DS MYOLO: A Reliable Object Detector Based on SSMs for Driving Scenarios

TL;DR

DS MYOLO is a new real-time object detector for driving scenarios that combines simplified selective scanning and efficient channel attention to improve global feature capture and detection accuracy.

Contribution

It introduces DS MYOLO, a novel detector using SimVSS and ECAConv modules, inspired by Mamba, to enhance global feature integration with low computational cost.

Findings

Outperforms comparable YOLO detectors on CCTSDB 2021 and VLD-45 datasets.

Achieves high detection accuracy with real-time processing.

Demonstrates robustness and efficiency in driving scenario applications.

Abstract

Accurate real-time object detection enhances the safety of advanced driver-assistance systems, making it an essential component in driving scenarios. With the rapid development of deep learning technology, CNN-based YOLO real-time object detectors have gained significant attention. However, the local focus of CNNs results in performance bottlenecks. To further enhance detector performance, researchers have introduced Transformer-based self-attention mechanisms to leverage global receptive fields, but their quadratic complexity incurs substantial computational costs. Recently, Mamba, with its linear complexity, has made significant progress through global selective scanning. Inspired by Mamba's outstanding performance, we propose a novel object detector: DS MYOLO. This detector captures global feature information through a simplified selective scanning fusion block (SimVSS Block) and effectively integrates the network's deep features. Additionally, we introduce an efficient channel attention convolution (ECAConv) that enhances cross-channel feature interaction while maintaining low computational complexity. Extensive experiments on the CCTSDB 2021 and VLD-45 driving scenarios datasets demonstrate that DS MYOLO exhibits significant potential and competitive advantage among similarly scaled YOLO series real-time object detectors.