SODFormer: Streaming Object Detection with Transformer Using Events and Frames

Abstract--DAVIS camera, streaming two complementary sensing modalities of asynchronous events and frames, has gradually been used to address major object detection challenges (e.g., fast motion blur and low-light). However, how to effectively leverage rich temporal cues and fuse two heterogeneous visual streams remains a challenging endeavor. To address this challenge, we propose a novel streaming object detector with Transformer, namely SODFormer, which first integrates events and frames to continuously detect objects in an asynchronous manner. Technically, we first build a large-scale multimodal neuromorphic object detection dataset (i.e., PKU-DAVIS-SOD) over 1080.1k Then, we design a spatiotemporal Transformer architecture to detect objects via an end-to-end sequence prediction problem, where the novel temporal Transformer module leverages rich temporal cues from two visual streams to improve the detection performance. Finally, an asynchronous attention-based fusion module is proposed to integrate two heterogeneous sensing modalities and take complementary advantages from each end, which can be queried at any time to locate objects and break through the limited output frequency from synchronized frame-based fusion strategies. The results show that the proposed SODFormer outperforms four state-of-the-art methods and our eight baselines by a significant margin. We also show that our unifying framework works well even in cases where the conventional frame-based camera fails, e.g., high-speed motion and low-light conditions. We refer to this phenomenon as unimodal intelligent surveillance, robot vision, etc. In fact, with degradation because it is mainly caused by the limitations conventional frame-based cameras, object detection performance of unimodal cameras (see Figure 1). While event cameras [4], [5], [6] has suffered from a significant drop in are insensitive in static or extremely slow-motion scenes, some challenging conditions (e.g., high-speed motion blur, frame-based cameras directly provide static fine textures low-light, and overexposure). A key question still remains: (i.e., absolute brightness) conversely.