This study aims to introduce the integrated approach, namely the integration of the Faster R-CNN technique and Optical gas imaging (OGI) for real-time natural gas leak detection of offshore platforms. OGI is used to record large number of leak videos which are essential to develop the desirable Faster R-CNN model. Due to the fact that the natural gas leak incidents are rare on the offshore platforms, it is difficult to record large number of the real-world leak videos by using the OGI. This study firstly proposes the strategy to simulate the OGI by the CFD tool. The proposed strategy could generate large number of virtual infrared images. Based on the infrared images, the Faster R-CNN approach is trained and its performance is tested. A case study of deep-water drilling platform is conducted. The results demonstrate the feasibility of the proposed strategy as well as the competing performance of the Faster R-CNN approach for the real-time automatic natural gas leak detection of offshore platforms.