A Double Deep Learning-Based Solution for Efficient Event Data Coding and Classification

Event cameras have the ability to capture asynchronous per-pixel brightness changes, usually called “events”, offering advantages over traditional frame-based cameras for computer vision tasks. Efficiently coding event data is critical for practical transmission and storage, given the very significant number of events captured. This paper proposes a novel double deep learning-based solution for efficient event data coding and classification, using a point cloud-based representation for events. Moreover, since the conversions from events to point clouds and back to events are key steps in the proposed solution, novel tools are proposed and their impact is evaluated in terms of compression and classification performance. Experimental results show that it is possible to achieve a classification performance for decompressed events which is similar to the one for original events, even after applying a lossy point cloud codec, notably the recent deep learning-based JPEG Pleno Point Cloud Coding standard, with a clear rate reduction. Experimental results also demonstrate that events coded using the JPEG standard achieve better classification performance than those coded using the conventional lossy MPEG Geometry-based Point Cloud Coding standard for the same rate. Furthermore, the adoption of deep learning-based coding offers future high potential for performing computer vision tasks in the compressed domain, which allows skipping the decoding stage, thus mitigating the impact of compression artifacts.