ShapeAug: Occlusion Augmentation for Event Camera Data
This addresses data scarcity and occlusion issues for event camera applications, particularly in automotive settings, but is incremental as it builds on existing augmentation techniques.
The paper tackles the challenge of limited training data and occlusion in event camera data by introducing a novel augmentation method that adds synthetic events for moving objects, resulting in up to 6.5% relative improvement in classification accuracy and up to 5% improvement in pedestrian detection.
Recently, Dynamic Vision Sensors (DVSs) sparked a lot of interest due to their inherent advantages over conventional RGB cameras. These advantages include a low latency, a high dynamic range and a low energy consumption. Nevertheless, the processing of DVS data using Deep Learning (DL) methods remains a challenge, particularly since the availability of event training data is still limited. This leads to a need for event data augmentation techniques in order to improve accuracy as well as to avoid over-fitting on the training data. Another challenge especially in real world automotive applications is occlusion, meaning one object is hindering the view onto the object behind it. In this paper, we present a novel event data augmentation approach, which addresses this problem by introducing synthetic events for randomly moving objects in a scene. We test our method on multiple DVS classification datasets, resulting in an relative improvement of up to 6.5 % in top1-accuracy. Moreover, we apply our augmentation technique on the real world Gen1 Automotive Event Dataset for object detection, where we especially improve the detection of pedestrians by up to 5 %.