Supercharging Object Detection in Video: from Glacial to Lightning Speed

http://www.youtube.com/watch?v=rR6EIakYSZ0 In the following series I will explore different tools and techniques for doing object detection in streaming video in real time or faster. Starting with the baseline Python detector running slowly and gradually picking up speed. In these series In the course of these posts we will explore optimizing object detection in videos. We … Continue reading Supercharging Object Detection in Video: from Glacial to Lightning Speed →

Supercharging Object Detection in Videos: Setup

We started from the Python object detector performance as baseline (~ 19 fps). Next we ditch Python and all our pre-installed libraries and custom build everything. C++ will become the development environment not just because it's more "bare bones" than Python and thus more performant but also to access functionality not available in Python. Environment … Continue reading Supercharging Object Detection in Videos: Setup →

Supercharging Object Detection in Video: First App

Tensorflow C++ Video Detector It is time to validate all this arduous setup work, run our first C++ detector and reap the first benefits. You may clone this repository, which is a fork of this repository, modified and adapted to the modern times. Ensuring the Right Build Paths Note the following excerpt from CMakeLists.txt: The … Continue reading Supercharging Object Detection in Video: First App →

Supercharging Object Detection in Video: TensorRT 5

Source code for the finished project is here. NVIDIA TensorRT is a framework used to optimize deep networks for inference by performing surgery on graphs trained with popular deep learning frameworks: Tensorflow, Caffe, etc. Preparing the Tensorflow Graph Our code is based on the Uff SSD sample installed with TensorRT 5.0. The guide together with … Continue reading Supercharging Object Detection in Video: TensorRT 5 →

On the Margins: Non-maximum Suppression with Tensorflow

I'm writing a series of posts on supercharging object detection inference performance in video streams using Tensorflow and cool tech from NVIDIA: step-by-step, starting from 6 fps all the way up to 230. But before I start, this small post is about a cool little gem, which I think is often overlooked. Anyone in the … Continue reading On the Margins: Non-maximum Suppression with Tensorflow →