object recognition and detection technology, and particularly relates to a method for object detection from the perspective of unmanned aerial vehicles, comprising the following steps: S1. Constructing an object detection network CT-RODN; CT-RODN includes a backbone network, feature fusion module, and attention prediction head; The backbone network includes a frequency domain based block composite attention module FBAM and a frequency domain based CNN-Transformer module FCTB; The FBAM module is used to enhance the understanding of small airborne targets by combining frequency domain analysis; The FCTB module is used to process and aggregate the feature maps obtained by convolution to obtain global information of the image; The feature fusion module is used to fuse the extracted features at various levels; The attention prediction head is used to extract key regions from the fused feature map and perform object detection and recognition based on the extracted key regions. This method can ensure the effectiveness of small target detection in high dynamic environments, thereby ensuring the reliability of target detection results for drones in complex backgrounds and multi-scale target scenes.
