Enhanced LSTM with Robust Memory and Motion Learning for Event-based Object Detection
Open Access
- 9 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 7478-7486
Abstract
Event cameras have shown great potential for autonomous driving due to their high temporal resolution and wide dynamic range. However, most existing event-based object detectors rely on LSTM-based temporal aggregation, which remains insufficient in highly dynamic scenes. In particular, conventional LSTMs depend on a single global memory to model temporal dependencies, making them vulnerable to abrupt variations in target-related event patterns and thus limiting robustness. Moreover, their implicit temporal modeling is not well suited to capturing motion dynamics explicitly, which often leads to inaccurate object localization. To address these issues, we propose EDeMM, a novel event-based object detection framework with enhanced memory and motion modeling capabilities. Specifically, we design a Double-Phase LSTM (DPLSTM) consisting of Outer and Inner recurrent units to jointly capture global temporal dependencies and local temporal variations, thereby improving memory robustness under dynamically changing inputs. We further introduce a Motion-Enhancement Module (MEM) to explicitly strengthen motion trend representation and improve localization accuracy in highly dynamic scenarios. Extensive experiments on the GEN1 and 1Mpx datasets demonstrate that EDeMM achieves superior detection performance and robustness under challenging real-world conditions.Keywords
Funding Information
- National Natural Science Foundation of China (62501435)
- National Natural Science Foundation of China (62402366)
This publication has 13 references indexed in Scilit:
- Asynchronous Event-Based Corner Detection Using Adaptive Time ThresholdIEEE Sensors Journal, 2023
- Asynchronous Spatio-Temporal Memory Network for Continuous Event-Based Object DetectionIEEE Transactions on Image Processing, 2022
- SPADE-E2VID: Spatially-Adaptive Denormalization for Event-Based Video ReconstructionIEEE Transactions on Image Processing, 2021
- A Differentiable Recurrent Surface for Asynchronous Event-Based Data2020
- High Speed and High Dynamic Range Video with an Event CameraIEEE Transactions on Pattern Analysis and Machine Intelligence, 2019
- Object Detection with Discriminatively Trained Part-Based ModelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- Spiking Neuron Models2002
- Learning to Forget: Continual Prediction with LSTMNeural Computation, 2000
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998