Can you tell a face from a HEVC bitstream?
This addresses the issue of computational efficiency in large-scale video analytics for applications like surveillance or streaming, though it appears incremental as it applies an existing method (CNN) to a new data source.
The paper tackled the problem of reducing computational resources in face detection by exploring whether faces can be detected directly from HEVC bitstreams without full image reconstruction, and demonstrated that this is possible with accuracy comparable to conventional methods.
Image and video analytics are being increasingly used on a massive scale. Not only is the amount of data growing, but the complexity of the data processing pipelines is also increasing, thereby exacerbating the problem. It is becoming increasingly important to save computational resources wherever possible. We focus on one of the poster problems of visual analytics -- face detection -- and approach the issue of reducing the computation by asking: Is it possible to detect a face without full image reconstruction from the High Efficiency Video Coding (HEVC) bitstream? We demonstrate that this is indeed possible, with accuracy comparable to conventional face detection, by training a Convolutional Neural Network on the output of the HEVC entropy decoder.