Architecture of a Low Latency H.264/AVC Video Codec for Robust ML based Image Classification

Abstract

The use of neural networks is considered as the state of the art in the field of image classification. A large number of different networks are available for this purpose, which, appropriately trained, permit a high level of classification accuracy. Typically, these networks are applied to uncompressed image data, since a corresponding training was also carried out using image data of similar high quality. However, if image data contains image errors, the classification accuracy deteriorates drastically. This applies in particular to coding artifacts which occur due to image and video compression. Typical application scenarios for video compression are narrowband transmission channels for which video coding is required but a subsequent classification is to be carried out on the receiver side. In this paper we present a special H.264/Advanced Video Codec (AVC) based video codec that allows certain regions of a picture to be coded with near constant picture quality in order to allow a reliable classification using neural networks, whereas the remaining image will be coded using constant bit rate. We have combined this feature with the ability to run with lowest latency properties, which is usually also required in remote control applications scenarios. The codec has been implemented as a fully hardwired High Definition video capable hardware architecture which is suitable for Field Programmable Gate Arrays.

An audio-video processing system design and implement based on CCSDS AOS protocol for manned spacecraft

“…The Audio-Video Processing System for Manned Spacecraft is designed to meet the requirements of audio-video communication between the ground crew and manned spacecraft. According to the audio-video encoding method [7][8][9] , the transmission mode, a processing system framework for manned spacecraft is designed which includes hardware resource layer, data processing layer, audio-video coding/decoding layer, data-driven model layer and application mode layer, as shown in Figure 2.…”