How to run inferece on the video input?

I have a trained model by using the faster rcnn , I can run inference on the images using the tlt-infer command. How to run inference on the video input?

Please see “Integrating a FasterRCNN model” in tlt user guide https://docs.nvidia.com/metropolis/TLT/tlt-getting-started-guide/index.html#deepstream_deployment

More info is also in https://devtalk.nvidia.com/default/topic/1065558/transfer-learning-toolkit/trt-engine-deployment/