Urban object detection algorithm based on feature enhancement and progressive dynamic aggregation strategy

Traditional target detection models face challenges in recognizing urban high-altitude remote sensing targets due to complex background noise and significant variations in target scale. These challenges can result in loss of feature information and missed object detection. In light of this, this article introduces a novel dual-gated feature mechanism and adaptive fusion strategy. First, the dual-gated feature mechanism enables selective suppression or enhancement of multilevel features, thereby reducing the interference of complex environmental noise in remote sensing on feature fusion. Second, the adaptive fusion strategy and module facilitate multilevel scale feature fusion, and by dynamically learning fusion weights, they mitigate scale conflicts during the feature extraction process and preserve feature information. Experimental comparisons and analysis on the RSOD and NWPU VHR-10 public datasets showcase the effectiveness of the proposed method. In comparison to current mainstream detection methods, the improved approach presented in this article demonstrates significant advantages in terms of detection performance and efficiency.