3D object detection is essential for autonomous driving, especially with the growing use of cost-effective visual cameras. However, relying solely on visual data for 3D detection presents key challenges: 1) Difficulty in obtaining accurate depth from single-frame images for precise 3D localization; 2) Challenge of projecting 3D bounding boxes consistently across multiple camera views for spatial coherence. To address these challenges, we propose a novel spatio-temporal transformer network that tracks object movement across frames using homography pose transformation matrices. This allows for the use of historical data to improve predictions for the current frame. Additionally, we integrate an advanced 3D Region of Interest (ROI) pooling technique, which refines 3D proposal generation, significantly enhancing detection precision. Our experimental results demonstrate the superior performance of our approach compared to existing methods, validating its effectiveness in real-world autonomous driving scenarios.