<p>Existing traffic light detection algorithms suffer from high computational overhead and low detection speeds, making it difficult to meet the real-time demands. Therefore, reducing computational overhead and increasing detection speed, while maintaining accuracy, becomes a critical challenge. To tackle these, this paper proposes GAD-DETR, an enhanced RT-DETR-based network. First, inspired by the approach of GhostNet to minimize computational redundancy and integrate reparameterized convolution (RepConv), the GRELAN module is developed to restructure the backbone network which significantly decreases model size and parameters while enhancing detection speed. To improve the recognition of small objects, whose features tend to be diluted as the network deepens, ADown is introduced to replace standard convolution for downsampling. Finally, a lightweight feature fusion module, DGSFM, is designed to further reduce computational costs and enhance efficiency. Experimental results indicate that GAD-DETR achieves a detection precision of 95.9% while significantly optimizing efficiency. The model size is reduced by 50.3%, with parameters and computations decreased by 50.8% and 51.2%, respectively. FPS increases from 76.7 to 117.8, demonstrating that the proposed algorithm achieves lightweight, real-time traffic light detection.</p>