EDeNN: Event Decay Neural Networks for low latency vision
This addresses the problem of high latency and inefficiency in event-based vision systems for robotics and real-time applications, representing a novel paradigm shift rather than an incremental improvement.
The paper tackled the inefficiency of using image frames for event camera data by developing a neural network that operates directly on event streams, achieving state-of-the-art performance in angular velocity regression and competitive optical flow estimation with processing latency less than 1/10 of other implementations.
Despite the success of neural networks in computer vision tasks, digital 'neurons' are a very loose approximation of biological neurons. Today's learning approaches are designed to function on digital devices with digital data representations such as image frames. In contrast, biological vision systems are generally much more capable and efficient than state-of-the-art digital computer vision algorithms. Event cameras are an emerging sensor technology which imitates biological vision with asynchronously firing pixels, eschewing the concept of the image frame. To leverage modern learning techniques, many event-based algorithms are forced to accumulate events back to image frames, somewhat squandering the advantages of event cameras. We follow the opposite paradigm and develop a new type of neural network which operates closer to the original event data stream. We demonstrate state-of-the-art performance in angular velocity regression and competitive optical flow estimation, while avoiding difficulties related to training SNN. Furthermore, the processing latency of our proposed approach is less than 1/10 any other implementation, while continuous inference increases this improvement by another order of magnitude.